Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

katsutan
April 08, 2019

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

文献紹介

長岡技術科学大学
勝田 哲弘

katsutan

April 08, 2019
Tweet

More Decks by katsutan

Other Decks in Technology

Transcript

  1. Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated

    Pooling Mechanisms Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 440–450 Melbourne, Australia, July 15 - 20, 2018. 文献紹介: 長岡技術科学大学 勝田 哲弘
  2. Abstract • Simple Word-Embedding-based Models (SWEMs)と word-embedding-based RNN/CNN modelsの比較 ◦

    SWEMsが多くの場合で同等、優れた精度を示す • Parameter freeのpoolingを活用するモデル ◦ hierarchical pooling ◦ parameter数が少なく済む 2
  3. Simple Word-Embedding Model (SWEM) パラメータを持たないモデル • Average-Pooling(一番単純なモデル) • Max Pooling(CNNでのmax-over-time

    pooling に近い) • Hierarchical Pooling ◦ ウィンドウ幅nでavg-poolingを行い、その上にmax-pooling 5
  4. Extension to other languages • Sogou news corpus(a Chinese dataset

    represented by Pinyin) ◦ SWEM-concat accuracy : 91.3% ◦ SWEM-hier (window size of 5) accuracy : 96.2% ◦ CNN (95.6%) and LSTM (95.2%) • より語順に敏感な中国語においても最高精度に匹敵する 14