Max-Margin Parsing (2004)by B. Taskar, D. Klein, M. Collins, D. Koller, and C. Manning
Abstract:
We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic programs for parsing. In particular, it allows one to efficiently learn a model which discriminates among the entire space of parse trees, as opposed to reranking the top few candidates. Our models can condition on arbitrary features of input sentences, thus incorporating an important kind of lexical information without the added algorithmic complexity of modeling headedness. We provide an efficient algorithm for learning such models and show experimental evidence of the model's improved performance over a natural baseline model and a lexicalized probabilistic context-free grammar.
Download Information
|
B. Taskar, D. Klein, M. Collins, D. Koller, and C. Manning (2004). "Max-Margin Parsing." Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP).
Winner of the Best Paper Award.
|
|
Bibtex citation
@inproceedings{Taskar+al:EMNLP04,
title = {Max-Margin Parsing},
author = {B. Taskar and D. Klein and M. Collins and D. Koller and C. Manning},
booktitle = {Proceedings of the Conference on Empirical Methods in Natural
Language Processing (EMNLP)},
year = 2004,
Note = {Winner of the Best Paper Award},
}
full list
|