earticle

영어

Currently there is much interest in the automatic acquisition of entities, with the goal of Named Entity Recognition (NER). However previous work has focused primarily on major languages, with the large, structured, and semantically rich knowledge bases and using the large corpus with annotated NER tags. In this paper, we describe a method for Chinese-Tibetan bilingual named entity recognition using easily obtainable bilingual dictionary and parallel political corpora. We present two distinct steps for NER, one step identifying entity candidates in Tibetan, and the second step typing the entity into the semantic class. We then test the approach on the dataset and give the analysis of NE type errors.