Computer Science – Computation and Language
Scientific paper
2008-01-30
Computer Science
Computation and Language
10 pages ; EMNLP'2007 Conference (Prague)
Scientific paper
Most current word prediction systems make use of n-gram language models (LM) to estimate the probability of the following word in a phrase. In the past years there have been many attempts to enrich such language models with further syntactic or semantic information. We want to explore the predictive powers of Latent Semantic Analysis (LSA), a method that has been shown to provide reliable information on long-distance semantic dependencies between words in a context. We present and evaluate here several methods that integrate LSA-based information with a standard language model: a semantic cache, partial reranking, and different forms of interpolation. We found that all methods show significant improvements, compared to the 4-gram baseline, and most of them to a simple cache model as well.
Antoine Jean-Yves
Wandmacher Tonio
No associations
LandOfFree
Methods to integrate a language model with semantic information for a word prediction component does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Methods to integrate a language model with semantic information for a word prediction component, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods to integrate a language model with semantic information for a word prediction component will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-122167