Discriminative phrase embedding for paraphrase identification

Wenpeng Yin; Hinrich Schütze

doi:10.3115/v1/n15-1154

Discriminative phrase embedding for paraphrase identification

Wenpeng Yin, Hinrich Schütze

Computer Science and Engineering

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

23 Scopus citations

Abstract

This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.

Original language	English (US)
Title of host publication	NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	1368-1373
Number of pages	6
ISBN (Electronic)	9781941643495
DOIs	https://doi.org/10.3115/v1/n15-1154
State	Published - 2015
Event	Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 - Denver, United States Duration: May 31 2015 → Jun 5 2015

Publication series

Name	NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference	Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
Country/Territory	United States
City	Denver
Period	5/31/15 → 6/5/15

All Science Journal Classification (ASJC) codes

Computer Science Applications
Language and Linguistics
Linguistics and Language

Access to Document

10.3115/v1/n15-1154

Cite this

Yin, W., & Schütze, H. (2015). Discriminative phrase embedding for paraphrase identification. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 1368-1373). (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/n15-1154

Yin, Wenpeng ; Schütze, Hinrich. / Discriminative phrase embedding for paraphrase identification. NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. pp. 1368-1373 (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

@inproceedings{fecf976f2b7e4d8684a8992363cc3a31,

title = "Discriminative phrase embedding for paraphrase identification",

abstract = "This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.",

author = "Wenpeng Yin and Hinrich Sch{\"u}tze",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 ; Conference date: 31-05-2015 Through 05-06-2015",

year = "2015",

doi = "10.3115/v1/n15-1154",

language = "English (US)",

series = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1368--1373",

booktitle = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics",

}

Yin, W & Schütze, H 2015, Discriminative phrase embedding for paraphrase identification. in NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 1368-1373, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015, Denver, United States, 5/31/15. https://doi.org/10.3115/v1/n15-1154

Discriminative phrase embedding for paraphrase identification. / Yin, Wenpeng; Schütze, Hinrich.
NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. p. 1368-1373 (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

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

TY - GEN

T1 - Discriminative phrase embedding for paraphrase identification

AU - Yin, Wenpeng

AU - Schütze, Hinrich

PY - 2015

Y1 - 2015

N2 - This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.

AB - This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.

UR - http://www.scopus.com/inward/record.url?scp=84960156158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960156158&partnerID=8YFLogxK

U2 - 10.3115/v1/n15-1154

DO - 10.3115/v1/n15-1154

M3 - Conference contribution

AN - SCOPUS:84960156158

T3 - NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

SP - 1368

EP - 1373

BT - NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

T2 - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015

Y2 - 31 May 2015 through 5 June 2015

ER -

Yin W, Schütze H. Discriminative phrase embedding for paraphrase identification. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2015. p. 1368-1373. (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). doi: 10.3115/v1/n15-1154

Discriminative phrase embedding for paraphrase identification

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this