Recognizing Textual Entailment via atomic propositions

Elena Akhmatova; Diego Mollá

doi:10.1007/11736790_22

Recognizing Textual Entailment via atomic propositions

Elena Akhmatova^*, Diego Mollá

^*Corresponding author for this work

School of Computing

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

5 Citations (Scopus)

Abstract

This paper describes Macquarie University's Centre for Language Technology contribution to the PASCAL 2005 Recognizing Textual Entailment challenge. Our main aim was to test the practicability of a purely logical approach. For this, atomic propositions were extracted from both the text and the entailment hypothesis and they were expressed in a custom logical notation. The text entails the hypothesis if every proposition of the hypothesis is entailed by some proposition in the text. To extract the propositions and encode them into a logical notation the system uses the output of Link Parser. To detect the independent entailment relations the system relies on the use of Otter and WordNet.

Original language	English
Title of host publication	Machine Learning Challenges
Subtitle of host publication	Evaluating Predictive Uncertainty, Visual Object Classification, and Recogisng Textual Entailment
Editors	Joaquin Quiñonero-Candela, Ido Dagan, Bernardo = Magnini, Florence d’Alché-Buc
Place of Publication	Berlin, Heidelberg
Publisher	Springer, Springer Nature
Pages	385-403
Number of pages	19
ISBN (Print)	3540334270, 9783540334279
DOIs	https://doi.org/10.1007/11736790_22
Publication status	Published - 2006
Event	1st PASCAL Machine Learning Challenges Workshop, MLCW 2005 - Southampton, United Kingdom Duration: 11 Apr 2005 → 13 Apr 2005

Publication series

Name	Lecture Notes in Computer Science
Volume	3944
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Other

Other	1st PASCAL Machine Learning Challenges Workshop, MLCW 2005
Country/Territory	United Kingdom
City	Southampton
Period	11/04/05 → 13/04/05

Access to Document

10.1007/11736790_22

Cite this

Akhmatova, E., & Mollá, D. (2006). Recognizing Textual Entailment via atomic propositions. In J. Quiñonero-Candela, I. Dagan, B. . Magnini, & F. d’Alché-Buc (Eds.), Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recogisng Textual Entailment (pp. 385-403). (Lecture Notes in Computer Science; Vol. 3944). Springer, Springer Nature. https://doi.org/10.1007/11736790_22

Akhmatova, Elena ; Mollá, Diego. / Recognizing Textual Entailment via atomic propositions. Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recogisng Textual Entailment. editor / Joaquin Quiñonero-Candela ; Ido Dagan ; Bernardo = Magnini ; Florence d’Alché-Buc. Berlin, Heidelberg : Springer, Springer Nature, 2006. pp. 385-403 (Lecture Notes in Computer Science).

@inproceedings{670ef17e7abd4c8e84e5e38ea780b448,

title = "Recognizing Textual Entailment via atomic propositions",

abstract = "This paper describes Macquarie University's Centre for Language Technology contribution to the PASCAL 2005 Recognizing Textual Entailment challenge. Our main aim was to test the practicability of a purely logical approach. For this, atomic propositions were extracted from both the text and the entailment hypothesis and they were expressed in a custom logical notation. The text entails the hypothesis if every proposition of the hypothesis is entailed by some proposition in the text. To extract the propositions and encode them into a logical notation the system uses the output of Link Parser. To detect the independent entailment relations the system relies on the use of Otter and WordNet.",

author = "Elena Akhmatova and Diego Moll{\'a}",

year = "2006",

doi = "10.1007/11736790_22",

language = "English",

isbn = "3540334270",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Springer Nature",

pages = "385--403",

editor = "Joaquin Qui{\~n}onero-Candela and Ido Dagan and Magnini, {Bernardo =} and Florence d{\textquoteright}Alch{\'e}-Buc",

booktitle = "Machine Learning Challenges",

address = "United States",

note = "1st PASCAL Machine Learning Challenges Workshop, MLCW 2005 ; Conference date: 11-04-2005 Through 13-04-2005",

}

Akhmatova, E & Mollá, D 2006, Recognizing Textual Entailment via atomic propositions. in J Quiñonero-Candela, I Dagan, B Magnini & F d’Alché-Buc (eds), Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recogisng Textual Entailment. Lecture Notes in Computer Science, vol. 3944, Springer, Springer Nature, Berlin, Heidelberg, pp. 385-403, 1st PASCAL Machine Learning Challenges Workshop, MLCW 2005, Southampton, United Kingdom, 11/04/05. https://doi.org/10.1007/11736790_22

Recognizing Textual Entailment via atomic propositions. / Akhmatova, Elena; Mollá, Diego.
Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recogisng Textual Entailment. ed. / Joaquin Quiñonero-Candela; Ido Dagan; Bernardo = Magnini; Florence d’Alché-Buc. Berlin, Heidelberg: Springer, Springer Nature, 2006. p. 385-403 (Lecture Notes in Computer Science; Vol. 3944).

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

TY - GEN

T1 - Recognizing Textual Entailment via atomic propositions

AU - Akhmatova, Elena

AU - Mollá, Diego

PY - 2006

Y1 - 2006

N2 - This paper describes Macquarie University's Centre for Language Technology contribution to the PASCAL 2005 Recognizing Textual Entailment challenge. Our main aim was to test the practicability of a purely logical approach. For this, atomic propositions were extracted from both the text and the entailment hypothesis and they were expressed in a custom logical notation. The text entails the hypothesis if every proposition of the hypothesis is entailed by some proposition in the text. To extract the propositions and encode them into a logical notation the system uses the output of Link Parser. To detect the independent entailment relations the system relies on the use of Otter and WordNet.

AB - This paper describes Macquarie University's Centre for Language Technology contribution to the PASCAL 2005 Recognizing Textual Entailment challenge. Our main aim was to test the practicability of a purely logical approach. For this, atomic propositions were extracted from both the text and the entailment hypothesis and they were expressed in a custom logical notation. The text entails the hypothesis if every proposition of the hypothesis is entailed by some proposition in the text. To extract the propositions and encode them into a logical notation the system uses the output of Link Parser. To detect the independent entailment relations the system relies on the use of Otter and WordNet.

UR - http://www.scopus.com/inward/record.url?scp=33745819979&partnerID=8YFLogxK

U2 - 10.1007/11736790_22

DO - 10.1007/11736790_22

M3 - Conference proceeding contribution

AN - SCOPUS:33745819979

SN - 3540334270

SN - 9783540334279

T3 - Lecture Notes in Computer Science

SP - 385

EP - 403

BT - Machine Learning Challenges

A2 - Quiñonero-Candela, Joaquin

A2 - Dagan, Ido

A2 - Magnini, Bernardo =

A2 - d’Alché-Buc, Florence

PB - Springer, Springer Nature

CY - Berlin, Heidelberg

T2 - 1st PASCAL Machine Learning Challenges Workshop, MLCW 2005

Y2 - 11 April 2005 through 13 April 2005

ER -

Akhmatova E, Mollá D. Recognizing Textual Entailment via atomic propositions. In Quiñonero-Candela J, Dagan I, Magnini B, d’Alché-Buc F, editors, Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recogisng Textual Entailment. Berlin, Heidelberg: Springer, Springer Nature. 2006. p. 385-403. (Lecture Notes in Computer Science). doi: 10.1007/11736790_22

Recognizing Textual Entailment via atomic propositions

Abstract

Publication series

Other

Access to Document

Other files and links

Fingerprint

Cite this