An Empirical Investigation of the Relation Between Discourse Structure and Co-Reference

An Empirical Investigation of the Relation Between Discourse Structure and Co-Reference Dan Cristea Department of Computer Science University “A.I. Cuza” Ias¸i, Romˆania dcristea@infoiasi.ro Nancy Ide Department of Computer Science Vassar College Poughkeepsie, NY, USA ide@cs.vassar.edu Daniel Marcu Information Sciences Institute and Department of Computer Science University of Southern California Los Angeles, CA, USA marcu@isi.edu Valentin Tablan � Department of Computer Science University of Sheffield United Kingdom v.tablan@sheffield.ac.uk Abstract We compare the potential of two classes of linear and hi- erarchical models of discourse to determine co-reference links and resolve anaphors. The comparison uses a cor- pus of thirty texts, which were manually annotated for co-reference and discourse structure. 1 Introduction Most current anaphora resolution systems implement a pipeline architecture with three modules (Lappin and Le- ass, 1994; Mitkov, 1997; Kameyama, 1997). 1. A COLLECT module determines a list of potential antecedents (LPA) for each anaphor (pronoun, defi- nite noun, proper name, etc.) that have the potential to resolve it. 2. A FILTER module eliminates referees incompatible with the anaphor from the LPA. 3. A PREFERENCE module determines the most likely antecedent on the basis of an ordering policy. In most cases, the COLLECT module determines an LPA by enumerating all antecedents in a window of text that precedes the anaphor under scrutiny (Hobbs, 1978; Lap- pin and Leass, 1994; Mitkov, 1997; Kameyama, 1997; Ge et al., 1998). This window can be as small as two or three sentences or as large as the entire preceding text. The FILTER module usually imposes semantic con- straints by requiring that the anaphor and potential an- tecedents have the same number and gender, that selec- tional restrictions are obeyed, etc. The PREFERENCE module imposes preferences on potential antecedents on the basis of their grammatical roles, parallelism, frequency, proximity, etc. In some cases, anaphora resolution systems implement these modules explic- itly (Hobbs, 1978; Lappin and Leass, 1994; Mitkov, � On leave from the Faculty of Computer Science, University “Al. I. Cuza” of Iasi. 1997; Kameyama, 1997). In other cases, these modules are integrated by means of statistical (Ge et al., 1998) or uncertainty reasoning techniques (Mitkov, 1997). The fact that current anaphora resolution systems rely exclusively on the linear nature of texts in order to de- termine the LPA of an anaphor seems odd, given that several studies have claimed that there is a strong rela- tion between discourse structure and reference (Sidner, 1981; Grosz and Sidner, 1986; Grosz et al., 1995; Fox, 1987; Vonk et al., 1992; Azzam et al., 1998; Hitzeman and Poesio, 1998). These studies claim, on the one hand, that the use of referents in naturally occurring texts im- poses constraints on the interpretation of discourse; and, on the other, that the structure of discourse constrains the LPAs to which anaphors can be resolved. The oddness of the situation can be explained by the fact that both groups seem prima facie to be right. Empirical exper- iments studies that employ linear techniques for deter- mining the LPAs of anaphors report recall …

Content truncated to 500 words