Discourse Structure and Co-Reference: An Empirical Study

Discourse Structure and Co-Reference: An Empirical Study Dan Cristea Department of Computer Science University "A.I. Cuza" Ia4i, Romania dcristea @ info iasi. r@ Nancy Ide Department of Computer Science Vassar College Poughkeepsie, NY, USA ideOcs.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 "A.I. Cuza'" la~i, Rom~Lnia valyt@ infoiasi.ro Abstract We compare the potential of two classes of finear and hierarchical models of discourse to determine co-reference links and resolve anaphors. The com- parison uses a corpus of thirty texts, which were manually annotated for co-reference'and discourse structure. 1 Introduction Most current anaphora resolution systems im- plement a pipeline architecture with three mod- ules CLappin and Leass," 1994; Mitkov, 1997; Kameyama, 1997). 1. A COLLECT module determines a list of poten- tial antecedents (LPA) for each anaphor (pro- noun, definite noun, proper name, etc.) that have the potential to resolve it, 2. A FILTER module eliminates referees incom- patible with the anaphor f~m the LPA. 3. A PREFEI~NCE module detennm" es 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 win- dow of text that pLeced__es the anaphor under scrutiny (Hobbs, 1978; Lappin and Leass, 1994; Mitkov, 1997; Kameyama, 1997; Ge et al., 1998). This window can be as small as two or three sen- tences or as large as the entire preceding text. The FILTER module usually imposes semantic con- straints by requiring that the anaphor and poten- tial antecedents have the same number and gender, that selectional restrictions are obeyed, etc. The PREFERENCE module imposes preferences on po- tential antecedents on the basis of their grammati- cal roles, parallelism, frequency, proximity, etc. In some cases, anaphora resolution systems implement these modules explicitly (I-Iobbs, 1978; Lappin and Leass, 1994; Mitkov, 1997; Kameyama, 1997). In other cases, these modules are integrated by means of statistical (Ge et al., 1998) or uncertainty reason- ing techniques (Mitkov, 1997). The fact that current anaphora resolution systems rely exclusively on the linear nature of texts in Or- der to determine the LPA of an anaphor seems odd, given that several studies have claimed that there is a strong relation between discourse structure and reference (Sidner, 1981; Gmsz and Sidner, 1986; Grosz et aL, 1995; Fox, 1987; Vonk et al., 1992; Azzam et al., 1998; Hitzeman and P .oesio, 1998). These studies claim, on the one hand, that the use of referents in naturally occurring texts imposes con- stmints on the interpretation of discourse; and, on the other, that the structure of discourse constrains the HAs to which anaphors can be resolved. The oddness of the situation can be explained by the fact that both groups seem primafacie to be righL Em- pkical experiments studies that employ linear tech- niques for determining the LPAs of anaphom report recall and precision anaphora resolution results in the range of …

Content truncated to 500 words