Named Entity Recognition with Bilingual Constraints

Wanxiang Che, Mengqiu Wang, Chris Manning and Ting Liu

Different languages contain complementary cues about entities, which can be used to improve Named Entity Recognition (NER) systems. We propose a method that formulates the problem of exploring such signals on unannotated bilingual text as a simple Integer Linear Program, which encourages entity tags to agree via bilingual constraints. Bilingual NER experiments on the large OntoNotes 4.0 Chinese-English corpus show that the proposed method can improve strong baselines for both Chinese and English. In particular, Chinese performance improves by over 5\% absolute F$_1$ score. We can then annotate a large amount of bilingual text (80k sentence pairs) using our method, and add it as up-training data to the original monolingual NER training corpus. The Chinese model retrained on this new combined dataset outperforms the strong baseline by over 3\% F$_1$ score.