Paraphrase substitution for recognizing textual entailment

W.E. Bosma; C. Callison-Burch

Paraphrase substitution for recognizing textual entailment

W.E. Bosma, C. Callison-Burch

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

Abstract

We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a ﬂexible match using automatically generated paraphrases. We ��?nd that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages.

Original language	Undefined
Title of host publication	Working Notes of CLEF 2006
Editors	A. Nardi, C. Peters, J.L. Vicedo
Publisher	CLEF
Pages	1-8
Number of pages	8
ISBN (Print)	2-912335-23-x
Publication status	Published - 20 Sep 2006
Event	7th Workshop of the Cross-Language Evaluation Forum, CLEF 2006 - Alicante, Spain Duration: 20 Sep 2006 → 22 Sep 2006 Conference number: 7

Publication series

Name
Publisher	CLEF
Number	10
ISSN (Print)	1818-8044

Workshop

Workshop	7th Workshop of the Cross-Language Evaluation Forum, CLEF 2006
Abbreviated title	CLEF 2006
Country/Territory	Spain
City	Alicante
Period	20/09/06 → 22/09/06

Keywords

EWI-9709
IR-64000
METIS-248215
HMI-SLT: Speech and Language Technology

Access to Document

Cite this

@inproceedings{45e1e07e7cb149038f49f9873e46f08a,

title = "Paraphrase substitution for recognizing textual entailment",

abstract = "We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a ﬂexible match using automatically generated paraphrases. We ��?nd that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages.",

keywords = "EWI-9709, IR-64000, METIS-248215, HMI-SLT: Speech and Language Technology",

author = "W.E. Bosma and C. Callison-Burch",

year = "2006",

month = sep,

day = "20",

language = "Undefined",

isbn = "2-912335-23-x",

publisher = "CLEF",

number = "10",

pages = "1--8",

editor = "A. Nardi and C. Peters and J.L. Vicedo",

booktitle = "Working Notes of CLEF 2006",

note = "null ; Conference date: 20-09-2006 Through 22-09-2006",

}

TY - GEN

T1 - Paraphrase substitution for recognizing textual entailment

AU - Bosma, W.E.

AU - Callison-Burch, C.

N1 - Conference code: 7

PY - 2006/9/20

Y1 - 2006/9/20

N2 - We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a ﬂexible match using automatically generated paraphrases. We ��?nd that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages.

AB - We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a ﬂexible match using automatically generated paraphrases. We ��?nd that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages.

KW - EWI-9709

KW - IR-64000

KW - METIS-248215

KW - HMI-SLT: Speech and Language Technology

M3 - Conference contribution

SN - 2-912335-23-x

SP - 1

EP - 8

BT - Working Notes of CLEF 2006

A2 - Nardi, A.

A2 - Peters, C.

A2 - Vicedo, J.L.

PB - CLEF

Y2 - 20 September 2006 through 22 September 2006

ER -