Combining multiple resources to improve SMT-based paraphrasing model

Shiqi Zhao; Cheng Niu; Ming Zhou; Ting Liu; Sheng Li

Combining multiple resources to improve SMT-based paraphrasing model

Shiqi Zhao^*
, Cheng Niu
, Ming Zhou
, Ting Liu
, Sheng Li

^*Corresponding author for this work

Faculty of Computing

Harbin Institute of Technology
Microsoft USA

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

66 Scopus citations

Abstract

This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60% and 55%, respectively. In addition, the contribution of each resource is evaluated, which indicates that all the exploited resources are useful for generating paraphrases of high quality.

Original language	English
Title of host publication	ACL-08
Subtitle of host publication	HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
Pages	1021-1029
Number of pages	9
State	Published - 2008
Event	46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT - Columbus, OH, United States Duration: 15 Jun 2008 → 20 Jun 2008

Publication series

Name	ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference	46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT
Country/Territory	United States
City	Columbus, OH
Period	15/06/08 → 20/06/08

Cite this

Zhao, S., Niu, C., Zhou, M., Liu, T., & Li, S. (2008). Combining multiple resources to improve SMT-based paraphrasing model. In ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 1021-1029). (ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

Zhao, Shiqi ; Niu, Cheng ; Zhou, Ming et al. / Combining multiple resources to improve SMT-based paraphrasing model. ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. pp. 1021-1029 (ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

@inproceedings{2288883a1d7f410a8ed283e82741e326,

title = "Combining multiple resources to improve SMT-based paraphrasing model",

abstract = "This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60\% and 55\%, respectively. In addition, the contribution of each resource is evaluated, which indicates that all the exploited resources are useful for generating paraphrases of high quality.",

author = "Shiqi Zhao and Cheng Niu and Ming Zhou and Ting Liu and Sheng Li",

year = "2008",

language = "英语",

isbn = "9781932432046",

series = "ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",

pages = "1021--1029",

booktitle = "ACL-08",

note = "46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT ; Conference date: 15-06-2008 Through 20-06-2008",

}

Zhao, S, Niu, C, Zhou, M, Liu, T & Li, S 2008, Combining multiple resources to improve SMT-based paraphrasing model. in ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, pp. 1021-1029, 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT, Columbus, OH, United States, 15/06/08.

Combining multiple resources to improve SMT-based paraphrasing model. / Zhao, Shiqi; Niu, Cheng; Zhou, Ming et al.
ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. p. 1021-1029 (ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Combining multiple resources to improve SMT-based paraphrasing model

AU - Zhao, Shiqi

AU - Niu, Cheng

AU - Zhou, Ming

AU - Liu, Ting

AU - Li, Sheng

PY - 2008

Y1 - 2008

N2 - This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60% and 55%, respectively. In addition, the contribution of each resource is evaluated, which indicates that all the exploited resources are useful for generating paraphrases of high quality.

AB - This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60% and 55%, respectively. In addition, the contribution of each resource is evaluated, which indicates that all the exploited resources are useful for generating paraphrases of high quality.

UR - https://www.scopus.com/pages/publications/84859901584

M3 - 会议稿件

AN - SCOPUS:84859901584

SN - 9781932432046

T3 - ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

SP - 1021

EP - 1029

BT - ACL-08

T2 - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT

Y2 - 15 June 2008 through 20 June 2008

ER -

Zhao S, Niu C, Zhou M, Liu T, Li S. Combining multiple resources to improve SMT-based paraphrasing model. In ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. p. 1021-1029. (ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

Combining multiple resources to improve SMT-based paraphrasing model

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this