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
โฆ LIBER โฆ
[Association for Computational Linguistics the 37th annual meeting of the Association for Computational Linguistics - College Park, Maryland (1999.06.20-1999.06.26)] Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics - - Supervised grammar induction using training data with limited constituent information
โ Scribed by Hwa, Rebecca
- Book ID
- 121837265
- Publisher
- Association for Computational Linguistics
- Year
- 1999
- Weight
- 662 KB
- Category
- Article
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
[Association for Computational Linguisti
โ
Hwa, Rebecca
๐
Article
๐
1999
๐
Association for Computational Linguistics
โ 662 KB
[Association for Computational Linguisti
โ
Reynar, Jeffrey C.
๐
Article
๐
1999
๐
Association for Computational Linguistics
โ 709 KB
[Association for Computational Linguisti
โ
Lee, Lillian
๐
Article
๐
1999
๐
Association for Computational Linguistics
โ 689 KB
[Association for Computational Linguisti
โ
Resnik, Philip
๐
Article
๐
1999
๐
Association for Computational Linguistics
โ 737 KB
[Association for Computational Linguisti
โ
Chen, Stanley F.
๐
Article
๐
1995
๐
Association for Computational Linguistics
โ 639 KB
[Association for Computational Linguisti
โ
Chen, Stanley F.
๐
Article
๐
1995
๐
Association for Computational Linguistics
โ 639 KB
We describe a corpus-based induction algorithm for probabilistic context-free grammars. The algorithm employs a greedy heuristic search within a Bayesian framework, and a post-pass using the Inside-Outside algorithm. We compare the performance of our algorithm to n-gram models and the Inside-Outside