A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue

A Machine Learning Approach to Pronoun Resolution in Spoken Dialogue Michael Strube and Christoph M¨uller European Media Laboratory GmbH Villa Bosch Schloß-Wolfsbrunnenweg 33 69118 Heidelberg, Germany � michael.strube|christoph.mueller � @eml.villa-bosch.de Abstract We apply a decision tree based approach to pronoun resolution in spoken dialogue. Our system deals with pronouns with NP- and non-NP-antecedents. We present a set of features designed for pronoun resolu- tion in spoken dialogue and determine the most promising features. We evaluate the system on twenty Switchboard dialogues and show that it compares well to Byron’s (2002) manually tuned system. 1 Introduction Corpus-based methods and machine learning tech- niques have been applied to anaphora resolution in written text with considerable success (Soon et al., 2001; Ng & Cardie, 2002, among others). It has been demonstrated that systems based on these ap- proaches achieve a performance that is comparable to hand-crafted systems. Since they can easily be applied to new domains it seems also feasible to port a given corpus-based anaphora resolution sys- tem from written text to spoken dialogue. This pa- per describes the extensions and adaptations needed for applying our anaphora resolution system (M¨uller et al., 2002; Strube et al., 2002) to pronoun resolu- tion in spoken dialogue. There are important differences between written text and spoken dialogue which have to be accounted for. The most obvious difference is that in spo- ken dialogue there is an abundance of (personal and demonstrative) pronouns with non-NP-antecedents or no antecedents at all. Corpus studies have shown that a significant amount of pronouns in spoken di- alogue have non-NP-antecedents: Byron & Allen (1998) report that about 50% of the pronouns in the TRAINS93 corpus have non-NP-antecedents. Eck- ert & Strube (2000) note that only about 45% of the pronouns in a set of Switchboard dialogues have NP-antecedents. The remainder consists of 22% which have non-NP-antecedents and 33% without antecedents. These studies suggest that the perfor- mance of a pronoun resolution algorithm can be im- proved considerably by enabling it to resolve also pronouns with non-NP-antecedents. Because of the difficulties a pronoun resolution algorithm encounters in spoken dialogue, previous approaches were applied only to tiny domains, they needed deep semantic analysis and discourse pro- cessing and relied on hand-crafted knowledge bases. In contrast, we build on our existing anaphora res- olution system and incrementally add new features specifically devised for spoken dialogue. That way we are able to determine relatively powerful yet computationally cheap features. To our knowledge the work presented here describes the first imple- mented system for corpus-based anaphora resolution dealing also with non-NP-antecedents. 2 NP- vs. Non-NP-Antecedents Spoken dialogue contains more pronouns with non- NP-antecedents than written text does. However, pronouns with NP-antecedents (like 3rd pers. mas- culine/feminine pronouns, cf. he in the example be- low) still constitute the largest fraction of all coref- erential pronouns in the Switchboard corpus. In spoken dialogue there are considerable num- bers of pronouns that pick up different kinds of abstract objects from the previous discourse, e.g. events, states, concepts, propositions …

Content truncated to 500 words