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

Split and Rephrase: Better Evaluation and a Str...

katsutan
November 12, 2018

Split and Rephrase: Better Evaluation and a Stronger Baseline

文献紹介

katsutan

November 12, 2018
Tweet

More Decks by katsutan

Other Decks in Technology

Transcript

  1. Split and Rephrase: Better Evaluation and a Stronger Baseline Roee

    Aharoni & Yoav Goldberg Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 719–724 Melbourne, Australia, July 15 - 20, 2018. 長岡技術科学大学 自然言語処理研究室 勝田 哲弘
  2. Introduction “Split-and-Rephrase” by Narayan et al. (2017) • データセット、評価方法、ベースラインの設定 •

    BlEU ◦ 48.9 for the best text-to-text system. ◦ 78.7 for the best RDF-aware one. text-to-textモデルに注目 3
  3. Preliminary Experiments Experimental Details • vanilla sequence-to-sequence models with attention

    (Bahdanau et al., 2015) ◦ OPENNMT-PY toolkit (Klein et al., 2017) ◦ LSTM cell size (128, 256 and 512, respectively) 6
  4. Experiments and Results 新しいデータセットによる評価 • new data split • v1.0

    モデルの拡張: Copy • copy-enhanced models of varying LSTM widths ◦ (128, 256 and 512) 12