tailieunhanh - Báo cáo khoa học: "A Chain-starting Classifier of Definite NPs in Spanish"

Given the great amount of definite noun phrases that introduce an entity into the text for the first time, this paper presents a set of linguistic features that can be used to detect this type of definites in Spanish. The efficiency of the different features is tested by building a rule-based and a learning-based chain-starting classifier. Results suggest that the classifier, which achieves high precision at the cost of recall, can be incorporated as either a filter or an additional feature within a coreference resolution system to boost its performance. . | A Chain-starting Classifier of Definite NPs in Spanish Marta Recasens CLiC - Centre de Llenguatge i Computacio Department of Linguistics University of Barcelona 08007 Barcelona Spain mrecasens@ Abstract Given the great amount of definite noun phrases that introduce an entity into the text for the first time this paper presents a set of linguistic features that can be used to detect this type of definites in Spanish. The efficiency of the different features is tested by building a rule-based and a learning-based chain-starting classifier. Results suggest that the classifier which achieves high precision at the cost of recall can be incorporated as either a filter or an additional feature within a coreference resolution system to boost its performance. 1 Introduction Although often treated together anaphoric pronoun resolution differs from coreference resolution van Deemter and Kibble 2000 . Whereas the former attempts to find an antecedent for each anaphoric pronoun in a discourse the latter aims to build full coreference chains namely linking all noun phrases NPs - whether pronominal or with a nominal head - that point to the same entity. The output of anaphora resolution1 are nounpronoun pairs or pairs of a discourse segment and a pronoun in some cases whereas the output of coreference resolution are chains containing a variety of items pronouns full NPs discourse segments. Thus coreference resolution requires a wider range of strategies in order to build the full chains of coreferent 1A different matter is the resolution of anaphoric full NPs . those semantically dependent on a previous mention. 2We follow the Ace terminology NIST 2003 but instead of talking of objects in the world we talk of objects in the discourse model we use entity for an object or set of objects in the discourse model and mention for a reference to an entity. One of the problems specific to coreference resolution is determining once a mention is encountered by the system