On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution

Ryu Iida; Kentaro Inui; Yuji Matsumoto

doi:10.1109/NLPKE.2005.1598742

On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution

Ryu Iida, Kentaro Inui, Yuji Matsumoto

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

2 Citations (Scopus)

Abstract

We propose a machine learning-based approach to noun phrase anaphora resolution that combines the advantages of previous learning-based models while overcoming their drawbacks. Our anaphora resolution process reverses the order of the steps in the classification-and-search model proposed by Ng and Cardie [12], but inherits all the advantages of that model. We conducted experiments on resolving noun phrase anaphora in Japanese. The results show that with the classification-and-search based modifications, our proposed model outperforms earlier learning-based approaches.

Original language	English
Title of host publication	Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05
Pages	244-249
Number of pages	6
DOIs	https://doi.org/10.1109/NLPKE.2005.1598742
Publication status	Published - 2005 Dec 1
Externally published	Yes
Event	2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05 - Wuhan, China Duration: 2005 Oct 30 → 2005 Nov 1

Publication series

Name	Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05
Volume	2005

Other

Other	2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05
Country/Territory	China
City	Wuhan
Period	05/10/30 → 05/11/1

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/NLPKE.2005.1598742

Cite this

Iida, R., Inui, K., & Matsumoto, Y. (2005). On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution. In Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05 (pp. 244-249). [1598742] (Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05; Vol. 2005). https://doi.org/10.1109/NLPKE.2005.1598742

On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution. / Iida, Ryu; Inui, Kentaro; Matsumoto, Yuji.

Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05. 2005. p. 244-249 1598742 (Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05; Vol. 2005).

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

Iida, R, Inui, K & Matsumoto, Y 2005, On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution. in Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05., 1598742, Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05, vol. 2005, pp. 244-249, 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05, Wuhan, China, 05/10/30. https://doi.org/10.1109/NLPKE.2005.1598742

Iida R, Inui K, Matsumoto Y. On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution. In Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05. 2005. p. 244-249. 1598742. (Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05). doi: 10.1109/NLPKE.2005.1598742

Iida, Ryu ; Inui, Kentaro ; Matsumoto, Yuji. / On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution. Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05. 2005. pp. 244-249 (Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05).

@inproceedings{57fc5e65fe00419aa68a25929a272448,

title = "On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution",

abstract = "We propose a machine learning-based approach to noun phrase anaphora resolution that combines the advantages of previous learning-based models while overcoming their drawbacks. Our anaphora resolution process reverses the order of the steps in the classification-and-search model proposed by Ng and Cardie [12], but inherits all the advantages of that model. We conducted experiments on resolving noun phrase anaphora in Japanese. The results show that with the classification-and-search based modifications, our proposed model outperforms earlier learning-based approaches.",

author = "Ryu Iida and Kentaro Inui and Yuji Matsumoto",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/NLPKE.2005.1598742",

language = "English",

isbn = "0780393619",

series = "Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05",

pages = "244--249",

booktitle = "Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05",

note = "2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05 ; Conference date: 30-10-2005 Through 01-11-2005",

}

TY - GEN

T1 - On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution

AU - Iida, Ryu

AU - Inui, Kentaro

AU - Matsumoto, Yuji

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We propose a machine learning-based approach to noun phrase anaphora resolution that combines the advantages of previous learning-based models while overcoming their drawbacks. Our anaphora resolution process reverses the order of the steps in the classification-and-search model proposed by Ng and Cardie [12], but inherits all the advantages of that model. We conducted experiments on resolving noun phrase anaphora in Japanese. The results show that with the classification-and-search based modifications, our proposed model outperforms earlier learning-based approaches.

AB - We propose a machine learning-based approach to noun phrase anaphora resolution that combines the advantages of previous learning-based models while overcoming their drawbacks. Our anaphora resolution process reverses the order of the steps in the classification-and-search model proposed by Ng and Cardie [12], but inherits all the advantages of that model. We conducted experiments on resolving noun phrase anaphora in Japanese. The results show that with the classification-and-search based modifications, our proposed model outperforms earlier learning-based approaches.

UR - http://www.scopus.com/inward/record.url?scp=33847288785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847288785&partnerID=8YFLogxK

U2 - 10.1109/NLPKE.2005.1598742

DO - 10.1109/NLPKE.2005.1598742

M3 - Conference contribution

AN - SCOPUS:33847288785

SN - 0780393619

SN - 9780780393615

T3 - Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05

SP - 244

EP - 249

BT - Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05

T2 - 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05

Y2 - 30 October 2005 through 1 November 2005

ER -

On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this