Paper: Exploiting Wikipedia as External Knowledge for Named Entity Recognition

ACL ID D07-1073
Title Exploiting Wikipedia as External Knowledge for Named Entity Recognition
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
Authors

We explore the use of Wikipedia as external knowledge to improve named entity recog- nition (NER). Our method retrieves the cor- responding Wikipedia entry for each can- didate word sequence and extracts a cate- gory label from the first sentence of the en- try, which can be thought of as a definition part. These category labels are used as fea- tures in a CRF-based NE tagger. We demon- strate using the CoNLL 2003 dataset that the Wikipedia category labels extracted by such a simple method actually improve the accu- racy of NER.