Robust stochastic parsing using the inside-outside algorithm

Abstract

The paper describes a parser of sequences of (English) part-of-speech labels which utilises a probabilistic grammar trained using the inside-outside algorithm. The initial (meta)grammar is defined by a linguist and further rules compatible with metagrammatical constraints are automatically generated. During training, rules with very low probability are rejected yielding a wide-coverage parser capable of ranking alternative analyses. A series of corpus-based experiments describe the parser's performance.

Revised and updated version of paper from AAAI Workshop on Probabilistically-based Natural Language Processing Techniques, 1992, 16 pages, uuencoded, compressed postscript

Cited by in corpus (8)

• Discovery of Linguistic Relations Using Lexical Attraction
• Unsupervised Language Acquisition: Theory and Practice
• Designing Statistical Language Learners: Experiments on Noun Compounds
• Automatic Extraction of Tagset Mappings from Parallel-Annotated Corpora
• Statistical Inference and Probabilistic Modelling for Constraint-Based NLP
• Learning Unification-Based Natural Language Grammars
• Supervised Grammar Induction Using Training Data with Limited Constituent Information
• Exploring the role of Punctuation in Parsing Natural Text