Analysis of Syntax-Based Pronoun Resolution Methods

Analysis of Syntax-Based Pronoun Resolution Methods Joel R. Tetreault University of Rochester Department of Computer Science Rochester, NY, 14627 tetreaul@cs, rochester, edu Abstract This paper presents a pronoun resolution algo- rithm that adheres to the constraints and rules of Centering Theory (Grosz et al., 1995) and is an alternative to Brennan et al.'s 1987 algo- rithm. The advantages of this new model, the Left-Right Centering Algorithm (LRC), lie in its incremental processing of utterances and in its low computational overhead. The algorithm is compared with three other pronoun resolu- tion methods: Hobbs' syntax-based algorithm, Strube's S-list approach, and the BFP Center- ing algorithm. All four methods were imple- mented in a system and tested on an annotated subset of the Treebank corpus consisting of 2026 pronouns. The noteworthy results were that Hobbs and LRC performed the best. 1 Introduction The aim of this project is to develop a pro- noun resolution algorithm which performs bet- ter than the Brennan et al. 1987 algorithm 1 as a cognitive model while also performing well empirically. A revised algorithm (Left-Right Centering) was motivated by the fact that the BFP al- gorithm did not allow for incremental process- ing of an utterance and hence of its pronouns, and also by the fact that it occasionally im- poses a high computational load, detracting from its psycholinguistic plausibility. A sec- ond motivation for the project is to remedy the dearth of empirical results on pronoun res- olution methods. Many small comparisons of methods have been made, such as by Strube (1998) and Walker (1989), but those usually consist of statistics based on a small hand- tested corpus. The problem with evaluating 1Henceforth BFP algorithms by hand is that it is time consum- ing and difficult to process corpora that are large enough to provide reliable, broadly based statistics. By creating a system that can run algorithms, one can easily and quickly analyze large amounts of data and generate more reli- able results. In this project, the new algorithm is tested against three leading syntax-based pro- noun resolution methods: Hobbs' naive algo- rithm (1977), S-list (Strube 1998), and BFP. Section 2 presents the motivation and algo- rithm for Left-Right Centering. In Section 3, the results of the algorithms are presented and then discussed in Section 4. 2 Left-Right Centering Algorithm Left-Right Centering (LRC) is a formalized algorithm built upon centering theory's con- straints and rules as detailed in Grosz et. al (1995). The creation of the LRC Algorithm is motivated by two drawbacks found in the BFP method. The first is BFP's limitation as a cognitive model since it makes no provision for incremental resolution of pronouns (Kehler 1997). Psycholinguistic research support the claim that listeners process utterances one word at a time, so when they hear a pronoun they will try to resolve it immediately. If new infor- mation comes into play which makes the reso- lution incorrect (such as a violation of binding constraints), the listener will go back and find a correct antecedent. This …

Content truncated to 500 words