Exploiting Wikipedia as External Knowledge for Named Entity Recognition

Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 698–707, Prague, June 2007. c⃝2007 Association for Computational Linguistics Exploiting Wikipedia as External Knowledge for Named Entity Recognition Jun’ichi Kazama and Kentaro Torisawa Japan Advanced Institute of Science and Technology (JAIST) Asahidai 1-1, Nomi, Ishikawa, 923-1292 Japan {kazama, torisawa}@jaist.ac.jp Abstract 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. 1 Introduction It has been known that Gazetteers, or entity dic- tionaries, are important for improving the perfor- mance of named entity recognition. However, build- ing and maintaining high-quality gazetteers is very time consuming. Many methods have been proposed for solving this problem by automatically extracting gazetteers from large amounts of texts (Riloff and Jones, 1999; Thelen and Riloff, 2002; Etzioni et al., 2005; Shinzato et al., 2006; Talukdar et al., 2006; Nadeau et al., 2006). However, these methods re- quire complicated induction of patterns or statistical methods to extract high-quality gazetteers. We have recently seen a rapid and successful growth of Wikipedia (http://www.wikipedia.org), which is an open, collaborative encyclopedia on the Web. Wikipedia has now more than 1,700,000 articles on the English version (March 2007) and the number is still increasing. Since Wikipedia aims to be an encyclopedia, most articles are about named entities and they are more structured than raw texts. Although it cannot be used as gazetteers di- rectly since it is not intended as a machine readable resource, extracting knowledge such as gazetteers from Wikipedia will be much easier than from raw texts or from usual Web texts because of its struc- ture. It is also important that Wikipedia is up- dated every day and therefore new named entities are added constantly. We think that extracting knowl- edge from Wikipedia for natural language process- ing is one of the promising ways towards enabling large-scale, real-life applications. In fact, many studies that try to exploit Wikipedia as a knowl- edge source have recently emerged (Bunescu and Pas¸ca, 2006; Toral and Mu˜noz, 2006; Ruiz-Casado et al., 2006; Ponzetto and Strube, 2006; Strube and Ponzetto, 2006; Zesch et al., 2007). As a first step towards such approach, we demon- strate in this paper that category labels extracted from the first sentence of a Wikipedia article, which can be thought of as the definition of the entity de- scribed in the article, are really useful to improve the accuracy of NER. For example, “Franz Fischler” has the article with the first sentence, “Franz Fischler (born September 23, 1946) is …

Content truncated to 500 words