Paper: A Structured Language Model Based On Context-Sensitive Probabilistic Left-Corner Parsing

ACL ID N01-1029
Title A Structured Language Model Based On Context-Sensitive Probabilistic Left-Corner Parsing
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2001
Authors

Recent contributions to statistical language model- ing for speech recognition have shown that prob- abilistically parsing a partial word sequence aids the prediction of the next word, leading to “struc- tured” language models that have the potential to outperform n-grams. Existing approaches to struc- tured language modeling construct nodes in the par- tial parse tree after all of the underlying words have been predicted. This paper presents a different ap- proach, based on probabilistic left-corner grammar (PLCG) parsing, that extends a partial parse both from the bottom up and from the top down, lead- ing to a more focused and more accurate, though somewhat less robust, search of the parse space. At the core of our new structured language model is a fast context-sensitive and lexica...