Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames

Daisuke Kawahara; Ryohei Sasano; Sadao Kurohashi

Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames

Daisuke Kawahara, Ryohei Sasano, Sadao Kurohashi

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

Abstract

This paper proposes a wide-range anaphora resolution system toward text understanding. This system resolves zero, direct and indirect anaphors in Japanese texts by integrating two sorts of linguistic resources: a hand-annotated corpus with various relations and automatically constructed case frames. The corpus has relevance tags which consist of predicate-argument relations, relations between nouns and coreferences, and is utilized for learning parameters of the system and testing it. The case frames are indispensable knowledge both for detecting zero/indirect anaphors and estimating appropriate antecedents. Our preliminary experiments showed promising results.

Original language	English
Title of host publication	Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004
Editors	Maria Francisca Xavier, Rute Costa, Fatima Ferreira, Maria Teresa Lino, Raquel Silva
Publisher	European Language Resources Association (ELRA)
Pages	1833-1836
Number of pages	4
ISBN (Electronic)	2951740816, 9782951740815
Publication status	Published - 2004
Externally published	Yes
Event	4th International Conference on Language Resources and Evaluation, LREC 2004 - Lisbon, Portugal Duration: 2004 May 26 → 2004 May 28

Publication series

Name	Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004

Other

Other	4th International Conference on Language Resources and Evaluation, LREC 2004
Country/Territory	Portugal
City	Lisbon
Period	04/5/26 → 04/5/28

ASJC Scopus subject areas

Library and Information Sciences
Education
Language and Linguistics
Linguistics and Language

Cite this

Kawahara, D., Sasano, R., & Kurohashi, S. (2004). Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames. In M. F. Xavier, R. Costa, F. Ferreira, M. T. Lino, & R. Silva (Eds.), Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004 (pp. 1833-1836). (Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004). European Language Resources Association (ELRA).

Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames. / Kawahara, Daisuke; Sasano, Ryohei; Kurohashi, Sadao.
Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. ed. / Maria Francisca Xavier; Rute Costa; Fatima Ferreira; Maria Teresa Lino; Raquel Silva. European Language Resources Association (ELRA), 2004. p. 1833-1836 (Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004).

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

Kawahara, D, Sasano, R & Kurohashi, S 2004, Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames. in MF Xavier, R Costa, F Ferreira, MT Lino & R Silva (eds), Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004, European Language Resources Association (ELRA), pp. 1833-1836, 4th International Conference on Language Resources and Evaluation, LREC 2004, Lisbon, Portugal, 04/5/26.

Kawahara D, Sasano R, Kurohashi S. Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames. In Xavier MF, Costa R, Ferreira F, Lino MT, Silva R, editors, Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. European Language Resources Association (ELRA). 2004. p. 1833-1836. (Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004).

Kawahara, Daisuke ; Sasano, Ryohei ; Kurohashi, Sadao. / Toward text understanding : Integrating relevance-tagged corpus and automatically constructed case frames. Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. editor / Maria Francisca Xavier ; Rute Costa ; Fatima Ferreira ; Maria Teresa Lino ; Raquel Silva. European Language Resources Association (ELRA), 2004. pp. 1833-1836 (Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004).

@inproceedings{7cee96819d064b6b9eaf2dba0bd593b3,

title = "Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames",

abstract = "This paper proposes a wide-range anaphora resolution system toward text understanding. This system resolves zero, direct and indirect anaphors in Japanese texts by integrating two sorts of linguistic resources: a hand-annotated corpus with various relations and automatically constructed case frames. The corpus has relevance tags which consist of predicate-argument relations, relations between nouns and coreferences, and is utilized for learning parameters of the system and testing it. The case frames are indispensable knowledge both for detecting zero/indirect anaphors and estimating appropriate antecedents. Our preliminary experiments showed promising results.",

author = "Daisuke Kawahara and Ryohei Sasano and Sadao Kurohashi",

year = "2004",

language = "English",

series = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",

publisher = "European Language Resources Association (ELRA)",

pages = "1833--1836",

editor = "Xavier, {Maria Francisca} and Rute Costa and Fatima Ferreira and Lino, {Maria Teresa} and Raquel Silva",

booktitle = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",

note = "4th International Conference on Language Resources and Evaluation, LREC 2004 ; Conference date: 26-05-2004 Through 28-05-2004",

}

TY - GEN

T1 - Toward text understanding

T2 - 4th International Conference on Language Resources and Evaluation, LREC 2004

AU - Kawahara, Daisuke

AU - Sasano, Ryohei

AU - Kurohashi, Sadao

PY - 2004

Y1 - 2004

N2 - This paper proposes a wide-range anaphora resolution system toward text understanding. This system resolves zero, direct and indirect anaphors in Japanese texts by integrating two sorts of linguistic resources: a hand-annotated corpus with various relations and automatically constructed case frames. The corpus has relevance tags which consist of predicate-argument relations, relations between nouns and coreferences, and is utilized for learning parameters of the system and testing it. The case frames are indispensable knowledge both for detecting zero/indirect anaphors and estimating appropriate antecedents. Our preliminary experiments showed promising results.

AB - This paper proposes a wide-range anaphora resolution system toward text understanding. This system resolves zero, direct and indirect anaphors in Japanese texts by integrating two sorts of linguistic resources: a hand-annotated corpus with various relations and automatically constructed case frames. The corpus has relevance tags which consist of predicate-argument relations, relations between nouns and coreferences, and is utilized for learning parameters of the system and testing it. The case frames are indispensable knowledge both for detecting zero/indirect anaphors and estimating appropriate antecedents. Our preliminary experiments showed promising results.

UR - http://www.scopus.com/inward/record.url?scp=77952971817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952971817&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77952971817

T3 - Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004

SP - 1833

EP - 1836

BT - Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004

A2 - Xavier, Maria Francisca

A2 - Costa, Rute

A2 - Ferreira, Fatima

A2 - Lino, Maria Teresa

A2 - Silva, Raquel

PB - European Language Resources Association (ELRA)

Y2 - 26 May 2004 through 28 May 2004

ER -

Toward text understanding: Integrating relevance-tagged corpus and automatically constructed case frames

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this