Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Combining Semantic and Syntactic Structure for Language Modeling

Rens Bod

Informatics Research Institute, University of Leeds, Leeds, UK and Institute for Logic, Language and Computation, University of Amsterdam, The Netherlands

Structured language models for speech recognition have been shown to remedy the weaknesses of n -gram models. All current structured language models, however, are limited in that they do not take into account dependencies between non-headwords. We show that non-headword dependencies contribute significantly to improved word error rate, and that a data-oriented parsing model trained on semantically and syntactically annotated data can exploit these dependencies. This paper contains the first published experiments with a data-oriented parsing model trained by means of a maximum likelihood reestimation procedure.


Full Paper

Bibliographic reference.  Bod, Rens (2000): "Combining semantic and syntactic structure for language modeling", In ICSLP-2000, vol.3, 106-109.