Dependency Language Modeling (1997)
| Citations: | 4 - 3 self |
BibTeX
@MISC{Stolcke97dependencylanguage,
author = {Andreas Stolcke and Ciprian Chelba and David Engle and Victor Jimenez and Lidia Mangu and Harry Printz and Eric Ristad and Roni Rosenfeld and Ciprian Chelba (jhu and David Engle (dod and Lidia Mangu (jhu and Harry Printz (ibm and Eric Ristad (princeton and Roni Rosenfeld (cmu and Dekai Wu (hong Kong Ust and Fred Jelinek (jhu and Sanjeev Khudanpur (jhu},
title = {Dependency Language Modeling},
year = {1997}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This report summarizes the work of the Dependency Language Modeling group at the 1996 Summer Speech Workshop at the Center for Language and Speech Processing at Johns Hopkins University (WS96). We motivate and descibe a novel statistical language model that models the syntactic dependencies between words. The model is formulated in the maximum entropy framework, which expresses statistical constraints on the frequencies of various type of dependencies, as well the standard N-gram statistics. We describe how this model was applied to the recognition of spontaneous English speech from the Switchboard corpus. Due to implementation constraints, only a reduced version of our model could be tested so far. The model gave a modest improvement over an N-gram baseline model. A by-product of the project is the Maximim Entropy Modeling Toolkit (MEMT), a freely available software package for domain-independent maximum entropy modeling. 1 Introduction Current state-of-the-art language models for s...
