tailieunhanh - Báo cáo khoa học: "Anaphor resolution in unrestricted texts with partial parsing"

In this paper we deal with several kinds of anaphora in unrestricted texts. These kinds of anaphora are pronominal references, surfacecount anaphora and one-anaphora. In order to solve these anaphors we work on the output of a part-of-speech tagger, on which we automatically apply a partial parsing from the formalism: Slot Unification Grammar, which has been implemented in Prolog. We only use the following kinds of information: lexical (the lemma of each word), morphologic (person, number, gender) and syntactic. . | Anaphor resolution in unrestricted texts with partial parsing1 A. Ferrandez M. Palomar Dept. Languages and Information Systems Alicante University - Apt. 99 03080 - Alicante - Spain antonio@ mpalomar@ L. Moreno Dept. Information Systems and Computation Valencia University of Technology lmoreno@ Abstract In this paper we deal with several kinds of anaphora in unrestricted texts. These kinds of anaphora are pronominal references surfacecount anaphora and one-anaphora. In order to solve these anaphors we work on the output of a part-of-speech tagger on which we automatically apply a partial parsing from the formalism Slot Unification Grammar which has been implemented in Prolog. We only use the following kinds of information lexical the lemma of each word morphologic person number gender and syntactic. Finally we show the experimental results and the restrictions and preferences that we have used for anaphor resolution with partial parsing. Introduction Nowadays there are two different approaches to anaphor resolution integrated and alternative. The former is based on the integration of different kinds of knowledge . syntactic or semantic information whereas the latter is based on statistical neural networks or the principles of reasoning with uncertainty . Connoly 1994 and Mitkov 1997 . Our system can be included into the first approach. In these integrated approaches the semantic and domain knowledge information is very expensive in relation to computational processing. As a consequence current anaphor resolution implementations mainly rely on constraints and preference heuristics which employ information originated from morphosyntactic or shallow semantic analysis . in Baldwin 1997 . These approaches however perform remarkably well. In Lappin and Leass 1994 it is described an algorithm for pronominal anaphor resolution with a high rate of correct analyses 85 . This one operates primarily on syntactic information only. In .