tailieunhanh - Báo cáo khoa học: "LEARNING TO RESOLVE BRIDGING REFERENCES"

We use machine learning techniques to find the best combination of local focus and lexical distance features for identifying the anchor of mereological bridging references. We find that using first mention, utterance distance, and lexical distance computed using either Google or WordNet results in an accuracy significantly higher than obtained in previous experiments. | LEARNING TO RESOLVE BRIDGING REFERENCES Massimo Poesio Rahul Mehta Axel Maroudas and Janet Hitzeman Dept. of Comp. Science University of Essex UK poesio at essex dot ac dot uk MITRE Corporation USA hitz at mitre dot org Abstract We use machine learning techniques to find the best combination of local focus and lexical distance features for identifying the anchor of mereological bridging references. We find that using first mention utterance distance and lexical distance computed using either Google or WordNet results in an accuracy significantly higher than obtained in previous experiments. 1 Introduction BRIDGING REFERENCES BR Clark 1977 -anaphoric expressions that cannot be resolved purely on the basis of string matching and thus require the reader to bridge the gap using commonsense inferences-are arguably the most interesting and at the same time the most challenging problem in anaphora resolution. Work such as Poesio et al. 1998 Poesio et al. 2002 Poesio 2003 provided an experimental confirmation of the hypothesis first put forward by Sidner 1979 that BRIDGING DESCRIPTIONS bd 1 are more similar to pronouns than to other types of definite descriptions in that they are sensitive to the local rather than the global focus Grosz and Sidner 1986 . This previ-uous work also suggested that simply choosing the entity whose description is lexically closest to that of the bridging description among those in the current focus space gives poor results in fact better results are obtained by always choosing as ANCHOR of the bridging reference2 the first-mentioned entity of the previous sentence Poesio 2003 . But neither source of information in isolation resulted in an accuracy over 40 . In short this earlier work suggested that a combination of salience and lexical We will use the term bridging descriptions to indicate bridging references realized by definite descriptions equated here with noun phrases with determiner the like the top. 2Following Poesio and Vieira 1998 we .