learning to parse natural language with maximum entropy models（学习与最大熵模型来解析自然语言）.pdfVIP

Machine Learning 34, 151–175 (1999) c 1999 Kluwer Academic Publishers. Manufactured in The Netherlands. Learning to Parse Natural Language with Maximum Entropy Models ADWAIT RATNAPARKHI adwait@ Department of Computer and Information Science, University of Pennsylvania, 200 South 33rd Street, Philadelphia, PA 19104-6389 Editors: Claire Cardie and Raymond Mooney Abstract. This paper presents a machine learning system for parsing natural language that learns from manually parsed example sentences, and parses unseen data at state-of-the-art accuracies. Its machine learning technology, based on the maximum entropy framework, is highly reusable and not specific to the parsing problem, while the linguistic hints that it uses to learn can be specified concisely. It therefore requires a minimal amount of human effort and linguistic knowledge for its construction. In practice, the running time of the parser on a test sentence is linear with respect to the sentence length. We also demonstrate that the parser can train from other domains without modification to the modeling framework or the linguistic hints it uses to learn. Furthermore, this paper shows that research into rescoring the top 20 parses returned by the parser might yield accuracies dramatically higher than the state-of-the-art. Keywords: maximum entropy models, natural language processing, parsing 1. Introduction The task of a natural language parser is to take a sentence as input and return a syntactic representation that corresponds to the likely semantic interpretation of the sentence. For example, some parsers, given the sentence I buy cars with tires would return a parse tree in the format: The author is now at the I