Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents

Daisuke Kawahara; Sadao Kurohashi

doi:10.1007/978-3-540-30211-7_2

Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents

Daisuke Kawahara, Sadao Kurohashi

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in its close position. Experimental results on 100 articles indicated that the precision and recall of zero pronoun detection is 87.1% and 74.8% respectively and the accuracy of antecedent estimation is 61.8%.

Original language	English
Pages (from-to)	12-21
Number of pages	10
Journal	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	3248
DOIs	https://doi.org/10.1007/978-3-540-30211-7_2
Publication status	Published - 2005
Externally published	Yes
Event	First International Joint Conference on Natural Language Processing - IJCNLP 2004 - Hainan Island, China Duration: Mar 22 2004 → Mar 24 2004

All Science Journal Classification (ASJC) codes

Theoretical Computer Science
Computer Science(all)

Access to Document

10.1007/978-3-540-30211-7_2

Cite this

@article{fe52aaf3d3414ae0b19b81da45426729,

title = "Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents",

abstract = "This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in its close position. Experimental results on 100 articles indicated that the precision and recall of zero pronoun detection is 87.1% and 74.8% respectively and the accuracy of antecedent estimation is 61.8%.",

author = "Daisuke Kawahara and Sadao Kurohashi",

year = "2005",

doi = "10.1007/978-3-540-30211-7_2",

language = "English",

volume = "3248",

pages = "12--21",

journal = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

issn = "0302-9743",

publisher = "Springer Verlag",

note = "First International Joint Conference on Natural Language Processing - IJCNLP 2004 ; Conference date: 22-03-2004 Through 24-03-2004",

}

TY - JOUR

T1 - Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2005

Y1 - 2005

N2 - This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in its close position. Experimental results on 100 articles indicated that the precision and recall of zero pronoun detection is 87.1% and 74.8% respectively and the accuracy of antecedent estimation is 61.8%.

AB - This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in its close position. Experimental results on 100 articles indicated that the precision and recall of zero pronoun detection is 87.1% and 74.8% respectively and the accuracy of antecedent estimation is 61.8%.

UR - http://www.scopus.com/inward/record.url?scp=26444527947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444527947&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-30211-7_2

DO - 10.1007/978-3-540-30211-7_2

M3 - Conference article

AN - SCOPUS:26444527947

SN - 0302-9743

VL - 3248

SP - 12

EP - 21

JO - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

JF - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

T2 - First International Joint Conference on Natural Language Processing - IJCNLP 2004

Y2 - 22 March 2004 through 24 March 2004

ER -

Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this