Feasibility study for ellipsis resolution in dialogues by machine-learning technique

Authors:
Yamamoto Kazuhide;Sumita Eiichiro
Affiliations:
ATR Interpreting Telecommunications Research Laboratories;ATR Interpreting Telecommunications Research Laboratories
Venue:
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Year:
1998

Citing 5
Cited 3

C4.5: programs for machine learning

C4.5: programs for machine learning
Empirical studies in discourse

Computational Linguistics
Evaluating automated and manual acquisition of anaphora resolution strategies

ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Verbal case frame acquisition from a bilingual corpus: gradual knowledge acquisition

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Anaphora resolution of Japanese zero pronouns with deictic reference

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2

An algorithm for anaphora resolution in Spanish texts

Computational Linguistics - Special issue on computational anaphora resolution
Multimodal translation system using texture-mapped lip-sync images for video mail and automatic dubbing applications

EURASIP Journal on Applied Signal Processing
An environment for extracting resolution rules of zero pronouns from corpora

Proceedings of the COLING-2000 Workshop on Semantic Annotation and Intelligent Content

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method for resolving the ellipses that appear in Japanese dialogues is proposed. This method resolves not only the subject ellipsis, but also those in object and other grammatical cases. In this approach, a machine-learning algorithm is used to select the attributes necessary for a resolution. A decision tree is built, and used as the actual ellipsis resolver. The results of blind tests have shown that the proposed method was able to provide a resolution accuracy of 91.7% for indirect objects, and 78.7% for subjects with a verb predicate. By investigating the decision tree we found that topic-dependent attributes are necessary to obtain high performance resolution, and that indispensable attributes vary according to the grammatical case. The problem of data size relative to decision-tree training is also discussed.