@inproceedings{6df98e86147b4ec59d5c8af3dc91d85e,
title = "Stochastic analysis of lexical and semantic enhanced structural language model",
abstract = "In this paper, we present a directed Markov random field model that integrates trigram models, structural language models (SLM) and probabilistic latent semantic analysis (PLSA) for the purpose of statistical language modeling. The SLM is essentially a generalization of shift-reduce probabilistic push-down automata thus more complex and powerful than probabilistic context free grammars (PCFGs). The added context-sensitiveness due to trigrams and PLSAs and violation of tree structure in the topology of the underlying random field model make the inference and parameter estimation problems plausibly intractable, however the analysis of the behavior of the lexical and semantic enhanced structural language model leads to a generalized inside-outside algorithm and thus to rigorous exact EM type re-estimation of the composite language model parameters.",
keywords = "Language modeling, Probabilistic latent semantic analysis, Structural language model, Trigram",
author = "Shaojun Wang and Shaomin Wang and Li Cheng and Russell Greiner and Dale Schuurmans",
year = "2006",
doi = "10.1007/11872436_9",
language = "English",
isbn = "3540452648",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "97--111",
booktitle = "Grammatical Inference",
address = "Germany",
note = "8th International Colloquium on Grammatical Inference, ICGI 2006 ; Conference date: 20-09-2006 Through 22-09-2006",
}