English

Expoiting Syntactic Structure for Language Modeling

Computation and Language 2007-05-23 v2

Abstract

The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint sequence of words--binary-parse-structure with headword annotation and operates in a left-to-right manner --- therefore usable for automatic speech recognition. The model, its probabilistic parameterization, and a set of experiments meant to evaluate its predictive power are presented; an improvement over standard trigram modeling is achieved.

Keywords

Cite

@article{arxiv.cs/9811022,
  title  = {Expoiting Syntactic Structure for Language Modeling},
  author = {Ciprian Chelba and Frederick Jelinek},
  journal= {arXiv preprint arXiv:cs/9811022},
  year   = {2007}
}

Comments

changed ACM-class membership and buggy author names