Discriminative, syntactic language modeling through latent svms (2008)
Cached
Download Links
| Venue: | In AMTA ’08 |
| Citations: | 19 - 2 self |
BibTeX
@INPROCEEDINGS{Cherry08discriminative,syntactic,
author = {Colin Cherry and Chris Quirk},
title = {Discriminative, syntactic language modeling through latent svms},
booktitle = {In AMTA ’08},
year = {2008}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We construct a discriminative, syntactic language model (LM) by using a latent support vector machine (SVM) to train an unlexicalized parser to judge sentences. That is, the parser is optimized so that correct sentences receive high-scoring trees, while incorrect sentences do not. Because of this alternative objective, the parser can be trained with only a part-of-speech dictionary and binary-labeled sentences. We follow the paradigm of discriminative language modeling with pseudonegative examples (Okanohara and Tsujii, 2007), and demonstrate significant improvements in distinguishing real sentences from pseudo-negatives. We also investigate the related task of separating machine-translation (MT) outputs from reference translations, again showing large improvements. Finally, we test our LM in MT reranking, and investigate the language-modeling parser in the context of unsupervised parsing. 1
Keyphrases
latent svms syntactic language binary-labeled sentence related task unsupervised parsing discriminative language incorrect sentence pseudonegative example mt reranking reference translation correct sentence unlexicalized parser language-modeling parser alternative objective significant improvement syntactic language model real sentence high-scoring tree large improvement latent support vector machine
