Article Structure
Abstract
This paper studies named entity translation and proposes “selective temporality” as a new feature, as using temporal features may be harmful for translating “atemporal” entities.
Introduction
Named entity translation discovery aims at mapping entity names for people, locations, etc.
Preliminaries
Our approach follows a graph alignment framework proposed in (You et al., 2010).
Entity Translation Discovery using Selective Temporality
Overall Framework: We propose our framework by putting together two separate procedures for temporal and atemporal entities to compute the overall similarity matrix R
Experimental Evaluation
4.1 Experimental Settings
Conclusion
This paper validated that considering temporality selectively is helpful for improving the translation quality.
Topics
named entity
- This paper studies named entity translation and proposes “selective temporality” as a new feature, as using temporal features may be harmful for translating “atemporal” entities.Page 1, “Abstract”
- Named entity translation discovery aims at mapping entity names for people, locations, etc.Page 1, “Introduction”
- As many new named entities appear every day in newspapers and web sites, their translations are nontrivial yet essential.Page 1, “Introduction”
- Early efforts of named entity translation have focused on using phonetic feature (called PH) to estimate a phonetic similarity between two names (Knight and Graehl, 1998; Li et al., 2004; Virga and Khudanpur, 2003).Page 1, “Introduction”
- To identify entities, we use a CRF-based named entity tagger (Finkel et al., 2005) and a Chinese word breaker (Gao et al., 2003) for English and Chinese corpora, respectively.Page 2, “Preliminaries”
See all papers in Proc. ACL 2013 that mention named entity.
See all papers in Proc. ACL that mention named entity.
Back to top.
similarity scores
- To integrate two similarity scores , we adopt an average as a composite function.Page 2, “Preliminaries”
- We finally compute initial similarity scores for all pairs (6, c) where e 6 V6 and c 6 VC, and build the initial similarity matrix R0.Page 2, “Preliminaries”
- From R”, we finally extract one-to-one matches by using simple greedy approach of three steps: (1) choosing the pair with the highest similarity score ; (2) removing the corresponding row and column from R”; (3) repeating (l) and (2) until the matching score is not less than a threshold 6.Page 2, “Preliminaries”
See all papers in Proc. ACL 2013 that mention similarity scores.
See all papers in Proc. ACL that mention similarity scores.
Back to top.
