tailieunhanh - Báo cáo khoa học: " Applying Co-Training to Reference Resolution"

In this paper, we investigate the practical applicability of Co-Training for the task of building a classifier for reference resolution. We are concerned with the question if Co-Training can significantly reduce the amount of manual labeling work and still produce a classifier with an acceptable performance. | Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics ACL Philadelphia July 2002 pp. 352-359. Applying Co-Training to Reference Resolution Christoph Muller European Media Laboratory GmbH Villa Bosch SchloB-Wolfsbrunnenweg 33 69118 Heidelberg Germany mueller@ Stefan Rapp Sony International Europe GmbH Advanced Technology Center Stuttgart Heinrich-Hertz-StraBe 1 70327 Stuttgart Germany rapp@ Michael Strube European Media Laboratory GmbH Villa Bosch SchloB-Wolfsbrunnenweg 33 69118 Heidelberg Germany strube@ Abstract In this paper we investigate the practical applicability of Co-Training for the task of building a classifier for reference resolution. We are concerned with the question if Co-Training can significantly reduce the amount of manual labeling work and still produce a classifier with an acceptable performance. 1 Introduction A major obstacle for natural language processing systems which analyze natural language texts or utterances is the need to identify the entities referred to by means of referring expressions. Among referring expressions pronouns and definite noun phrases NPs are the most prominent. Supervised machine learning algorithms were used for pronoun resolution with good results Ge et al. 1998 and for definite NPs with fairly good results Aone and Bennett 1995 McCarthy and Lehnert 1995 Soon et al. 2001 . However the deficiency of supervised machine learning approaches is the need for an unknown amount of annotated training data for optimal performance. So researchers in NLP began to experiment with weakly supervised machine learning algorithms such as Co-Training Blum and Mitchell 1998 . Among others Co-Training was applied to document classification Blum and Mitchell 1998 named-entity recognition Collins and Singer 1999 noun phrase bracketing Pierce and Cardie 2001 and statistical parsing Sarkar 2001 . In this paper we apply Co-Training to the problem of reference .