Sentence_simplification_with_deep_reinforcement_learning.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=47 MARUYAMA
May 21, 2018
48

 Sentence_simplification_with_deep_reinforcement_learning.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=128

MARUYAMA

May 21, 2018
Tweet

Transcript

  1. Sentence Simplification with Deep Reinforcement Learning Proceedings of the 2017

    Conference on Empirical Methods in Natural Language Processing, 2017 pp. 584–594 Zhang Xingxing, Lapata Mirella Nagaoka University of Technology Takumi Maruyama
  2. Abstract Ø Sentence simplification aims to make sentences easier to

    read and understand Ø This paper proposes encoder-decoder model coupled with a deep reinforcement learning frame work for text simplification Ø The proposed model outperforms competitive simplification systems on experiments. 2
  3. Reinforcement Learning for Sentence Simplification Ø This paper proposes following

    two models: • Deep Reinforcement learning sentence simplification model (DRESS) • DRESS + Lexical Simplification model (DRESS-LS) 3
  4. DRESS Ø The overview of deep reinforcement learning simplification model

    4
  5. DRESS Ø The overview of deep reinforcement learning simplification model

    Encoder-Decoder model 5
  6. DRESS Ø The overview of deep reinforcement learning simplification model

    Reinforcement Learning 6
  7. DRESS Ø Reward ! ", $, % $ = '(!(

    ", $, % $ + '*!* ", % $ + '+!+ % $ ,-, ,., ,/ ∈ [0, 1] where 5-: The simplicity reward 5.: The relevance reward 5/: The fluency reward 7
  8. DRESS Ø Reward • Simplicity: • Relevance: • Fluency: !"

    = $%&'( ), + ,, , + . − $ %&'( ), ,, + , !0 = 123 4) , 4+ , = 4) 5 4+ , 4) 4+ , !6 = 789 . + , : ;<. + , =2>?@A B C; |B CE:;G. 4) and 4+ , are sentence vectors 8
  9. DRESS-LS Ø Lexical simplification is a task that replaces complex

    words with simpler alternatives Ø This paper uses pre-trained encoder-decoder model for lexical simplification Ø ! "# "$:#&$ , ( = 1 − , -./ "# "$:#&$ , ( + ,-/1 "# (, 2# Where , ∈ [0,1] 9
  10. Experimental Setup Ø Three simplification datasets • WikiSmall (Zhu et

    al. 2010) • WikiLarge (Kauchak 2013, Woodsend and Lapata 2011, Zhu et al. 2010) • Newsela (Xu et al. 2015) Dataset Train Dev. Test WikiSmall 89,042 205 100 WikiLarge 296,402 2,000 359 Newsela 94,208 1,129 1,076 10
  11. Experimental Setup Ø Comparison systems • PBMT-R: • Hybrid: A

    hybrid semantic-based model that combine simplification model and monolingual machine translation model • SBMT-SARI: A syntax-based translation model trained with PPDB and tuned with SARI A monolingual phrase base machine translation with a reranking post-processing step 11
  12. Results (Five point Likert scale) 12

  13. Results (Five point Likert scale) 13

  14. Results (Five point Likert scale) 14

  15. Results 15

  16. Results 16