Combining semantic and syntactic structure for language modeling
Computation and Language
2007-05-23 v1
Abstract
Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between non-headwords. We show that non-headword dependencies contribute to significantly improved word error rate, and that a data-oriented parsing model trained on semantically and syntactically annotated data can exploit these dependencies. This paper also contains the first DOP model trained by means of a maximum likelihood reestimation procedure, which solves some of the theoretical shortcomings of previous DOP models.
Cite
@article{arxiv.cs/0110051,
title = {Combining semantic and syntactic structure for language modeling},
author = {Rens Bod},
journal= {arXiv preprint arXiv:cs/0110051},
year = {2007}
}
Comments
4 pages