<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Subculture Science Research Group&#39;s Blog</title>
    <link>https://www.subcul-science.com/en/</link>
    <description>Recent content on Subculture Science Research Group&#39;s Blog</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Sun, 15 Nov 2026 15:30:00 +0900</lastBuildDate>
    <atom:link href="https://www.subcul-science.com/en/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Small LLM That Answers Before It Thinks: Four Roles and a Comparison Design</title>
      <link>https://www.subcul-science.com/en/post/20261115umigame-gan-solution/</link>
      <pubDate>Sun, 15 Nov 2026 15:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115umigame-gan-solution/</guid>
      <description>Small LLMs commit to a hunch and stop tracking candidates. This post breaks down the failure modes, describes a loop that grows a creator and a solver in turn, and reports how far a per-turn reward actually moved the numbers.</description>
    </item>
    <item>
      <title>Co-evolving Four Roles, GAN-Style: The Testbed Behind umigame_GAN</title>
      <link>https://www.subcul-science.com/en/post/20261115umigame-gan-tech/</link>
      <pubDate>Sun, 15 Nov 2026 15:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115umigame-gan-tech/</guid>
      <description>A testbed for strengthening trial-and-error reasoning in small LLMs: four competing roles, a domain-independent loop, R-Zero and EDA style rewards, and an MLX LoRA comparison design. Code excerpts and measured numbers from the repository.</description>
    </item>
    <item>
      <title>When the Timeline Fills Up with Reposts and Copies: Designing a Filter That Only Changes What You See</title>
      <link>https://www.subcul-science.com/en/post/20261115x-original-filter-solution/</link>
      <pubDate>Sun, 15 Nov 2026 15:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115x-original-filter-solution/</guid>
      <description>How to fix a timeline buried under reposts and re-uploaded images without deleting anything: why mute and keyword filters fall short, how to pick the original by timestamp, and how to keep a way back when the filter guesses wrong.</description>
    </item>
    <item>
      <title>Detecting Duplicate Images with dHash and Hamming Distance in a Chrome Extension</title>
      <link>https://www.subcul-science.com/en/post/20261115x-original-filter-tech/</link>
      <pubDate>Sun, 15 Nov 2026 15:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115x-original-filter-tech/</guid>
      <description>How the X Original Filter Chrome extension hides reposts and duplicate images on X: a 64-bit dHash built from a 9x8 thumbnail, Hamming distance matching, an IndexedDB record of first sightings, and a rule that the earlier timestamp wins.</description>
    </item>
    <item>
      <title>Less Time Searching the Cargo Area: A Load Plan That Does Not Cram the Van</title>
      <link>https://www.subcul-science.com/en/post/202611153d-packing-solution/</link>
      <pubDate>Sun, 15 Nov 2026 14:50:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/202611153d-packing-solution/</guid>
      <description>Work inside the cargo area takes about 18% of a delivery driver&amp;rsquo;s time, and the cause is cramming the van full at the cost of delivery order. This post covers a load plan that stops at the volume the order can survive, and the simulation used to measure it.</description>
    </item>
    <item>
      <title>Loading 80 Parcels into a Kei Van in Seconds: Extreme Points and an Independent Validator</title>
      <link>https://www.subcul-science.com/en/post/202611153d-packing-tech/</link>
      <pubDate>Sun, 15 Nov 2026 14:40:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/202611153d-packing-tech/</guid>
      <description>How a 3D load-planning demo builds stacks that respect delivery order, this-side-up, load bearing, and support ratio. Extreme points plus GRASP generate candidates, and a validator written independently of the solver decides whether a plan is feasible.</description>
    </item>
    <item>
      <title>Folding the Search for a Repost&#39;s Origin into One Query</title>
      <link>https://www.subcul-science.com/en/post/20261115origin-finder-solution/</link>
      <pubDate>Sun, 15 Nov 2026 14:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115origin-finder-solution/</guid>
      <description>Tracing a reposted image back to its original post is a manual loop across several reverse image search engines and dozens of page dates. How Origin Finder collapses that loop, and what it still leaves to a human.</description>
    </item>
    <item>
      <title>Finding the Original of a Reposted Image: How Origin Finder Combines Five Reverse Image Searches</title>
      <link>https://www.subcul-science.com/en/post/20261115origin-finder-tech/</link>
      <pubDate>Sun, 15 Nov 2026 14:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115origin-finder-tech/</guid>
      <description>How Origin Finder calls five reverse image search engines in parallel, decides which candidates are the same image in staged passes, and returns the oldest post as the origin. Code excerpts and measured numbers from the repository.</description>
    </item>
    <item>
      <title>Turning a Drawing-Only Part Back into Editable 3D: How image2CAD Keeps Dimensions and History</title>
      <link>https://www.subcul-science.com/en/post/20261115image2cad-solution/</link>
      <pubDate>Sun, 15 Nov 2026 14:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115image2cad-solution/</guid>
      <description>When the CAD file is gone and only a drawing survives, modelling the shape by hand is not enough: the first dimension edit breaks it. How image2CAD treats drawing dimensions as the source of truth, tests editability mechanically, and uses three independent checks to avoid false accepts.</description>
    </item>
    <item>
      <title>From 2D Drawings to Editable FreeCAD Models: the image2CAD Pipeline</title>
      <link>https://www.subcul-science.com/en/post/20261115image2cad-tech/</link>
      <pubDate>Sun, 15 Nov 2026 14:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115image2cad-tech/</guid>
      <description>image2CAD turns a drawing PDF or scan into a history-based FreeCAD PartDesign model. Two Python processes talk only through a JSON IR, dimensions stay as expressions, and three checks decide which candidate gets accepted. A tour of the design with code from the repository.</description>
    </item>
    <item>
      <title>Turning One Image into a Talking 3D Character: Making the Build Repeatable</title>
      <link>https://www.subcul-science.com/en/post/202611153d-chatting-solution/</link>
      <pubDate>Sun, 15 Nov 2026 13:50:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/202611153d-chatting-solution/</guid>
      <description>Full mesh generation gives a different character on every run, and hand editing leaves no record. How driving VRoid Studio through an MCP turned character work into a repeatable cycle of change, export, compare, and accept.</description>
    </item>
    <item>
      <title>Building a Talking 3D Character App with FastAPI, TypeScript, VRM and Passkeys</title>
      <link>https://www.subcul-science.com/en/post/202611153d-chatting-tech/</link>
      <pubDate>Sun, 15 Nov 2026 13:40:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/202611153d-chatting-tech/</guid>
      <description>How 3D Chatting is put together: FastAPI middleware ordering and passkey registration, VRM handling in TypeScript and three.js, and an MCP server that operates VRoid Studio through screenshots and OCR.</description>
    </item>
    <item>
      <title>Reading Trend Performance in Numbers — Filling the Blind Spot in View-Count Rankings</title>
      <link>https://www.subcul-science.com/en/post/20261115youtube-analyser-solution/</link>
      <pubDate>Sun, 15 Nov 2026 13:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115youtube-analyser-solution/</guid>
      <description>A view-count ranking cannot tell you whether a trend video worked. This is how one app puts a viral coefficient, a median, and an engagement rate on one screen, aligns the comparison group, and where those numbers still fail.</description>
    </item>
    <item>
      <title>Trend Analysis with Next.js and the YouTube Data API — Designing Filters and Aggregation</title>
      <link>https://www.subcul-science.com/en/post/20261115youtube-analyser-tech/</link>
      <pubDate>Sun, 15 Nov 2026 13:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115youtube-analyser-tech/</guid>
      <description>How a Next.js app filters YouTube trend videos and aggregates views, engagement rate, and a viral coefficient: a Route Handler that keeps the API key server-side, a three-call fetch chain, and a quota estimate the README undercounts.</description>
    </item>
    <item>
      <title>Stop Calculating Business Trip Travel Time by Hand</title>
      <link>https://www.subcul-science.com/en/post/20261115booking-butler-solution/</link>
      <pubDate>Sun, 15 Nov 2026 13:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115booking-butler-solution/</guid>
      <description>Copying addresses into a map app and subtracting travel time from every meeting is a nightly ritual for anyone who travels for work. BookingButler derives the origin from the calendar and works backwards from arrival. Here is what got automated and what stayed manual.</description>
    </item>
    <item>
      <title>A Travel Calendar in Go, Gorilla Mux, and React: How BookingButler Is Built</title>
      <link>https://www.subcul-science.com/en/post/20261115booking-butler-tech/</link>
      <pubDate>Sun, 15 Nov 2026 13:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115booking-butler-tech/</guid>
      <description>How BookingButler turns Google Calendar events into departure times: a Go + Gorilla Mux API that exchanges the auth code, resolves stations with Google Maps, and fetches routes from NAVITIME. The design, the code, and the gaps left in it.</description>
    </item>
    <item>
      <title>A Search-Enabled Chat UI in the Shortest Path: A Research Assistant with Streamlit and a ReAct Agent</title>
      <link>https://www.subcul-science.com/en/post/20261115chatgpt-streamlit-solution/</link>
      <pubDate>Sun, 15 Nov 2026 12:50:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115chatgpt-streamlit-solution/</guid>
      <description>Ask a chat model about last week and you get stale knowledge. Then you search in another tab, paste the result, and ask again. Here is how a LangChain ReAct agent with Google and Wikipedia tools collapses that loop into one Streamlit file, and where the approach stops working.</description>
    </item>
    <item>
      <title>Inside chatGPT_streamlit: A Search-Enabled Chat UI with Streamlit and LangChain ReAct</title>
      <link>https://www.subcul-science.com/en/post/20261115chatgpt-streamlit-tech/</link>
      <pubDate>Sun, 15 Nov 2026 12:40:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115chatgpt-streamlit-tech/</guid>
      <description>A tour of chatGPT_streamlit: a LangChain ReAct agent with Google and Wikipedia tools behind a Streamlit chat UI. How the tools, prefix/suffix prompt, and session_state history are wired, plus the version pinning and the gaps between README and code.</description>
    </item>
    <item>
      <title>Cutting the Cost of Knowing What Is Trending on X</title>
      <link>https://www.subcul-science.com/en/post/20261115topic-digestx-solution/</link>
      <pubDate>Sun, 15 Nov 2026 12:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115topic-digestx-solution/</guid>
      <description>Following an X timeline costs three things: finding the right posts, reading them, and summarizing them. How TopicDigestX moves each to a server, the trade-offs, and what is still not built.</description>
    </item>
    <item>
      <title>Building the TopicDigestX Backend on FastAPI and PostgreSQL</title>
      <link>https://www.subcul-science.com/en/post/20261115topic-digestx-tech/</link>
      <pubDate>Sun, 15 Nov 2026 12:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115topic-digestx-tech/</guid>
      <description>How TopicDigestX wires FastAPI, PostgreSQL, and a planned Alembic layer: Pydantic Settings, one SQLAlchemy model, and the dependency gaps that still block the database path.</description>
    </item>
    <item>
      <title>Reversing the Order of House Hunting: Designing a Gym-First Search</title>
      <link>https://www.subcul-science.com/en/post/20261115muscle-realestate-solution/</link>
      <pubDate>Sun, 15 Nov 2026 12:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115muscle-realestate-solution/</guid>
      <description>House hunting starts with the office; the gym comes after the move. Muscle Real Estate flips that order into four stages: facilities, commute area, gym, property. The design, its trade-offs, and what is still mock.</description>
    </item>
    <item>
      <title>Choosing a Home From the Gym Outward: A Go (Gin) &#43; React API for Commute-Aware Search</title>
      <link>https://www.subcul-science.com/en/post/20261115muscle-realestate-tech/</link>
      <pubDate>Sun, 15 Nov 2026 12:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115muscle-realestate-tech/</guid>
      <description>Muscle Real Estate reverses the usual house hunt: pick a gym first, filter by commute area, then look at nearby properties. The layering in Go and Gin, the PostGIS complex search, and the commute API that is still mock.</description>
    </item>
    <item>
      <title>Fine-tuning a Japanese LLM Without a GPU: One Mac, One Pipeline</title>
      <link>https://www.subcul-science.com/en/post/20261115ft-llm-solution/</link>
      <pubDate>Sun, 15 Nov 2026 11:50:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115ft-llm-solution/</guid>
      <description>No CUDA GPU, no cloud quota, no separate evaluation scripts. How FT_LLM turns fine-tuning a Japanese LLM into one Mac workflow, and where the approach still falls short.</description>
    </item>
    <item>
      <title>A LoRA Training Pipeline for Japanese LLMs on MLX: LFM2.5-1.2B-JP</title>
      <link>https://www.subcul-science.com/en/post/20261115ft-llm-tech/</link>
      <pubDate>Sun, 15 Nov 2026 11:40:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115ft-llm-tech/</guid>
      <description>How FT_LLM fine-tunes LFM2.5-1.2B-JP with LoRA on Apple Silicon: config resolution, two execution modes, a chunked loss for long sequences, early stopping, and character-level evaluation, with code excerpts and measured numbers.</description>
    </item>
    <item>
      <title>Three Constraints in Setlist Planning, and How Each One Was Removed</title>
      <link>https://www.subcul-science.com/en/post/20261115setlist-automation-solution/</link>
      <pubDate>Sun, 15 Nov 2026 11:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115setlist-automation-solution/</guid>
      <description>Planning a setlist where members switch instruments runs into three constraints: transition cost, stage time, and where the break goes. How the manual limits were framed, and how OR-Tools TSP plus a break inserter removed them.</description>
    </item>
    <item>
      <title>Optimizing a Band Setlist with OR-Tools TSP: Cost Matrices and Break Insertion</title>
      <link>https://www.subcul-science.com/en/post/20261115setlist-automation-tech/</link>
      <pubDate>Sun, 15 Nov 2026 11:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115setlist-automation-tech/</guid>
      <description>How SetlistAutomation turns song ordering into a traveling salesman problem: a transition cost matrix, an OR-Tools search configuration, YouTube Data API durations, and a break-inserter that hides the heaviest instrument swap.</description>
    </item>
    <item>
      <title>Reading Aloud in My Own Voice: Voice-Clone TTS from 30 Seconds of Audio</title>
      <link>https://www.subcul-science.com/en/post/20261115tts-solution/</link>
      <pubDate>Sun, 15 Nov 2026 11:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115tts-solution/</guid>
      <description>Ready-made TTS reads text well but never in your voice. Here is how a reference clip of about 30 seconds becomes a registered voice you can call over HTTP, using TADA and FastAPI.</description>
    </item>
    <item>
      <title>A Japanese Voice-Clone TTS Pipeline with TADA, FastAPI, Whisper, and FFmpeg</title>
      <link>https://www.subcul-science.com/en/post/20261115tts-tech/</link>
      <pubDate>Sun, 15 Nov 2026 11:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115tts-tech/</guid>
      <description>How a reference-audio voice-clone TTS is built with TADA 3B-ML, FastAPI, Whisper, and FFmpeg: registration in a CLI, generation in a server, and why prompt.pt is passed between them.</description>
    </item>
    <item>
      <title>Filling a Quiet Discord Channel and a Broken News Flow with One Resident Bot</title>
      <link>https://www.subcul-science.com/en/post/20261115discord-bot-solution/</link>
      <pubDate>Sun, 15 Nov 2026 10:50:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115discord-bot-solution/</guid>
      <description>Two common problems in a small Discord server: chat that never gets going, and news that stays inside everyone&amp;rsquo;s own RSS reader. How one resident bot addresses both with a persona, scheduled posts, and interests that grow from conversation.</description>
    </item>
    <item>
      <title>A Discord Bot That Lives in the Chat: Ollama, discord.js, and a News Pipeline</title>
      <link>https://www.subcul-science.com/en/post/20261115discord-bot-tech/</link>
      <pubDate>Sun, 15 Nov 2026 10:40:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115discord-bot-tech/</guid>
      <description>How Lobster, a Kansai-dialect Discord bot, is built: one Node process running discord.js and Ollama, persona composition, an instant 👀 acknowledgement, 17 RSS feeds, and interests that change from chat.</description>
    </item>
    <item>
      <title>No One to Critique Your Drawing, and No Wish to Upload It</title>
      <link>https://www.subcul-science.com/en/post/20261115dessan-sensei-solution/</link>
      <pubDate>Sun, 15 Nov 2026 10:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115dessan-sensei-solution/</guid>
      <description>Drawing alone means no reviewer nearby, and uploading practice sketches to a cloud service feels wrong. How Dessan-sensei removed both walls with a local vision model on the LAN, using text-only history as context and level-aware prompting.</description>
    </item>
    <item>
      <title>A Drawing Critique App in Go, SQLite (WAL), React, and an Ollama VLM</title>
      <link>https://www.subcul-science.com/en/post/20261115dessan-sensei-tech/</link>
      <pubDate>Sun, 15 Nov 2026 10:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115dessan-sensei-tech/</guid>
      <description>Dessan-sensei scores a drawing photo on six axes out of ten using a local vision model. A tour of the four layers — Go, SQLite in WAL mode, React, and Ollama — through the prompt builder, the JSON parser, and the transactional save.</description>
    </item>
    <item>
      <title>Automating the Split of Stream Archives: Three Walls of Manual Work, Memory, and Speed</title>
      <link>https://www.subcul-science.com/en/post/20261115jam-slicer-solution/</link>
      <pubDate>Sun, 15 Nov 2026 10:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115jam-slicer-solution/</guid>
      <description>Splitting a long stream archive into individual songs runs into three walls: manual timestamps, huge memory use, and waiting. How JamSlicer removes each one, with the design and code behind it.</description>
    </item>
    <item>
      <title>How JamSlicer Splits Long Videos with FFmpeg silencedetect</title>
      <link>https://www.subcul-science.com/en/post/20261115jam-slicer-tech/</link>
      <pubDate>Sun, 15 Nov 2026 10:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115jam-slicer-tech/</guid>
      <description>A technical tour of JamSlicer: one FFmpeg pass for volume analysis, segment calculation in the browser, and stream-copy cutting. Why each layer is split the way it is, with code from the repository.</description>
    </item>
    <item>
      <title>A LINE Butler That Keeps Its Character While Recommending Products</title>
      <link>https://www.subcul-science.com/en/post/20261115turtle-buttler-solution/</link>
      <pubDate>Sun, 15 Nov 2026 09:50:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115turtle-buttler-solution/</guid>
      <description>A characterful bot turns into a salesperson when you add product links, and a sales bot loses the character. How turtle-buttler split voice, catalogue, and judgement across a prompt, an API, and the model.</description>
    </item>
    <item>
      <title>Building a LINE Butler Bot with Gemini Function Calling and MCP</title>
      <link>https://www.subcul-science.com/en/post/20261115turtle-buttler-tech/</link>
      <pubDate>Sun, 15 Nov 2026 09:40:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115turtle-buttler-tech/</guid>
      <description>How turtle-buttler, a LINE bot that speaks as a Kansai-dialect butler, is put together: Gemini 2.0 Flash function calling, MCP servers backed by Firebase Realtime Database, and an HTTP fallback for Cloud Run.</description>
    </item>
    <item>
      <title>When Your Likes Get Buried: Designing Capture and Rediscovery for X Favorites</title>
      <link>https://www.subcul-science.com/en/post/20261115x-fav-gallery-solution/</link>
      <pubDate>Sun, 15 Nov 2026 09:30:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115x-fav-gallery-solution/</guid>
      <description>Likes on X sink into the timeline the moment you tap them, and there is no way to search by what an image looks like. How Refav Gallery split capture, storage, and rediscovery to fix that, including the tradeoffs and measured results.</description>
    </item>
    <item>
      <title>Rediscovering Likes with Similar Images: Next.js, pgvector, DINOv2, and an MV3 Extension</title>
      <link>https://www.subcul-science.com/en/post/20261115x-fav-gallery-tech/</link>
      <pubDate>Sun, 15 Nov 2026 09:20:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115x-fav-gallery-tech/</guid>
      <description>How Refav Gallery turns X likes into a searchable image gallery: passive interception in a Manifest V3 extension, DINOv2 embeddings on Modal, a pgvector HNSW/exact-KNN split, and MMR for diversity, with code and measured numbers from the repository.</description>
    </item>
    <item>
      <title>Preventing Missed Sequels by Design: Stop Relying on Remembering at the Bookstore</title>
      <link>https://www.subcul-science.com/en/post/20261115tsuzukan-solution/</link>
      <pubDate>Sun, 15 Nov 2026 09:10:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115tsuzukan-solution/</guid>
      <description>Missing the next volume is not a memory problem, it is a problem of where the state lives. How tsuzukan records owned volumes by ISBN and reports what the series is missing, including the cases a machine cannot decide.</description>
    </item>
    <item>
      <title>How tsuzukan Tracks Manga Sequels: Go, React 19, and Three Bibliographic APIs</title>
      <link>https://www.subcul-science.com/en/post/20261115tsuzukan-tech/</link>
      <pubDate>Sun, 15 Nov 2026 09:00:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20261115tsuzukan-tech/</guid>
      <description>A tour of tsuzukan&amp;rsquo;s internals: a Go 1.26 + Gin API, a React 19 frontend, PostgreSQL, Firebase Auth, and three bibliographic sources with very different personalities — openBD, NDL Search, and Rakuten Books — folded behind one interface.</description>
    </item>
    <item>
      <title>How to Solve Audio File Volume Inconsistency and Quality Unification Issues with ffmpeg Normalization</title>
      <link>https://www.subcul-science.com/en/post/20250705audio-volume-normalization-solution/</link>
      <pubDate>Sat, 05 Jul 2025 21:05:51 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20250705audio-volume-normalization-solution/</guid>
      <description>&lt;h2 id=&#34;audio-volume-issues-in-audio-file-processing&#34;&gt;Audio Volume Issues in Audio File Processing&lt;/h2&gt;&#xA;&lt;p&gt;When producing and distributing audio content, do you face these problems?&lt;/p&gt;&#xA;&lt;h3 id=&#34;1-volume-inconsistency-issues&#34;&gt;1. Volume Inconsistency Issues&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Volume levels are not unified across multiple audio files&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;Volume differences occur due to different recording environments and equipment&lt;/li&gt;&#xA;&lt;li&gt;Listeners need to frequently adjust volume levels&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h3 id=&#34;2-quality-inconsistency-issues&#34;&gt;2. Quality Inconsistency Issues&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Noise and unwanted frequencies are mixed in&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;Silent sections are too long and difficult to listen to&lt;/li&gt;&#xA;&lt;li&gt;Unable to achieve professional-quality audio&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h3 id=&#34;3-manual-processing-limitations&#34;&gt;3. Manual Processing Limitations&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Processing large numbers of audio files individually is inefficient&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;Automation is difficult with GUI audio editing software&lt;/li&gt;&#xA;&lt;li&gt;Applying consistent processing standards is challenging&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h2 id=&#34;real-world-audio-quality-challenge-cases&#34;&gt;Real-world Audio Quality Challenge Cases&lt;/h2&gt;&#xA;&lt;h3 id=&#34;failure-case-limitations-of-manual-adjustment&#34;&gt;Failure Case: Limitations of Manual Adjustment&lt;/h3&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# Traditional approach&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# 1. Open each file in audio editing software&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# 2. Visually and auditorily adjust levels&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# 3. Manually apply noise reduction&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# 4. Manually cut silent sections&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# Problems:&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# - Time-consuming for processing large numbers of files&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# - Processing standards are subjective and inconsistent&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# - Quality variations due to human errors&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;The solution to this problem is &lt;strong&gt;automated volume normalization with ffmpeg&lt;/strong&gt;.&lt;/p&gt;</description>
    </item>
    <item>
      <title>How to Efficiently Solve Low Accuracy and High Cost Issues in Japanese Text Generation with T5</title>
      <link>https://www.subcul-science.com/en/post/20250705japanese-text-generation-solution/</link>
      <pubDate>Sat, 05 Jul 2025 21:00:38 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20250705japanese-text-generation-solution/</guid>
      <description>&lt;h2 id=&#34;challenges-in-japanese-text-generation&#34;&gt;Challenges in Japanese Text Generation&lt;/h2&gt;&#xA;&lt;p&gt;When working on Japanese text summarization, title generation, and document classification tasks, do you face these problems?&lt;/p&gt;&#xA;&lt;h3 id=&#34;1-accuracy-issues&#34;&gt;1. Accuracy Issues&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Traditional rule-based methods cannot generate natural Japanese text&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;English-oriented models cannot handle Japanese grammar and expressions&lt;/li&gt;&#xA;&lt;li&gt;Need to build separate models for multiple tasks&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h3 id=&#34;2-development-cost-issues&#34;&gt;2. Development Cost Issues&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Time and resources required for task-specific model development&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;Different approaches needed for document classification, summarization, and title generation&lt;/li&gt;&#xA;&lt;li&gt;Enormous effort required for preparing training data and building models&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h3 id=&#34;3-operational-complexity&#34;&gt;3. Operational Complexity&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Need to manage and operate multiple models&lt;/strong&gt;&lt;/li&gt;&#xA;&lt;li&gt;Different APIs and interfaces for each task&lt;/li&gt;&#xA;&lt;li&gt;Complex model updates and maintenance&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h2 id=&#34;real-world-text-generation-challenge-cases&#34;&gt;Real-world Text Generation Challenge Cases&lt;/h2&gt;&#xA;&lt;h3 id=&#34;failure-case-limitations-of-task-specific-individual-development&#34;&gt;Failure Case: Limitations of Task-specific Individual Development&lt;/h3&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-python&#34; data-lang=&#34;python&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# Traditional approach&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;classification_model&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;load_bert_classifier&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;()&lt;/span&gt;      &lt;span class=&#34;c1&#34;&gt;# For document classification&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;summarization_model&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;load_summarization_model&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;()&lt;/span&gt;   &lt;span class=&#34;c1&#34;&gt;# For summarization&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;title_generation_model&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;load_title_model&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;()&lt;/span&gt;        &lt;span class=&#34;c1&#34;&gt;# For title generation&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# Problems:&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# - Managing 3 separate models&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# - 3x memory usage&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# - High development and maintenance costs&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;The solution to this problem is &lt;strong&gt;Japanese T5 (Text-To-Text Transfer Transformer)&lt;/strong&gt;.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Subculture Science Research Group the 6th meeting:　What is the point of football viewing?</title>
      <link>https://www.subcul-science.com/en/post/20210619subcul/</link>
      <pubDate>Sun, 20 Jun 2021 02:35:35 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210619subcul/</guid>
      <description>&lt;h2 id=&#34;dialogue&#34;&gt;Dialogue&lt;/h2&gt;&#xA;&lt;p&gt;R: I don&amp;rsquo;t understand soccer at all, but you can talk a lot, can&amp;rsquo;t you tarky?&lt;/p&gt;&#xA;&lt;p&gt;R: I don&amp;rsquo;t know anything about soccer, but you can talk a lot, can&amp;rsquo;t you? tarky: That&amp;rsquo;s because I used to go to the home games of my favorite clubs quite often.&lt;/p&gt;&#xA;&lt;p&gt;Hanasana: In Hiroshima, there&amp;rsquo;s Sanfrecce Hiroshima. A recent topic for Sanfrecce Hiroshima is the Emperor&amp;rsquo;s Cup. In soccer, from the top to the bottom, there is J1, J2, J3, and JFL, and there was a giant-killing when they were trounced 1-5 by a team from the fifth division.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Subculture Science Research Group the 5th meeting　NFT</title>
      <link>https://www.subcul-science.com/en/post/20210612subcul/</link>
      <pubDate>Sun, 13 Jun 2021 08:32:56 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210612subcul/</guid>
      <description>&lt;h2 id=&#34;interactive&#34;&gt;interactive&lt;/h2&gt;&#xA;&lt;p&gt;R: I&amp;rsquo;ve recently become interested in something called NFT.&lt;/p&gt;&#xA;&lt;p&gt;TARKY: Yeah, I gave it a try.&lt;/p&gt;&#xA;&lt;p&gt;R: What&amp;rsquo;s it like?&lt;/p&gt;&#xA;&lt;p&gt;tarky: Right now I&amp;rsquo;m stuck at creating an account, but I wonder if it&amp;rsquo;s that different from trading virtual currency.&lt;/p&gt;&#xA;&lt;p&gt;R: I&amp;rsquo;m not sure about the virtual currency trading, though.&lt;/p&gt;&#xA;&lt;p&gt;tarky: First, you open an account at an NFT exchange and deposit virtual currency into it.&lt;/p&gt;&#xA;&lt;p&gt;Then you use the virtual currency to buy collections (works of art linked to virtual currency).&lt;/p&gt;</description>
    </item>
    <item>
      <title>Subculture Science Club Spilling the beans: How to speak with responsibly and evidence</title>
      <link>https://www.subcul-science.com/en/post/20210607subcul/</link>
      <pubDate>Mon, 07 Jun 2021 23:34:02 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210607subcul/</guid>
      <description>&lt;p&gt;R: I&amp;rsquo;d like you to give evidence or sources when you talk about it.&lt;/p&gt;&#xA;&lt;p&gt;Tarky: What do you mean? Commentators on TV shows say whatever they want.&lt;/p&gt;&#xA;&lt;p&gt;R: Those are experts of some kind, aren&amp;rsquo;t they? I&amp;rsquo;d like you to ensure their expertise.&lt;/p&gt;&#xA;&lt;p&gt;Tarky: That&amp;rsquo;s a natural science argument, so I don&amp;rsquo;t think it&amp;rsquo;s something that is generally required or accepted.&lt;/p&gt;&#xA;&lt;p&gt;R: Does that mean you think so?&lt;/p&gt;&#xA;&lt;p&gt;Tarky: The argument is refined with evidence. The argument is refined by criticism. I think this is a special method of argumentation in the natural sciences, which we developed in our graduate school days. It&amp;rsquo;s not the best way to appeal to the masses.&lt;/p&gt;</description>
    </item>
    <item>
      <title>The 4th Regular Meeting of the Subculture Science Research Group: Sake and Wood</title>
      <link>https://www.subcul-science.com/en/post/20210605subcul/</link>
      <pubDate>Sat, 05 Jun 2021 22:23:32 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210605subcul/</guid>
      <description>&lt;h2 id=&#34;conversation-style&#34;&gt;Conversation style&lt;/h2&gt;&#xA;&lt;p&gt;R: Liquor and wood go hand in hand.&lt;/p&gt;&#xA;&lt;p&gt;Tarky: Oh!&lt;/p&gt;&#xA;&lt;p&gt;R: When you went to a brewery in Taiwan, you saw a row of sake barrels, right? It&amp;rsquo;s a common belief that whiskey tastes different depending on the wood of the barrel.&lt;/p&gt;&#xA;&lt;p&gt;Tarky: Oh, weren&amp;rsquo;t they burned?&lt;/p&gt;&#xA;&lt;p&gt;R: Even if it&amp;rsquo;s burned, some things soak in. And Quercus serrata is good. R: Even if it&amp;rsquo;s burned, there&amp;rsquo;s something that soaks in.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Subculture Science Research Group Regular Meeting No.3 Wood for electric guitar or anything else?</title>
      <link>https://www.subcul-science.com/en/post/20210528subcul/</link>
      <pubDate>Sat, 29 May 2021 22:49:12 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210528subcul/</guid>
      <description>&lt;h2 id=&#34;conversation-style&#34;&gt;Conversation style&lt;/h2&gt;&#xA;&lt;p&gt;R: Something about Fender being forced to stop using ash wood&lt;/p&gt;&#xA;&lt;p&gt;R: I heard that Fender had to stop using ash wood because of climate problems in the southern United States.&lt;/p&gt;&#xA;&lt;p&gt;R: I was wondering, what&amp;rsquo;s the point of wood in an electric guitar?&lt;/p&gt;&#xA;&lt;p&gt;tarky: What do you mean?&lt;/p&gt;&#xA;&lt;p&gt;R: It doesn&amp;rsquo;t seem to matter what material it&amp;rsquo;s made of, but it&amp;rsquo;s a problem.&lt;/p&gt;&#xA;&lt;p&gt;tarky: Oh, I see. To sum it up, from the performer&amp;rsquo;s point of view, it makes sense. But from the audience&amp;rsquo;s point of view, it doesn&amp;rsquo;t make much difference.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Building a python environment with poetry on mac os</title>
      <link>https://www.subcul-science.com/en/post/20210520poetry/</link>
      <pubDate>Thu, 20 May 2021 20:53:52 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210520poetry/</guid>
      <description>&lt;p&gt;Pip is a major method of installing python libraries.&lt;/p&gt;&#xA;&lt;p&gt;poetry is a more advanced version control tool for development environments.&lt;/p&gt;&#xA;&lt;p&gt;It seems to have official support for pyenv integration.&lt;/p&gt;&#xA;&lt;p&gt;I&amp;rsquo;ll write down how to install it on mac os and what I got stuck.&lt;/p&gt;&#xA;&lt;h2 id=&#34;advantages-of-poetry&#34;&gt;Advantages of poetry&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Can organize library dependencies.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;There are some unexpected side effects depending on the version of the library.&lt;/li&gt;&#xA;&lt;li&gt;Trying to recreate the environment can cause errors with library versions and installation order.&lt;/li&gt;&#xA;&lt;li&gt;Building the environment is an inevitable part of human work, so it should be automated if possible.&lt;/li&gt;&#xA;&lt;li&gt;Also, it seems to be able to update the library version to take dependencies into account.&lt;/li&gt;&#xA;&lt;li&gt;And it keeps a record of the status.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Is it possible to separate the dependency records by git branch?&lt;/li&gt;&#xA;&lt;li&gt;The libraries you can install are comparable to pip&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Does it have the same references as pypy?&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Usability is not much different from pip&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Poetry add instead of pip install&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;It recognizes virtual environments created with pyenv and works with them.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;I&amp;rsquo;m going to install it because it seems to be a convenient way to build an environment without much effort.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Why is fasttext so fast?</title>
      <link>https://www.subcul-science.com/en/post/20210519fasttext/</link>
      <pubDate>Wed, 19 May 2021 02:10:01 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210519fasttext/</guid>
      <description>&lt;h2 id=&#34;features-of-fasttext&#34;&gt;Features of fasttext&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Improved objective function&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Consideration of negative samples&lt;/li&gt;&#xA;&lt;li&gt;This should not affect training time.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Change in optimization method&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Use of stochastic optimization&lt;/li&gt;&#xA;&lt;li&gt;If it affects the learning time, it should be this one&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Implementation in C language&#xA;&lt;ul&gt;&#xA;&lt;li&gt;This is the most effective, isn&amp;rsquo;t it?&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;If we implement it in ## pytorch, it won&amp;rsquo;t be much different from word2vec.&#xA;It would depend on the amount of data to be trained.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Using Amazon Transcribe for transcription and speaker separation</title>
      <link>https://www.subcul-science.com/en/post/20210517awstranscribe/</link>
      <pubDate>Mon, 17 May 2021 15:07:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210517awstranscribe/</guid>
      <description>&lt;p&gt;There is a transcription service called Amazon Transcribe.&lt;/p&gt;&#xA;&lt;p&gt;The features of this service include&lt;/p&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Speaker separation as of 2021/05/17&lt;/li&gt;&#xA;&lt;li&gt;Japanese language support&lt;/li&gt;&#xA;&lt;li&gt;It supports both video and audio formats.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;There are some points.&lt;/p&gt;&#xA;&lt;p&gt;I&amp;rsquo;ll write down how to use it with GUI.&lt;/p&gt;&#xA;&lt;h2 id=&#34;procedure&#34;&gt;Procedure&lt;/h2&gt;&#xA;&lt;p&gt;There is nothing difficult about the procedure, just follow the instructions on the screen. 1.&lt;/p&gt;&#xA;&lt;p&gt;Login to the AWS console. 1.&lt;/p&gt;&#xA;&lt;ol&gt;&#xA;&lt;li&gt;you need to create an account for AWS. 2.&lt;/li&gt;&#xA;&lt;li&gt;upload the audio file to S3. 1.&#xA;You don&amp;rsquo;t need to tweak any options. 2.&#xA;2. choose a region that is close to your location.&lt;/li&gt;&#xA;&lt;li&gt;transcribe with Amazon Transcribe&#xA;&lt;ol&gt;&#xA;&lt;li&gt;click &amp;ldquo;create job&lt;/li&gt;&#xA;&lt;li&gt;name can be anything as long as it&amp;rsquo;s distinguishable. 3.&#xA;For Langueage, select Japanese. 4.&#xA;For Input data, select the file you uploaded from Browse S3.&#xA;Click Next. 6.&#xA;Audio setting&#xA;Turn on Audio identification (speaker separation).&#xA;Select Speaker Identification to distinguish between speakers by using the characteristics of each speaker. 3.&#xA;Turn on Alternative results. 1.&#xA;Set Maximum alternative to 1. 2.&#xA;The number of alternatives you set here will be output. If you want to examine the variations, you can set the number to more than 2. 7.&lt;/li&gt;&#xA;&lt;li&gt;click create. 8.&lt;/li&gt;&#xA;&lt;li&gt;confirm that the job you entered in Name is added to Transcription jobs. 9.&#xA;Wait for the Status to become Complete. 10.&#xA;Click on the target to get the output json.&lt;/li&gt;&#xA;&lt;/ol&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ol&gt;&#xA;&lt;h2 id=&#34;extract-speech-by-speaker&#34;&gt;Extract speech by speaker&lt;/h2&gt;&#xA;&lt;p&gt;Example script&#xA;Writing in python&lt;/p&gt;</description>
    </item>
    <item>
      <title>Impressions of manga the type of Yankee who gives one-pointed advice to passersby.</title>
      <link>https://www.subcul-science.com/en/post/20210510advice/</link>
      <pubDate>Mon, 10 May 2021 17:39:51 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210510advice/</guid>
      <description>&lt;p&gt;This is a story about a yankee who gives a bad impression of being a yankee and gives advice and help to people in need.&lt;/p&gt;&#xA;&lt;p&gt;The story is about a yankee who takes care of an abandoned cat, and the gap between the two gives him a good impression.&#xA;But the author&amp;rsquo;s creative ability to add a twist to it and make it into a system that can be used in each story is amazing.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Personal Feelings about Symptoms of Depression</title>
      <link>https://www.subcul-science.com/en/post/20210509utsu/</link>
      <pubDate>Sun, 09 May 2021 10:41:35 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210509utsu/</guid>
      <description>&lt;h2 id=&#34;feeling-depressed&#34;&gt;Feeling depressed&lt;/h2&gt;&#xA;&lt;p&gt;In my case, treatment for depression is going well.&lt;/p&gt;&#xA;&lt;p&gt;However, I am still far from a full recovery.&lt;/p&gt;&#xA;&lt;p&gt;In order to reaffirm that I am recovering.&#xA;To reaffirm that I&amp;rsquo;m recovering, I&amp;rsquo;m going to list the symptoms I&amp;rsquo;ve been having and see how much I&amp;rsquo;ve improved.&lt;/p&gt;&#xA;&lt;h2 id=&#34;list-of-symptoms&#34;&gt;List of symptoms&lt;/h2&gt;&#xA;&lt;h2 id=&#34;mental-symptoms&#34;&gt;Mental symptoms&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Two contradictory sensations prevent me from taking action.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Agitation and lethargy&lt;/li&gt;&#xA;&lt;li&gt;Obsessive need to do something and feeling stagnant&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Feeling of helplessness&lt;/li&gt;&#xA;&lt;li&gt;Stagnation due to inability to think&lt;/li&gt;&#xA;&lt;li&gt;Automatic thinking&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Having a conversation with someone in your head&lt;/li&gt;&#xA;&lt;li&gt;Sometimes I don&amp;rsquo;t even make an appearance&lt;/li&gt;&#xA;&lt;li&gt;Thought resources are being allocated&lt;/li&gt;&#xA;&lt;li&gt;A kind of escape from reality?&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Leaning towards negative thoughts&lt;/li&gt;&#xA;&lt;li&gt;Burning sensation in the brain&lt;/li&gt;&#xA;&lt;li&gt;Self-deprecation&#xA;&lt;ul&gt;&#xA;&lt;li&gt;A strong sense of shame that you have failed and will be laughed at for all your actions&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Generalized anxiety&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Fear of other people, paranoia about being yelled at&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Black and white thinking, extremes of meaning and meaninglessness&lt;/li&gt;&#xA;&lt;li&gt;Delusions&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Delusions of being disliked&lt;/li&gt;&#xA;&lt;li&gt;Delusion that your thoughts will be understood by others&lt;/li&gt;&#xA;&lt;li&gt;Delusion that your state of mind or state of being is not understood&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Fear of wanting the other person to think you are smart and not to be disappointed&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Fear of being blamed for failure&lt;/li&gt;&#xA;&lt;li&gt;Feeling as if you are terribly at fault when there is a discrepancy in your perception of information&lt;/li&gt;&#xA;&lt;li&gt;Feeling the need to cheat&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;The pain of being conscious and not doing anything is hard&lt;/li&gt;&#xA;&lt;li&gt;Feelings of wanting to die&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Feeling that life is over&lt;/li&gt;&#xA;&lt;li&gt;Feeling that you are tired of living&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Not being able to take care of yourself&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Cannot take a bath&lt;/li&gt;&#xA;&lt;li&gt;Not being able to brush your teeth&lt;/li&gt;&#xA;&lt;li&gt;Loss of appetite or binge eating&lt;/li&gt;&#xA;&lt;li&gt;Feeling like you shouldn&amp;rsquo;t do things that are good for you (make you feel better or easier)&lt;/li&gt;&#xA;&lt;li&gt;Afraid to go to sleep at night or wake up in the morning&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Unable to manage money&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Unable to be conscious in the first place&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Feeling like you are a stranger&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Loss of understanding of one&amp;rsquo;s own feelings&lt;/li&gt;&#xA;&lt;li&gt;A sense of separation between the mind and the will&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Losing touch with things you used to like, in my case, rejection of guitars&lt;/li&gt;&#xA;&lt;li&gt;A strong sense of rejection of certain places&lt;/li&gt;&#xA;&lt;li&gt;Rejection of moving content such as anime, and difficulty in being moved by it&lt;/li&gt;&#xA;&lt;li&gt;Sense of dependence on others&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Reload social networking site notifications incessantly&lt;/li&gt;&#xA;&lt;li&gt;Feeling like a so-called &amp;ldquo;menhera&amp;rdquo;?&lt;/li&gt;&#xA;&lt;li&gt;Only stopping to send messages in succession.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h3 id=&#34;physical-symptoms&#34;&gt;Physical symptoms&lt;/h3&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Sluggishness in arms and legs&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Unable to move, sitting on the street, unable to turn over in bed.&lt;/li&gt;&#xA;&lt;li&gt;Inability to act without a strong sense of awareness&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Loss of appetite for tasty foods&lt;/li&gt;&#xA;&lt;li&gt;Weight gain or loss&lt;/li&gt;&#xA;&lt;li&gt;Physical pain&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Unexpected chest pain&lt;/li&gt;&#xA;&lt;li&gt;Headache&lt;/li&gt;&#xA;&lt;li&gt;Back pain&lt;/li&gt;&#xA;&lt;li&gt;Discomfort in the throat&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Insomnia or hypersomnia&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Waking up in the middle of the night&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Dizziness&lt;/li&gt;&#xA;&lt;li&gt;Jet lag? Feeling very sick&lt;/li&gt;&#xA;&lt;li&gt;Tooth decay&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Tooth decay due to skipping brushing?&lt;/li&gt;&#xA;&lt;li&gt;Tooth decay progresses because you don&amp;rsquo;t visit the dentist regularly&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Tension&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Stiff shoulders&lt;/li&gt;&#xA;&lt;li&gt;General body tension&lt;/li&gt;&#xA;&lt;li&gt;Calf tightness&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Decreased cognitive ability&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Inability to read letters&lt;/li&gt;&#xA;&lt;li&gt;Inability to hear what others are saying&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h2 id=&#34;efforts-to-recover-from-symptoms&#34;&gt;Efforts to recover from symptoms&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Visits to the internal medicine department&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Prescription of psychotropic drugs&lt;/li&gt;&#xA;&lt;li&gt;Prescription of sleeping pills&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Increased time spent in bed.&lt;/li&gt;&#xA;&lt;li&gt;I slept for almost a month.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Visit to a psychosomatic doctor&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Prescription of psychotropic drugs&lt;/li&gt;&#xA;&lt;li&gt;Prescription of sleep inducing drugs&lt;/li&gt;&#xA;&lt;li&gt;Application for medical treatment for independence support&lt;/li&gt;&#xA;&lt;li&gt;I could feel the change in my symptoms after the change in medication. From that point on, I have been slowly recovering over time.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Counseling&#xA;&lt;ul&gt;&#xA;&lt;li&gt;To be honest, I don&amp;rsquo;t know how effective it is. I continue to take it because I feel I need it.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Supplements&#xA;&lt;ul&gt;&#xA;&lt;li&gt;No particular effect was seen.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Aroma oil&#xA;&lt;ul&gt;&#xA;&lt;li&gt;No particular effect was seen.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Bath&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Bathing stimulates the body&amp;rsquo;s senses and provides some distraction.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Sauna&#xA;&lt;ul&gt;&#xA;&lt;li&gt;It became easier to fall asleep after the sauna.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Massage&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Makes it easier to fall asleep.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Mindfulness&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I mainly did body scan meditation. I was able to confirm that I was wasting energy in my body. It also helped me fall asleep.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Employment&#xA;&lt;ul&gt;&#xA;&lt;li&gt;It brought about a change in environment, but it was a very risky move.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Regularly hang out with friends&#xA;&lt;ul&gt;&#xA;&lt;li&gt;In order not to succumb to suicidal thoughts and the feeling that my life was over, I made plans and gave myself a reason to live that long.&lt;/li&gt;&#xA;&lt;li&gt;As a result, I had a lot of experiences.&lt;/li&gt;&#xA;&lt;li&gt;The next thing I knew, I began to feel bored with being able to perform steadily with the same members.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Becoming aware of pain and suffering, and creating imaginary friends who comforted me and told me I was okay.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;The results were very positive. Over the course of a month, the sense of pain really did decrease.&lt;/li&gt;&#xA;&lt;li&gt;On the other hand, I became newly aware of the pain that I had been feeling unconsciously.&lt;/li&gt;&#xA;&lt;li&gt;This will continue to reduce the stress response.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;For delusions and cognitive distortions, verbalizing these thoughts and feelings and consciously counteracting them&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Derivative of the above method&lt;/li&gt;&#xA;&lt;li&gt;Combined with written disclosure&lt;/li&gt;&#xA;&lt;li&gt;Imagery to correct bad habits in emotions and perception of reality&lt;/li&gt;&#xA;&lt;li&gt;Guide yourself to a more objective perception of reality&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Take a walk&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Does it provide some distraction?&lt;/li&gt;&#xA;&lt;li&gt;I feel a faint sense of entrapment when I stay in my room, so I take walks more often.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Creating a support app to make a habit of the behavior that may help improve symptoms.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I made the app myself.&lt;/li&gt;&#xA;&lt;li&gt;Creating the app itself did not improve my symptoms.&lt;/li&gt;&#xA;&lt;li&gt;Also, I don&amp;rsquo;t feel that using the app has led to any improvement in my symptoms.&lt;/li&gt;&#xA;&lt;li&gt;On the other hand, I was able to recognize that my strong desire to escape the pain was strong enough to accomplish the creation of an app that I had no experience with.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Writing a diary&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I used voice input to talk for 10 minutes.&lt;/li&gt;&#xA;&lt;li&gt;It helps me recognize my thoughts and the things that have been lingering in the corner of my mind.&lt;/li&gt;&#xA;&lt;li&gt;I can also see how my symptoms have been changing from past sentences.&lt;/li&gt;&#xA;&lt;li&gt;I can check the severity of my symptoms from the progress of my writing.&lt;/li&gt;&#xA;&lt;li&gt;What is my current condition? Is it good or bad? I didn&amp;rsquo;t even know that, so it was an important indicator for me to see how I was doing.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Drawing illustrations&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I&amp;rsquo;m not a painter by nature, but it was a good distraction.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Go to a sports club&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I heard that exercise is good for your physical and mental health, so I tried it.&lt;/li&gt;&#xA;&lt;li&gt;Nervous about working with unfamiliar people&lt;/li&gt;&#xA;&lt;li&gt;But I feel a little refreshed as I try my best to exercise.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Read a book&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Rehabilitation for not being able to read anymore&lt;/li&gt;&#xA;&lt;li&gt;Also, I heard that in the UK they give books as a prescription for depression?&lt;/li&gt;&#xA;&lt;li&gt;I started with one line a day.&lt;/li&gt;&#xA;&lt;li&gt;It&amp;rsquo;s still hard for me to read.&lt;/li&gt;&#xA;&lt;li&gt;I think I read 3 or 4 books a month even though it&amp;rsquo;s hard for me.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Exposure to moving content such as anime and movies&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Crying&lt;/li&gt;&#xA;&lt;li&gt;Rehabilitation of the mind&lt;/li&gt;&#xA;&lt;li&gt;I felt that my emotions were fixed, so I imagined moving them.&lt;/li&gt;&#xA;&lt;li&gt;But it&amp;rsquo;s really like rehabilitation, and it&amp;rsquo;s painful.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Finding a girlfriend&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Not very effective.&lt;/li&gt;&#xA;&lt;li&gt;I don&amp;rsquo;t know if it&amp;rsquo;s because I&amp;rsquo;m not ready to enjoy love or if it&amp;rsquo;s because of my health condition.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Attending a session&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I didn&amp;rsquo;t enjoy it that much. Hardship comes first.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h2 id=&#34;examples-of-failure&#34;&gt;Examples of failure&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Suicidal thoughts turned into a doomed desire and I went to fall for a scam.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I ended up in financial debt. Now I&amp;rsquo;m on track to pay it back.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;I got a job even though I am in a condition where I cannot move well.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;I went there to avoid a change in environment and financial difficulties. I was desperate even then, but it was a reckless act. We believe that there were ways to recover from the disease sufficiently and to utilize employment support.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;When I was transferred to the hospital, I failed to apply for medical care for independence support.&#xA;&lt;ul&gt;&#xA;&lt;li&gt;It was hard for me to submit an application for medical care for services and supports for persons with disabilities, which resulted in high medical expenses.&lt;/li&gt;&#xA;&lt;li&gt;I ended up using the medical care for independence support.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h2 id=&#34;summary-of-what-helped-me-improve-my-symptoms&#34;&gt;Summary of what helped me improve my symptoms&lt;/h2&gt;&#xA;&lt;p&gt;In the end, going to a psychosomatic medicine clinic, doing nothing but resting my mind and taking my time seemed to be the most effective.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Creating data in Natural Language Inference (NLI) format for Sentence transformer</title>
      <link>https://www.subcul-science.com/en/post/20210217nlibert/</link>
      <pubDate>Wed, 17 Feb 2021 10:32:03 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210217nlibert/</guid>
      <description>&lt;p&gt;Using the Sentence Transformer to&#xA;I&amp;rsquo;m trying to use Sentence Transformer to infer causal relationships between documents.&lt;/p&gt;&#xA;&lt;p&gt;If we can do this, we can extract the cause and symptoms of the incident from the report.&lt;/p&gt;&#xA;&lt;p&gt;So, I wondered if NLI could be used for feature learning to extract causal information. I thought.&lt;/p&gt;&#xA;&lt;h2 id=&#34;what-is-nli&#34;&gt;What is NLI?&lt;/h2&gt;&#xA;&lt;p&gt;Inference of the relationship between two sentences&lt;/p&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Forward&lt;/li&gt;&#xA;&lt;li&gt;Inverse&lt;/li&gt;&#xA;&lt;li&gt;Unrelated&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;The three relations are.&lt;/p&gt;&#xA;&lt;h2 id=&#34;apply-to-causal-relationships&#34;&gt;Apply to causal relationships&lt;/h2&gt;&#xA;&lt;p&gt;If we apply the three relationships of NLI to causality, the following patterns are possible.&lt;/p&gt;</description>
    </item>
    <item>
      <title>On the use of distributed representations bagging for class classification and generalization performance</title>
      <link>https://www.subcul-science.com/en/post/20210204classifier/</link>
      <pubDate>Thu, 04 Feb 2021 13:24:19 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210204classifier/</guid>
      <description>&lt;p&gt;After the distributed representation has been obtained, the&#xA;After the distributed representation is obtained, machine learning can be used to classify it.&lt;/p&gt;&#xA;&lt;p&gt;Models that can be used include&lt;/p&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Decision Tree&lt;/li&gt;&#xA;&lt;li&gt;SVM Support Vector Machine&lt;/li&gt;&#xA;&lt;li&gt;NN Neural Networks&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;and others.&lt;/p&gt;&#xA;&lt;p&gt;SVM is included in NN in a broad sense.&lt;/p&gt;&#xA;&lt;p&gt;In this section, we will use the decision tree method.&lt;/p&gt;&#xA;&lt;h2 id=&#34;bagging&#34;&gt;Bagging&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Image of majority voting with multiple decision trees&lt;/li&gt;&#xA;&lt;li&gt;Simple theory&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Decision trees are highly explainable and are a classic machine learning model.&lt;/li&gt;&#xA;&lt;li&gt;Computational load is light compared to deep learning&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Depends on the size of the model&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;li&gt;Not much explainability&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Do we want to analyze each of the multiple decision trees?&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;``py&#xA;from sklearn.ensemble import BaggingClassifier&#xA;from sklearn.tree import DecisionTreeClassifier&lt;/p&gt;</description>
    </item>
    <item>
      <title>How to train a Japanese model with Sentence transformer to get a distributed representation of a sentence</title>
      <link>https://www.subcul-science.com/en/post/20210203sbert/</link>
      <pubDate>Wed, 03 Feb 2021 15:58:41 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210203sbert/</guid>
      <description>&lt;p&gt;.&#xA;BERT is a model that can be powerfully applied to natural language processing tasks.&lt;/p&gt;&#xA;&lt;p&gt;However, it does not do a good job of capturing sentence-wise features.&lt;/p&gt;&#xA;&lt;p&gt;Some claim that sentence features appear in [ CLS\ ], but&#xA;This paper](&lt;a href=&#34;https://arxiv.org/abs/1908.10084&#34;&gt;https://arxiv.org/abs/1908.10084&lt;/a&gt;) claims that it does not contain that much useful information for the task.&lt;/p&gt;&#xA;&lt;p&gt;Sentence BERT is a model that extends BERT to be able to obtain features per sentence.&lt;/p&gt;&#xA;&lt;p&gt;The following are the steps to create Sentence BERT in Japanese.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Using BART (sentence summary model) with hugging face</title>
      <link>https://www.subcul-science.com/en/post/20210119huggingface/</link>
      <pubDate>Tue, 19 Jan 2021 03:03:11 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20210119huggingface/</guid>
      <description>&lt;ul&gt;&#xA;&lt;li&gt;BART is a model for document summarization&lt;/li&gt;&#xA;&lt;li&gt;Derived from the same transformer as BERT&lt;/li&gt;&#xA;&lt;li&gt;Unlike BERT, it has an encoder-decoder structure&#xA;&lt;ul&gt;&#xA;&lt;li&gt;This is because it is intended for sentence generation&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;This page shows the steps to run a tutorial on BART.&lt;/p&gt;&#xA;&lt;h2 id=&#34;procedure&#34;&gt;Procedure&lt;/h2&gt;&#xA;&lt;ol&gt;&#xA;&lt;li&gt;install transformers&lt;/li&gt;&#xA;&lt;/ol&gt;&#xA;&lt;p&gt;Run ``sh&#xA;pip install transformers&lt;/p&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-fallback&#34; data-lang=&#34;fallback&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;Run summary&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;2. Run the summary&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;from transformers import BartTokenizer, BartForConditionalGeneration, BartConfig&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;model = BartForConditionalGeneration.from_pretrained(&amp;#39;facebook/bart-large&amp;#39;)&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;tokenizer = BartTokenizer.from_pretrained(&amp;#39;facebook/bart-large&amp;#39;)&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ARTICLE_TO_SUMMARIZE = &amp;#34;My friends are cool but they eat too many carbs.&amp;#34;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;inputs = tokenizer([ARTICLE_TO_SUMMARIZE], max_length=1024, return_tensors=&amp;#39;pt&amp;#39;)&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;# Generate Summary&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;summary_ids = model.generate(inputs[&amp;#39;input_ids&amp;#39;], num_beams=4, max_length=5, early_stopping=True)&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;print([tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in summary_ids])&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;```&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;On 2021/01/18, the output was MyMy friends.&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;Interesting.&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;## Where I got stuck.&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;Error when the version of pytorch is different from the one specified in transformers.&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;pip install -U torch&lt;/p&gt;</description>
    </item>
    <item>
      <title>Thoughts on manga women who want to cook and women who want to eat</title>
      <link>https://www.subcul-science.com/en/post/mangashecooks/</link>
      <pubDate>Wed, 13 Jan 2021 06:35:39 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/mangashecooks/</guid>
      <description>&lt;h2 id=&#34;summary&#34;&gt;Summary&lt;/h2&gt;&#xA;&lt;p&gt;A story about the interaction between the hero, who enjoys cooking and wants to cook a lot, but can&amp;rsquo;t consume enough on his own, and the heroine, who eats a lot? This is a story about the interaction between the heroine?&lt;/p&gt;&#xA;&lt;h2 id=&#34;thoughts&#34;&gt;Thoughts&lt;/h2&gt;&#xA;&lt;p&gt;Why do I need to be a woman? This is a story about a woman who wants to cook a lot but can&amp;rsquo;t consume it all by herself.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Procedure for obtaining a distributed representation of a Japanese sentence using a trained Universal Sentence Encoder</title>
      <link>https://www.subcul-science.com/en/post/universal-sentence-encoder/</link>
      <pubDate>Mon, 22 Jun 2020 18:29:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/universal-sentence-encoder/</guid>
      <description>&lt;p&gt;.&lt;/p&gt;&#xA;&lt;p&gt;A vector of documents can be obtained using Universal Sentence Encoder.&lt;/p&gt;&#xA;&lt;h2 id=&#34;features&#34;&gt;Features&lt;/h2&gt;&#xA;&lt;p&gt;Supports multiple languages.&lt;/p&gt;&#xA;&lt;p&gt;Japanese is supported.&lt;/p&gt;&#xA;&lt;p&gt;Can handle Japanese sentences as vectors.&lt;/p&gt;&#xA;&lt;h2 id=&#34;usage&#34;&gt;Usage&lt;/h2&gt;&#xA;&lt;p&gt;Clustering, similarity calculation, feature extraction.&lt;/p&gt;&#xA;&lt;h2 id=&#34;usage-1&#34;&gt;Usage&lt;/h2&gt;&#xA;&lt;p&gt;Execute the following command as preparation.&lt;/p&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-sh&#34; data-lang=&#34;sh&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;pip install tensorflow tensorflow_hub tensorflow_text numpy   &#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;Trained models are available.&lt;/p&gt;&#xA;&lt;p&gt;See the python description below for details on how to use it.&lt;/p&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-py&#34; data-lang=&#34;py&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;kn&#34;&gt;import&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;tensorflow_hub&lt;/span&gt; &lt;span class=&#34;k&#34;&gt;as&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;hub&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;kn&#34;&gt;import&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;tensorflow_text&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;kn&#34;&gt;import&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;numpy&lt;/span&gt; &lt;span class=&#34;k&#34;&gt;as&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;np&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;# for avoiding error  &lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;kn&#34;&gt;import&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;ssl&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;ssl&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;_create_default_https_context&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;ssl&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;_create_unverified_context&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;k&#34;&gt;def&lt;/span&gt; &lt;span class=&#34;nf&#34;&gt;cos_sim&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;v1&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;,&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;v2&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;):&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;   &lt;span class=&#34;k&#34;&gt;return&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;np&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;dot&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;v1&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;,&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;v2&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;)&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;/&lt;/span&gt; &lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;np&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;linalg&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;norm&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;v1&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;)&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;*&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;np&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;linalg&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;norm&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;v2&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;))&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;embed&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;hub&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;load&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;s2&#34;&gt;&amp;#34;https://tfhub.dev/google/universal-sentence-encoder-multilingual/3&amp;#34;&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;)&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;texts&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;p&#34;&gt;[&lt;/span&gt;&lt;span class=&#34;s2&#34;&gt;&amp;#34;I saw a comedy show yesterday.&amp;#34;&lt;/span&gt; &lt;span class=&#34;p&#34;&gt;,&lt;/span&gt; &lt;span class=&#34;s2&#34;&gt;&amp;#34;There was a comedy show on TV last night.&amp;#34;&lt;/span&gt; &lt;span class=&#34;p&#34;&gt;,&lt;/span&gt; &lt;span class=&#34;s2&#34;&gt;&amp;#34;I went to the park yesterday.&amp;#34;&lt;/span&gt; &lt;span class=&#34;p&#34;&gt;,&lt;/span&gt; &lt;span class=&#34;s2&#34;&gt;&amp;#34;I saw a comedy show last night.&amp;#34;&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;,&lt;/span&gt; &lt;span class=&#34;s2&#34;&gt;&amp;#34;Yesterday, I went to the park.&amp;#34;&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;]&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;vectors&lt;/span&gt; &lt;span class=&#34;o&#34;&gt;=&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;embed&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;(&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;texts&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;)&lt;/span&gt;  &#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;err&#34;&gt;```&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;n&#34;&gt;See&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;the&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;following&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;link&lt;/span&gt; &lt;span class=&#34;k&#34;&gt;for&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;more&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;details&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;p&#34;&gt;[&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;Try&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;Universal&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;Sentence&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;Encoder&lt;/span&gt; &lt;span class=&#34;ow&#34;&gt;in&lt;/span&gt; &lt;span class=&#34;n&#34;&gt;Japanese&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;](&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;https&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;:&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;//&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;qiita&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;.&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;com&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;/&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;kenta1984&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;/&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;items&lt;/span&gt;&lt;span class=&#34;o&#34;&gt;/&lt;/span&gt;&lt;span class=&#34;mi&#34;&gt;9613&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;da23766a2578a27a&lt;/span&gt;&lt;span class=&#34;p&#34;&gt;)&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;c1&#34;&gt;### Postscript&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;err&#34;&gt;```&lt;/span&gt;&lt;span class=&#34;n&#34;&gt;py&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;&lt;span class=&#34;kn&#34;&gt;import&lt;/span&gt; &lt;span class=&#34;nn&#34;&gt;tensorflow_text&lt;/span&gt;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;Without this line, you will get an error like ``Sentencepiece not found! error.&#xA;This line is not explicitly used in the sample source, but is required for the actual execution.&#xA;This line is not explicitly used in the sample source, but is required in the actual runtime.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Enumerating Applications of Document Classification Problems Only</title>
      <link>https://www.subcul-science.com/en/post/20200618blog-post_54/</link>
      <pubDate>Thu, 18 Jun 2020 06:42:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20200618blog-post_54/</guid>
      <description>&lt;h2 id=&#34;applying-the-document-classification-problem&#34;&gt;Applying the Document Classification Problem&lt;/h2&gt;&#xA;&lt;p&gt;You&amp;rsquo;ve learned about machine learning, but you don&amp;rsquo;t know how to use it! Isn&amp;rsquo;t it?&lt;/p&gt;&#xA;&lt;p&gt;It is easy to overlook this if you don&amp;rsquo;t pay attention to it when you study it, but if you don&amp;rsquo;t keep your antennas up, you won&amp;rsquo;t know how to use it.&lt;/p&gt;&#xA;&lt;p&gt;If you don&amp;rsquo;t keep your antennae up, you won&amp;rsquo;t know how to use it. Since a tool is only a tool if it is used, you should make a note of how you use your newly acquired tool.&lt;/p&gt;</description>
    </item>
    <item>
      <title>A note on how to use BERT learned from Japanese Wikipedia, now available</title>
      <link>https://www.subcul-science.com/en/post/wikipediabert/</link>
      <pubDate>Wed, 17 Jun 2020 07:34:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/wikipediabert/</guid>
      <description>&lt;p&gt;huggingface has released a Japanese model for BERT.&lt;/p&gt;&#xA;&lt;p&gt;The Japanese model is included in transformers.&lt;/p&gt;&#xA;&lt;p&gt;However, I stumbled over a few things before I could get it to actually work in a Mac environment, so I&amp;rsquo;ll leave a note.&lt;/p&gt;&#xA;&lt;h2 id=&#34;preliminaries-installing-mecab&#34;&gt;Preliminaries: Installing mecab&lt;/h2&gt;&#xA;&lt;p&gt;The morphological analysis engine, mecab, is required to use BERT&amp;rsquo;s Japanese model.&lt;/p&gt;&#xA;&lt;p&gt;The tokenizer will probably ask for mecab.&lt;/p&gt;&#xA;&lt;p&gt;This time, we will use homebrew to install Mecab and ipadic.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Using Google colaboratory to learn how Word2Vec works and models</title>
      <link>https://www.subcul-science.com/en/post/20200615google-colaboratory-word2vec/</link>
      <pubDate>Mon, 15 Jun 2020 07:42:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20200615google-colaboratory-word2vec/</guid>
      <description>&lt;p&gt;**&lt;/p&gt;&#xA;&lt;p&gt;&lt;a href=&#34;https://1.bp.blogspot.com/-k8gzRPw7B9g/XureK3JosxI/AAAAAAAAg64/vqbEhpkjtMc9rV_iRM2Vbz4gjBNSn33PgCK4BGAsYHg/s1920/CAAF8720-DCD1-4454-8CF8-42C024EA7BA7.jpeg&#34;&gt;&lt;img src=&#34;https://1.bp.blogspot.com/-k8gzRPw7B9g/XureK3JosxI/AAAAAAAAg64/vqbEhpkjtMc9rV_iRM2Vbz4gjBNSn33PgCK4BGAsYHg/s320/CAAF8720-DCD1-4454-8CF8-42C024EA7BA7.jpeg&#34; alt=&#34;&#34;&gt;&lt;/a&gt;&lt;/p&gt;&#xA;&lt;p&gt;Let&amp;rsquo;s start with Word2Vec.**&lt;/p&gt;&#xA;&lt;p&gt;word2vec is a model that can learn the semantic vectors of words from unlabeled text are.&lt;/p&gt;&#xA;&lt;p&gt;Dealing with word vectors allows for applications such as word similarity calculation and clustering, and BERT. And BERT, an extension of that technology, is also used in Google&amp;rsquo;s search service.&lt;/p&gt;&#xA;&lt;p&gt;It&amp;rsquo;s hard to understand the concept.&lt;/p&gt;&#xA;&lt;p&gt;But are you struggling to learn about word2vec? It&amp;rsquo;s hard to understand the concept because it&amp;rsquo;s not something you&amp;rsquo;re familiar with.&lt;/p&gt;</description>
    </item>
    <item>
      <title>How to use NeuralClassifier, a library that provides a crazy number of models for document classification problems</title>
      <link>https://www.subcul-science.com/en/post/neuralclassifier/</link>
      <pubDate>Mon, 15 Jun 2020 02:11:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/neuralclassifier/</guid>
      <description>&lt;p&gt;[! [](https://1.bp.blogspot.com/-YlMb8v77MN4/XurdQSzS1yI/AAAAAAAAg6Y/oSZrJ0c9yxYbzQnNNTynRvZnEp-xGE7NwCK4BGAsYHg/s320/AFE90C8A-A49C- 4475-9F05-50E2D56D5B63.jpeg)](&lt;a href=&#34;https://1.bp.blogspot.com/-YlMb8v77MN4/XurdQSzS1yI/AAAAAAAAg6Y/oSZrJ0c9yxYbzQnNNTynRvZnEp-xGE7NwCK4&#34;&gt;https://1.bp.blogspot.com/-YlMb8v77MN4/XurdQSzS1yI/AAAAAAAAg6Y/oSZrJ0c9yxYbzQnNNTynRvZnEp-xGE7NwCK4&lt;/a&gt; BGAsYHg/s1920/AFE90C8A-A49C-4475-9F05-50E2D56D5B63.jpeg)&lt;/p&gt;&#xA;&lt;p&gt;NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit is a python library for multi-label document classification problems published by Tencent.&lt;/p&gt;&#xA;&lt;p&gt;For more information, see&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;[NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit](&lt;a href=&#34;https://github.com/Tencent/NeuralNLP-&#34;&gt;https://github.com/Tencent/NeuralNLP-&lt;/a&gt; NeuralClassifier)&#xA;NeuralClassifier is designed for quick implementation of neural models for hierarchical multi-label classification task, which is more challenging and common in real-world scenarios.&lt;/p&gt;&#xA;&lt;/blockquote&gt;&#xA;&lt;p&gt;for more details.&lt;/p&gt;&#xA;&lt;p&gt;NeuralClassifier is designed for quick implementation of neural models for hierarchical multi-label classification task, which is more challenging and common in real-world scenarios.&lt;/p&gt;</description>
    </item>
    <item>
      <title>I even did a document classification problem with Fasttext</title>
      <link>https://www.subcul-science.com/en/post/20200613fasttext/</link>
      <pubDate>Sat, 13 Jun 2020 07:29:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20200613fasttext/</guid>
      <description>&lt;h2 id=&#34;summary-of-what-ive-done-with-fasttext-to-the-document-classification-problem&#34;&gt;Summary of what I&amp;rsquo;ve done with Fasttext to the document classification problem.&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Facebook research has published a document classification library using Fasttext.&lt;/li&gt;&#xA;&lt;li&gt;Fasttext is easy to install in a python environment.&lt;/li&gt;&#xA;&lt;li&gt;Run time is fast.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;h2 id=&#34;preliminaries&#34;&gt;Preliminaries&lt;/h2&gt;&#xA;&lt;p&gt;I decided to tackle the task of document classification, and initially thought.&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit&lt;/p&gt;&#xA;&lt;/blockquote&gt;&#xA;&lt;p&gt;NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit. However, it was not very accurate.&lt;/p&gt;</description>
    </item>
    <item>
      <title>I made a summary text generation AI for making short-form news</title>
      <link>https://www.subcul-science.com/en/post/20200613abstractnews/</link>
      <pubDate>Sat, 13 Jun 2020 00:24:00 +0900</pubDate>
      <guid>https://www.subcul-science.com/en/post/20200613abstractnews/</guid>
      <description>&lt;p&gt;.&lt;/p&gt;&#xA;&lt;p&gt;We have successfully trained a model to automatically generate titles from news texts using a machine translation model based on deep learning.&lt;/p&gt;&#xA;&lt;h2 id=&#34;preliminaries&#34;&gt;Preliminaries&lt;/h2&gt;&#xA;&lt;p&gt;In the past, I was involved in a project to automatically generate titles from manuscripts for online news. In the past, I was involved in a project to automatically generate titles from manuscripts for online news.&lt;/p&gt;&#xA;&lt;p&gt;In order to tackle this project, I was looking into existing methods.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
