Paper: An Information Theoretic Approach to Bilingual Word Clustering

ACL ID P13-2136
Title An Information Theoretic Approach to Bilingual Word Clustering
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

We present an information theoretic objec- tive for bilingual word clustering that in- corporates both monolingual distributional evidence as well as cross-lingual evidence from parallel corpora to learn high qual- ity word clusters jointly in any number of languages. The monolingual component of our objective is the average mutual in- formation of clusters of adjacent words in each language, while the bilingual com- ponent is the average mutual information of the aligned clusters. To evaluate our method, we use the word clusters in an NER system and demonstrate a statisti- cally significant improvement in F1 score when using bilingual word clusters instead of monolingual clusters.