Paraphrase identification with lexico-syntactic graph subsumption

Vasile Rus, Philip M. McCarthy, Mihai C. Lintean, Danielle McNamara, Arthur C. Graesser

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

50 Citations (Scopus)

Abstract

The paper presents a new approach to the problem of paraphrase identification. The new approach extends a previously proposed method for the task of textual entailment. The relationship between paraphrases and entailment is discussed to theoretically justify the new approach. The proposed approach is useful because it uses relatively few resources compared to similar systems yet it produces results similar or better than other approaches to paraphrase identification. The approach also offers significantly better results than two baselines. We report results on a standard data set as well as on a new, balanced data set.

Original languageEnglish (US)
Title of host publicationProceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21
Pages201-206
Number of pages6
StatePublished - 2008
Externally publishedYes
Event21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21 - Coconut Grove, FL, United States
Duration: May 15 2008May 17 2008

Other

Other21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21
CountryUnited States
CityCoconut Grove, FL
Period5/15/085/17/08

Fingerprint

Syntactics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Rus, V., McCarthy, P. M., Lintean, M. C., McNamara, D., & Graesser, A. C. (2008). Paraphrase identification with lexico-syntactic graph subsumption. In Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21 (pp. 201-206)

Paraphrase identification with lexico-syntactic graph subsumption. / Rus, Vasile; McCarthy, Philip M.; Lintean, Mihai C.; McNamara, Danielle; Graesser, Arthur C.

Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21. 2008. p. 201-206.

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

Rus, V, McCarthy, PM, Lintean, MC, McNamara, D & Graesser, AC 2008, Paraphrase identification with lexico-syntactic graph subsumption. in Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21. pp. 201-206, 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21, Coconut Grove, FL, United States, 5/15/08.
Rus V, McCarthy PM, Lintean MC, McNamara D, Graesser AC. Paraphrase identification with lexico-syntactic graph subsumption. In Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21. 2008. p. 201-206
Rus, Vasile ; McCarthy, Philip M. ; Lintean, Mihai C. ; McNamara, Danielle ; Graesser, Arthur C. / Paraphrase identification with lexico-syntactic graph subsumption. Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21. 2008. pp. 201-206
@inproceedings{a8ef7b91d0cb499ba999631739607179,
title = "Paraphrase identification with lexico-syntactic graph subsumption",
abstract = "The paper presents a new approach to the problem of paraphrase identification. The new approach extends a previously proposed method for the task of textual entailment. The relationship between paraphrases and entailment is discussed to theoretically justify the new approach. The proposed approach is useful because it uses relatively few resources compared to similar systems yet it produces results similar or better than other approaches to paraphrase identification. The approach also offers significantly better results than two baselines. We report results on a standard data set as well as on a new, balanced data set.",
author = "Vasile Rus and McCarthy, {Philip M.} and Lintean, {Mihai C.} and Danielle McNamara and Graesser, {Arthur C.}",
year = "2008",
language = "English (US)",
isbn = "9781577353652",
pages = "201--206",
booktitle = "Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21",

}

TY - GEN

T1 - Paraphrase identification with lexico-syntactic graph subsumption

AU - Rus, Vasile

AU - McCarthy, Philip M.

AU - Lintean, Mihai C.

AU - McNamara, Danielle

AU - Graesser, Arthur C.

PY - 2008

Y1 - 2008

N2 - The paper presents a new approach to the problem of paraphrase identification. The new approach extends a previously proposed method for the task of textual entailment. The relationship between paraphrases and entailment is discussed to theoretically justify the new approach. The proposed approach is useful because it uses relatively few resources compared to similar systems yet it produces results similar or better than other approaches to paraphrase identification. The approach also offers significantly better results than two baselines. We report results on a standard data set as well as on a new, balanced data set.

AB - The paper presents a new approach to the problem of paraphrase identification. The new approach extends a previously proposed method for the task of textual entailment. The relationship between paraphrases and entailment is discussed to theoretically justify the new approach. The proposed approach is useful because it uses relatively few resources compared to similar systems yet it produces results similar or better than other approaches to paraphrase identification. The approach also offers significantly better results than two baselines. We report results on a standard data set as well as on a new, balanced data set.

UR - http://www.scopus.com/inward/record.url?scp=55849148021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55849148021&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577353652

SP - 201

EP - 206

BT - Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference, FLAIRS-21

ER -