Resolving Discourse Deictic Anaphora in Dialogues

Proceedings of EACL '99 Resolving Discourse Deictic Anaphora in Dialogues Miriam Eckert & Michael Strube Institute for Research in Cognitive Science University of Pennsylvania 3401 Walnut Street, Suite 400A Philadelphia, PA 19104, USA {miriame, strube}@linc, cis. upenn, edu Abstract Most existing anaphora resolution algo- rithms are designed to account only for anaphors with NP-antecedents. This paper describes an algorithm for the resolution of discourse deictic anaphors, which constitute a large percentage of anaphors in spoken di- alogues. The success of the resolution is dependent on the classification of all pro- nouns and demonstratives into individual, discourse deictic and vague anaphora. Fi- nally, the empirical results of the application of the algorithm to a corpus of spoken dia- logues are presented. 1 Introduction Most anaphora resolution algorithms are designed to deal with the co-indexing relation between anaphors and NP-antecedents. In the spoken language corpus we examined - the Switchboard corpus of telephone conversations (LDC, 1993) - this type of link only accounts for 45.1% of all anaphoric references. An- other 22.6% are anaphors whose referents are not in- dividual, concrete entities but events, facts and propo- sitions, e.g., (1) B.7: A.8: [We never know what they're thinking]/. Thati's right. [I don't trust them]j, maybe I guess itj's because of what happened over there with their own people, how they threw them out of power. (sw3241) Whilst there have been attempts to classify abstract objects and the rules governing anaphoric reference to them (Webber, 1991; Asher, 1993; Dahl and Hellman, 1995), there have been no exhaustive, empirical stud- ies using actual resolution algorithms. These have so far only been applied to written corpora. However, the high frequency of abstract object anaphora in dia- logues means that any attempt to resolve anaphors in spoken language cannot succeed without taking this into account. Summarised below are some issues specific to anaphora resolution in spoken dialogues (see also Byron and Stent (1998) who mention some of these problems in their account of the Centering model (Grosz et al., 1995)). Center of attention in multi-party discourse. In spontaneous speech it is possible that the participants of a dialogue may not be focussing on the same entity at a given point in the discourse. Utterances with no discourse entities. E.g., Uh- huh; yeah; right. Byron and Stent (1998) and Walker (1998) assign no importance to such utterances in their models. We assume that these also can be used to acknowledge a preceding utterance. Abandoned or partial utterances. Speakers may in- terrupt each other or make speech repairs, e.g., (2) Uh, our son/has this kind of, you know, he/'s, well hei started out going Stephen F Austin (sw3117) Self-corrected speech cannot be ignored as can be seen by the fact that the entity referred to by the NP our son is subsequently referred to by a pronoun and must therefore have entered the discourse model. Determination of utterance boundaries. Most anaphor resolution algorithms rely on a syntactic def- inition of utterance which cannot be provided by spo- ken …

Content truncated to 500 words