Klein, Dan and Manning, Christopher D. (2001) Distributional Phrase Structure Induction. In: Conference on Computational Natural Language Learning (CoNLL-2001), July 6-7, 2001, Toulouse, France.
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.
|Item Type:||Conference or Workshop Item (Paper)|
|Uncontrolled Keywords:||nlp, grammar induction, unsupervised learning|
|Related URLs:||Project Homepage||http://www-nlp.stanford.edu/|
|Deposited By:||Import Account|
|Deposited On:||08 Oct 2001 17:00|
|Last Modified:||27 Dec 2008 10:09|
Repository Staff Only: item control page