Analysis of Syntax-Based Pronoun Resolution Methods

This paper presents a pronoun resolution algor i thm that adheres to the constraints and rules of Centering Theory (Grosz et al., 1995) and is an alternative to Brennan et al.'s 1987 algori thm. The advantages of this new model, the Left-Right Centering Algorithm (LRC), lie in its incremental processing of utterances and in its low computat ional overhead. The algorithm is compared with three other pronoun resolution methods: Hobbs' syntax-based algorithm, Strube's S-list approach, and the BFP Centering algorithm. All four methods were implemented 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 I n t r o d u c t i o n The aim of this project is to develop a pronoun resolution algorithm which performs better 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 algori thm did not allow for incremental processing of an utterance and hence of its pronouns, and also by the fact that it occasionally imposes a high computational load, detracting from its psycholinguistic plausibility. A second motivation for the project is to remedy the dearth of empirical results on pronoun resolution 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 handtested corpus. The problem with evaluating 1Henceforth BFP algorithms by hand is that it is t ime consuming 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 reliable results. In this project, the new algorithm is tested against three leading syntax-based pronoun resolution methods: Hobbs' naive algor i thm (1977), S-list (Strube 1998), and BFP. Section 2 presents the motivation and algor i thm for Left-Right Centering. In Section 3, the results of the algorithms are presented and then discussed in Section 4. 2 Left-Right Centering A l g o r i t h m Left-Right Centering (LRC) is a formalized algorithm built upon centering theory's constraints 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 l imitation 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 information comes into play which makes the resolution incorrect (such as a violation of binding constraints), the listener will go back and find a correct antecedent. This incremental resolution problem also motivates Strube's S-list approach. The second drawback to the BFP algorithm is the computational explosion of generating and filtering anchors. In utterances with two or more pronouns and a Cf-list with several candidate antecedents for each pronoun, thousands of anchors can easily be generated making for a time consuming filtering phase. An exam-