The Research On Resolution Of Chinese Pronoun

Natural Language provides people with rich mechanisms for varying the expressions of the same meaning. However, it also challenges computational researchers to do with a great of nontrivial problems, one of them is anaphora resolution. In some application fields of discourse processing, such as Automatic Summarization, Information Retrieval, and Information Extraction etc., the final processing result is usually generated by directly extracting some important sentences from text or document, in which some pronouns could be contained without their antecedents. So, it is very important to resolve pronominal anaphora in Natural Language Processing, and that has attracted the attentions of increasing researchers. Many approaches developed offer approximation solutions, including principle-based, such as purely syntactic ones, semantic and pragmatic ones, and statistics-based ones. In this paper, we put forward a modal to resolve anaphora (including empty pronoun) based on the characteristics of Chinese. In this method, we apply some corresponding rules on the sentences after their patterns distinguished in the text, then analyze the semantic relation of the components of the sentence and form a corresponding semantic network, get rid of some candidates according to the co-constrain of the nodes in that network, put every component which refers to people into forward-looking centers, ordered by their semantic role, ascertain the hierarchy of sentences, analyze the transition types resulted by the scheme of different resolutions, finally, choice the most possible scheme of resolution according to the precedence of the types.