Skip to content

Latest commit

 

History

History
44 lines (19 loc) · 1.66 KB

Paraphrase Generation.md

File metadata and controls

44 lines (19 loc) · 1.66 KB

https://en.wikipedia.org/wiki/Paraphrasing_(computational_linguistics)

methods:

Deep Reinforcement Learning

VAE

Literature review

  • A Survey of Paraphrasing and Textual Entailment Methods, 2010 arxiv

paper

  • Dictionary-Guided Editing Networks for Paraphrase Generation, AAAI 2019, arxiv

  • Paraphrase Generation with Deep Reinforcement Learning, EMNLP 2018, arxiv | pdf | code

    • generation model

      notes The generator, built as a sequence-to-sequence learning model, can produce paraphrases given a sentence.
      The evaluator, constructed as a deep matching model, can judge whether two sentences are paraphrases of each other.
      The generator is first trained by deep learning and then further fine-tuned by reinforcement learning in which the reward is given by the evaluator.

  • A Deep Generative Framework for Paraphrase Generation, AAAI 2018, arxiv | blog | code | code

  • Neural Paraphrase Generation with Stacked Residual LSTM Networks, COLING 2016 arxiv | code

tools