Introduction of a new paraphrase generation tool based on Monte-Carlo sampling

Jonathan Chevelu, Thomas Lavergne, Yves Lepage, Thierry Moudenc

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

We propose a new specifically designed method for paraphrase generation based on Monte-Carlo sampling and show how this algorithm is suitable for its task. Moreover, the basic algorithm presented here leaves a lot of opportunities for future improvement. In particular, our algorithm does not constraint the scoring function in opposite to Viterbi based decoders. It is now possible to use some global features in paraphrase scoring functions. This algorithm opens new outlooks for paraphrase generation and other natural language processing applications like statistical machine translation.

Original languageEnglish
Title of host publicationACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.
Pages249-252
Number of pages4
Publication statusPublished - 2009
Externally publishedYes
EventJoint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 - Suntec
Duration: 2009 Aug 22009 Aug 7

Other

OtherJoint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009
CitySuntec
Period09/8/209/8/7

Fingerprint

Paraphrase
Sampling
language
Scoring
Statistical Machine Translation
Natural Language Processing

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Chevelu, J., Lavergne, T., Lepage, Y., & Moudenc, T. (2009). Introduction of a new paraphrase generation tool based on Monte-Carlo sampling. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf. (pp. 249-252)

Introduction of a new paraphrase generation tool based on Monte-Carlo sampling. / Chevelu, Jonathan; Lavergne, Thomas; Lepage, Yves; Moudenc, Thierry.

ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. 2009. p. 249-252.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chevelu, J, Lavergne, T, Lepage, Y & Moudenc, T 2009, Introduction of a new paraphrase generation tool based on Monte-Carlo sampling. in ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. pp. 249-252, Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, 09/8/2.
Chevelu J, Lavergne T, Lepage Y, Moudenc T. Introduction of a new paraphrase generation tool based on Monte-Carlo sampling. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. 2009. p. 249-252
Chevelu, Jonathan ; Lavergne, Thomas ; Lepage, Yves ; Moudenc, Thierry. / Introduction of a new paraphrase generation tool based on Monte-Carlo sampling. ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. 2009. pp. 249-252
@inproceedings{7b4a07ca8a264ed8b73971476a8dc94a,
title = "Introduction of a new paraphrase generation tool based on Monte-Carlo sampling",
abstract = "We propose a new specifically designed method for paraphrase generation based on Monte-Carlo sampling and show how this algorithm is suitable for its task. Moreover, the basic algorithm presented here leaves a lot of opportunities for future improvement. In particular, our algorithm does not constraint the scoring function in opposite to Viterbi based decoders. It is now possible to use some global features in paraphrase scoring functions. This algorithm opens new outlooks for paraphrase generation and other natural language processing applications like statistical machine translation.",
author = "Jonathan Chevelu and Thomas Lavergne and Yves Lepage and Thierry Moudenc",
year = "2009",
language = "English",
isbn = "9781617382581",
pages = "249--252",
booktitle = "ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.",

}

TY - GEN

T1 - Introduction of a new paraphrase generation tool based on Monte-Carlo sampling

AU - Chevelu, Jonathan

AU - Lavergne, Thomas

AU - Lepage, Yves

AU - Moudenc, Thierry

PY - 2009

Y1 - 2009

N2 - We propose a new specifically designed method for paraphrase generation based on Monte-Carlo sampling and show how this algorithm is suitable for its task. Moreover, the basic algorithm presented here leaves a lot of opportunities for future improvement. In particular, our algorithm does not constraint the scoring function in opposite to Viterbi based decoders. It is now possible to use some global features in paraphrase scoring functions. This algorithm opens new outlooks for paraphrase generation and other natural language processing applications like statistical machine translation.

AB - We propose a new specifically designed method for paraphrase generation based on Monte-Carlo sampling and show how this algorithm is suitable for its task. Moreover, the basic algorithm presented here leaves a lot of opportunities for future improvement. In particular, our algorithm does not constraint the scoring function in opposite to Viterbi based decoders. It is now possible to use some global features in paraphrase scoring functions. This algorithm opens new outlooks for paraphrase generation and other natural language processing applications like statistical machine translation.

UR - http://www.scopus.com/inward/record.url?scp=77957860080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957860080&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781617382581

SP - 249

EP - 252

BT - ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.

ER -