Abstract
Evocation is a directed yet weighted semantic relationship between lexicalized concepts. Although evocation relations are considered potentially useful in several semantic NLP tasks, the prediction of the evocation relation between an arbitrary pair of concepts remains difficult, since evocation relationships cover a broader range of semantic relations rooted in human perception and experience. This paper presents a supervised learning approach to predict the strength (by regression) and to determine the directionality (by classification) of the evocation relation that might hold between a pair of lexicalized concepts. Empirical results that were obtained by investigating useful features are shown, indicating that a combination of the proposed features largely outperformed individual baselines, and also suggesting that semantic relational vectors computed from existing semantic vectors for lexicalized concepts were indeed effective for both the prediction of strength and the determination of directionality.
| Original language | English |
|---|---|
| Title of host publication | COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016 |
| Subtitle of host publication | Technical Papers |
| Publisher | Association for Computational Linguistics, ACL Anthology |
| Pages | 1657-1668 |
| Number of pages | 12 |
| ISBN (Print) | 9784879747020 |
| Publication status | Published - 2016 Jan 1 |
| Event | 26th International Conference on Computational Linguistics, COLING 2016 - Osaka, Japan Duration: 2016 Dec 11 → 2016 Dec 16 |
Other
| Other | 26th International Conference on Computational Linguistics, COLING 2016 |
|---|---|
| Country | Japan |
| City | Osaka |
| Period | 16/12/11 → 16/12/16 |
Fingerprint
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Language and Linguistics
- Linguistics and Language
Cite this
Predicting the evocation relation between lexicalized concepts. / Hayashi, Yoshihiko.
COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers. Association for Computational Linguistics, ACL Anthology, 2016. p. 1657-1668.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Predicting the evocation relation between lexicalized concepts
AU - Hayashi, Yoshihiko
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Evocation is a directed yet weighted semantic relationship between lexicalized concepts. Although evocation relations are considered potentially useful in several semantic NLP tasks, the prediction of the evocation relation between an arbitrary pair of concepts remains difficult, since evocation relationships cover a broader range of semantic relations rooted in human perception and experience. This paper presents a supervised learning approach to predict the strength (by regression) and to determine the directionality (by classification) of the evocation relation that might hold between a pair of lexicalized concepts. Empirical results that were obtained by investigating useful features are shown, indicating that a combination of the proposed features largely outperformed individual baselines, and also suggesting that semantic relational vectors computed from existing semantic vectors for lexicalized concepts were indeed effective for both the prediction of strength and the determination of directionality.
AB - Evocation is a directed yet weighted semantic relationship between lexicalized concepts. Although evocation relations are considered potentially useful in several semantic NLP tasks, the prediction of the evocation relation between an arbitrary pair of concepts remains difficult, since evocation relationships cover a broader range of semantic relations rooted in human perception and experience. This paper presents a supervised learning approach to predict the strength (by regression) and to determine the directionality (by classification) of the evocation relation that might hold between a pair of lexicalized concepts. Empirical results that were obtained by investigating useful features are shown, indicating that a combination of the proposed features largely outperformed individual baselines, and also suggesting that semantic relational vectors computed from existing semantic vectors for lexicalized concepts were indeed effective for both the prediction of strength and the determination of directionality.
UR - http://www.scopus.com/inward/record.url?scp=85055003537&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85055003537&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85055003537
SN - 9784879747020
SP - 1657
EP - 1668
BT - COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016
PB - Association for Computational Linguistics, ACL Anthology
ER -