Supervised Grammar Induction Using Training Data with Limited Constituent Information

Details Supervised Grammar Induction Using Training Data with Limited Constituent Information Supervised Grammar Induction Using Training Data with Limited Constituent Information

1999-05-02

arxiv.org/abs/cs/9905001v1

Computer Science

Computation and Language

7 pages, 2 figures, to appear in the proc. of ACL '99

Scientific paper

Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is prohibitively expensive. This work aims to improve the induction strategy when there are few labels in the training data. We show that the most informative linguistic constituents are the higher nodes in the parse trees, typically denoting complex noun phrases and sentential clauses. They account for only 20% of all constituents. For inducing grammars from sparsely labeled training data (e.g., only higher-level constituent labels), we propose an adaptation strategy, which produces grammars that parse almost as well as grammars induced from fully labeled corpora. Our results suggest that for a partial parser to replace human annotators, it must be able to automatically extract higher-level constituents rather than base noun phrases.

Affiliated with

Also associated with

No associations

Rating

Supervised Grammar Induction Using Training Data with Limited Constituent Information does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Supervised Grammar Induction Using Training Data with Limited Constituent Information, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Supervised Grammar Induction Using Training Data with Limited Constituent Information will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-90586