Learning to Parse Natural Language with Maximum Entropy Models

  • Authors:
  • Adwait Ratnaparkhi

  • Affiliations:
  • Department of Computer and Information Science, University of Pennsylvania, 200 South 33rd Street, Philadelphia, PA 19104-6389. adwait@unagi.cis.upenn.edu

  • Venue:
  • Machine Learning - Special issue on natural language learning
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a machine learning systemfor parsing natural language thatlearns from manually parsed example sentences, andparses 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 learncan 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 modificationto 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 parsermight yield accuracies dramatically higher than the state-of-the-art.