Previous abstract | CoNLL-2001 Proceedings | Next abstract

Distributional Phrase Structure Induction

Dan Klein and Christopher D. Manning

Unsupervised grammar induction systems commonly judge potential constituents on the basis of their effects on the likelihood of the data. Linguistic justifications of constituency, on the other hand, rely on notions such as substitutability and varying external contexts. We describe two systems for distributional grammar induction which operate on such principles, using part-of-speech tags as the contextual features. The advantages and disadvantages of these systems are examined, including precision/recall trade-offs, error analysis, and extensibility.

[ps] [pdf] [bibtex]

Last update: July 12, 2001.