Paper: Automatic Grammar Induction And Parsing Free Text: A Transformation-Based Approach

ACL ID P93-1035
Title Automatic Grammar Induction And Parsing Free Text: A Transformation-Based Approach
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1993
Authors
  • Eric Brill (University of Pennsylvania, Philadelphia PA)

In this paper we describe a new technique for parsing free text: a transformational grammar I is automatically learned that is capable of accu- rately parsing text into binary-branching syntac- tic trees with nonterminals unlabelled. The algo- rithm works by beginning in a very naive state of knowledge about phrase structure. By repeatedly comparing the results of bracketing in the current state to proper bracketing provided in the training corpus, the system learns a set of simple structural transformations that can be applied to reduce er- ror. After describing the algorithm, we present results and compare these results to other recent results in automatic grammar induction.