Abstract
This paper demonstrates the importance of relation equivalence for entity translation pair discovery. Existing approach of understanding relation equivalence has focused on using explicit features of cooccurring entities. In this paper, we explore latent features of temporality for understanding relation equivalence, and empirically show that the explicit and latent features complement each other. Our proposed hybrid approach of using both explicit and latent features improves relation translation by 0.16 F1-score, and in turn improves entity translation by 0.02.
| Original language | English |
|---|---|
| Title of host publication | Long Papers |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 848-853 |
| Number of pages | 6 |
| ISBN (Print) | 9781937284732 |
| Publication status | Published - 2014 Jan 1 |
| Event | 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States Duration: 2014 Jun 22 → 2014 Jun 27 |
Publication series
| Name | 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference |
|---|---|
| Volume | 2 |
Other
| Other | 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 |
|---|---|
| Country | United States |
| City | Baltimore, MD |
| Period | 14/6/22 → 14/6/27 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Language and Linguistics
- Linguistics and Language
Cite this
}
Understanding relation temporality of entities. / Lee, Taesung; Hwang, Seung Won.
Long Papers. Association for Computational Linguistics (ACL), 2014. p. 848-853 (52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference; Vol. 2).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Understanding relation temporality of entities
AU - Lee, Taesung
AU - Hwang, Seung Won
PY - 2014/1/1
Y1 - 2014/1/1
N2 - This paper demonstrates the importance of relation equivalence for entity translation pair discovery. Existing approach of understanding relation equivalence has focused on using explicit features of cooccurring entities. In this paper, we explore latent features of temporality for understanding relation equivalence, and empirically show that the explicit and latent features complement each other. Our proposed hybrid approach of using both explicit and latent features improves relation translation by 0.16 F1-score, and in turn improves entity translation by 0.02.
AB - This paper demonstrates the importance of relation equivalence for entity translation pair discovery. Existing approach of understanding relation equivalence has focused on using explicit features of cooccurring entities. In this paper, we explore latent features of temporality for understanding relation equivalence, and empirically show that the explicit and latent features complement each other. Our proposed hybrid approach of using both explicit and latent features improves relation translation by 0.16 F1-score, and in turn improves entity translation by 0.02.
UR - http://www.scopus.com/inward/record.url?scp=84906924206&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84906924206&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84906924206
SN - 9781937284732
T3 - 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference
SP - 848
EP - 853
BT - Long Papers
PB - Association for Computational Linguistics (ACL)
ER -