Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser

Daisuke Kawahara, Sadao Kurohashi

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

This paper describes a probabilistic model for coordination disambiguation integrated into syntactic and case structure analysis. Our model probabilistically assesses the parallelism of a candidate coordinate structure using syntactic/semantic similarities and cooccurrence statistics. We integrate these probabilities into the framework of fully-lexicalized parsing based on large-scale case frames. This approach simultaneously addresses two tasks of coordination disambiguation: the detection of coordinate conjunctions and the scope disambiguation of coordinate structures. Experimental results on web sentences indicate the effectiveness of our approach.

Original languageEnglish
Pages306-314
Number of pages9
Publication statusPublished - Dec 1 2007
Event2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007 - Prague, Czech Republic
Duration: Jun 28 2007Jun 28 2007

Other

Other2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007
CountryCzech Republic
CityPrague
Period6/28/076/28/07

Fingerprint

Syntactics
Semantics
Statistics
candidacy
statistics
semantics
Statistical Models

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems
  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Cite this

Kawahara, D., & Kurohashi, S. (2007). Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser. 306-314. Paper presented at 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007, Prague, Czech Republic.

Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser. / Kawahara, Daisuke; Kurohashi, Sadao.

2007. 306-314 Paper presented at 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007, Prague, Czech Republic.

Research output: Contribution to conferencePaper

Kawahara, D & Kurohashi, S 2007, 'Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser', Paper presented at 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007, Prague, Czech Republic, 6/28/07 - 6/28/07 pp. 306-314.
Kawahara D, Kurohashi S. Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser. 2007. Paper presented at 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007, Prague, Czech Republic.
Kawahara, Daisuke ; Kurohashi, Sadao. / Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser. Paper presented at 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007, Prague, Czech Republic.9 p.
@conference{744149badf38420e92b81767651098ab,
title = "Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser",
abstract = "This paper describes a probabilistic model for coordination disambiguation integrated into syntactic and case structure analysis. Our model probabilistically assesses the parallelism of a candidate coordinate structure using syntactic/semantic similarities and cooccurrence statistics. We integrate these probabilities into the framework of fully-lexicalized parsing based on large-scale case frames. This approach simultaneously addresses two tasks of coordination disambiguation: the detection of coordinate conjunctions and the scope disambiguation of coordinate structures. Experimental results on web sentences indicate the effectiveness of our approach.",
author = "Daisuke Kawahara and Sadao Kurohashi",
year = "2007",
month = "12",
day = "1",
language = "English",
pages = "306--314",
note = "2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007 ; Conference date: 28-06-2007 Through 28-06-2007",

}

TY - CONF

T1 - Probabilistic coordination disambiguation in a fully-lexicalized Japanese parser

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper describes a probabilistic model for coordination disambiguation integrated into syntactic and case structure analysis. Our model probabilistically assesses the parallelism of a candidate coordinate structure using syntactic/semantic similarities and cooccurrence statistics. We integrate these probabilities into the framework of fully-lexicalized parsing based on large-scale case frames. This approach simultaneously addresses two tasks of coordination disambiguation: the detection of coordinate conjunctions and the scope disambiguation of coordinate structures. Experimental results on web sentences indicate the effectiveness of our approach.

AB - This paper describes a probabilistic model for coordination disambiguation integrated into syntactic and case structure analysis. Our model probabilistically assesses the parallelism of a candidate coordinate structure using syntactic/semantic similarities and cooccurrence statistics. We integrate these probabilities into the framework of fully-lexicalized parsing based on large-scale case frames. This approach simultaneously addresses two tasks of coordination disambiguation: the detection of coordinate conjunctions and the scope disambiguation of coordinate structures. Experimental results on web sentences indicate the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=77952990361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952990361&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:77952990361

SP - 306

EP - 314

ER -