An-Operation-Network-for-Abstractive-Sentence-Compression.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=47 MARUYAMA
July 25, 2018
43

 An-Operation-Network-for-Abstractive-Sentence-Compression.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=128

MARUYAMA

July 25, 2018
Tweet

Transcript

  1. An Operation Network for Abstractive Sentence Compression Naitong Yu, Jie

    Zhang, Minlie Huang, Xiaoyan Zhu The 27th International Conference on Computational Linguistics (COLING 2018) Nagaoka University of Technology Takumi Maruyama Literature review:
  2. Introduction Ø %*, • % (" %+ Ø 2 

    • Delete-based approach • Generate-based approach Ø 0/- • %*, )&.$ • Delete-based approach Generate-based approach # State-of-the-art'!
  3. Introduction Ø Delete-based approach • )+59G%?7””  • 5BC””FE6 D2

    • “” & $(5BC@ Ø Generate-based approach • “=;””>A”, “.<”, “H)”& • ,4*”=;”/0 8: Delete-based approachGenerate-based approach /' “=;”-) "!#31
  4. Baselines Ø Seq2seq (generate-only model)

  5. Baselines Ø Pointer-Generator (copy-and-generate model)

  6. Method Ø Operation Network

  7. Method Ø Delete decoder • • !" ∈ $, &

    '( : *+,ℎ.//01 '2320, 4( : 4512062 704258 0(6( ): 6( 0;<0//.1=
  8. Method Ø Copy-Generate decoder • Generate probability Generate modeCopy mode

    - Generate mode - Copy mode attention distribution   • Final probability distribution
  9. Method Ø Copy-Generate decoder •

  10. Dataset Ø Toutanova et al. (2016) • Business letters, news

    journals, technical documents • Training set: 21, 145 pairs Validation set: 1,908 pairs Test set: 3,370 pairs
  11. Evaluation Metrics Ø Automatic evaluation • Compression Ratio • ROUGE

    (ROUGE-1, ROUGE-2, ROUGE-L) • BLEU Ø Manual evaluation • Grammaticality • Non-Redundancy
  12. Results

  13. Results

  14. Conclusion Ø Delete-based approachGenerate-based approach    Ø Delete

      Ø Abstractive sentence compressionSOTA