Abstract
This paper proposes a novel smoothing model with a combinatorial optimization scheme for all-words word sense disambiguation from untagged corpora. By generalizing discrete senses to a continuum, we introduce a smoothing in context-sense space to cope with data-sparsity resulting from a large variety of linguistic context and sense, as well as to exploit senseinterdependency among the words in the same text string. Through the smoothing, all the optimal senses are obtained at one time under maximum marginal likelihood criterion, by competitive probabilistic kernels made to reinforce one another among nearby words, and to suppress conflicting sense hypotheses within the same word. Experimental results confirmed the superiority of the proposed method over conventional ones by showing the better performances beyond most-frequent-sense baseline performance where none of SemEval-2 unsupervised systems reached.
| Original language | English |
|---|---|
| Title of host publication | ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 884-893 |
| Number of pages | 10 |
| Volume | 1 |
| ISBN (Print) | 9781937284503 |
| Publication status | Published - 2013 |
| Event | 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia Duration: 2013 Aug 4 → 2013 Aug 9 |
Other
| Other | 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 |
|---|---|
| City | Sofia |
| Period | 13/8/4 → 13/8/9 |
Fingerprint
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language
Cite this
Density maximization in context-sense metric space for all-words WSD. / Tanigaki, Koichi; Shiba, Mitsuteru; Munaka, Tatsuji; Sagisaka, Yoshinori.
ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2013. p. 884-893.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Density maximization in context-sense metric space for all-words WSD
AU - Tanigaki, Koichi
AU - Shiba, Mitsuteru
AU - Munaka, Tatsuji
AU - Sagisaka, Yoshinori
PY - 2013
Y1 - 2013
N2 - This paper proposes a novel smoothing model with a combinatorial optimization scheme for all-words word sense disambiguation from untagged corpora. By generalizing discrete senses to a continuum, we introduce a smoothing in context-sense space to cope with data-sparsity resulting from a large variety of linguistic context and sense, as well as to exploit senseinterdependency among the words in the same text string. Through the smoothing, all the optimal senses are obtained at one time under maximum marginal likelihood criterion, by competitive probabilistic kernels made to reinforce one another among nearby words, and to suppress conflicting sense hypotheses within the same word. Experimental results confirmed the superiority of the proposed method over conventional ones by showing the better performances beyond most-frequent-sense baseline performance where none of SemEval-2 unsupervised systems reached.
AB - This paper proposes a novel smoothing model with a combinatorial optimization scheme for all-words word sense disambiguation from untagged corpora. By generalizing discrete senses to a continuum, we introduce a smoothing in context-sense space to cope with data-sparsity resulting from a large variety of linguistic context and sense, as well as to exploit senseinterdependency among the words in the same text string. Through the smoothing, all the optimal senses are obtained at one time under maximum marginal likelihood criterion, by competitive probabilistic kernels made to reinforce one another among nearby words, and to suppress conflicting sense hypotheses within the same word. Experimental results confirmed the superiority of the proposed method over conventional ones by showing the better performances beyond most-frequent-sense baseline performance where none of SemEval-2 unsupervised systems reached.
UR - http://www.scopus.com/inward/record.url?scp=84907341856&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84907341856&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9781937284503
VL - 1
SP - 884
EP - 893
BT - ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
ER -