Misreading Chat

#38 – Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates

Listen Later

ニューラル自然言語処理の前処理として複雑な単語を限られた語彙集合で分割するアルゴリズムについて向井が話します。感想などはハッシュタグ #misreading か [email protected] にお寄せください。

https://misreading.chat/wp-content/uploads/2018/11/ep381.mp3

  • Neural Machine Translation of Rare Words with Subword Units
  • [1804.10959] Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
  • google/sentencepiece: Unsupervised text tokenizer for Neural Network-based text generation.
  • vocabulary for chromium class names
    • subword examples

      •  

      • WebAssembly Threads ready to try in Chrome 70
        • WebAssembly/threads: Threads and Atomics in WebAssembly
          • ...more
          View all episodesView all episodes
          Download on the App Store
          Misreading ChatBy Hajime Morrita, Jun Mukai
          • 5
          • 5
          • 5
          • 5
          • 5

          5

          6 ratings

          More shows like Misreading Chat

          View all
          Rebuild by Tatsuhiko Miyagawa

          Rebuild

          48 Listeners

          耳で学ぶAI、ロボシンク by 矢野 哲平

          耳で学ぶAI、ロボシンク

          0 Listeners