关键词: 指代消解，先行语，Fuzzy Rough集，基于实例的学习

Abstract: Anaphora resolution is an important issue in natural language processing. This paper presented an approach based on Fuzzy Rough sets model combined with instance -based learning approach to resolve pronominal anaphora within Chinese text. The first phase of the presented approach is preprocessing. In this phase,after extracting noun phases and eliminating those whose number and gender features arc inconsistent with pronominal anaphora, the potential antecedents set was formed. hhen, the attri-butc values of every noun phase in this set were computed according to an attribute set which only involves shallow syntactic and semantic information. The second phase aimed to select representative examples from the potential antecedents set and reduce redundant attributes to improve the generalization capability of these examples. hhese tasks were done by using concepts of Fuzzy Rough sets model. The two phases above can be regarded as learning phase. In the last phase, those examples were used to estimate whether a new noun phase is the that antecedent of a pronominal anaphor. The presented approach was tested by People Daily corpus. The results show this approach is effective.

Key words: Anaphora resolution,Antecedent,Fuzzy Rough sets,Instance-based learning