Paper: Understanding Relation Temporality of Entities

ACL ID P14-2137
Title Understanding Relation Temporality of Entities
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

This paper demonstrates the importance of relation equivalence for entity trans- lation pair discovery. Existing approach of understanding relation equivalence has focused on using explicit features of co- occurring entities. In this paper, we ex- plore latent features of temporality for un- derstanding relation equivalence, and em- pirically show that the explicit and latent features complement each other. Our pro- posed hybrid approach of using both ex- plicit and latent features improves relation translation by 0.16 F1-score, and in turn improves entity translation by 0.02.