Paper: A Probabilistic Genre-Independent Model Of Pronominalization

ACL ID A00-2003
Title A Probabilistic Genre-Independent Model Of Pronominalization
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2000
Authors

Our aim in this paper is to identify genre- independent factors that influence the decision to pronominalize. Results based on the annotation of twelve texts from four genres show that only a few factors have a strong influence on pronominaliza- tion across genres, i.e. distance from last mention, agreement, and form of the antecedent. Finally, we describe a probabilistic model of pronominalization derived from our data.