Improving Language Models by Clustering Training Sentences

Details Improving Language Models by Clustering Training Sentences Improving Language Models by Clustering Training Sentences

1994-10-04

arxiv.org/abs/cmp-lg/9410001v1

Computer Science

Computation and Language

Expanded version of a paper to appear in ANLP-94, Stuttgart. Latex, 7 pages. Needs latex-acl.sty

Scientific paper

Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus automatically into subcorpora on the criterion of entropy reduction, and calculating separate language model parameters for each cluster. This kind of clustering offers a way to represent important contextual effects and can therefore significantly improve the performance of a model. It also offers a reasonably automatic means to gather evidence on whether a more complex, context-sensitive model using the same general kind of linguistic information is likely to reward the effort that would be required to develop it: if clustering improves the performance of a model, this proves the existence of further context dependencies, not exploited by the unclustered model. As evidence for these claims, I present results showing that clustering improves some models but not others for the ATIS domain. These results are consistent with other findings for such models, suggesting that the existence or otherwise of an improvement brought about by clustering is indeed a good pointer to whether it is worth developing further the unclustered model.

Affiliated with

Also associated with

No associations

Rating

Improving Language Models by Clustering Training Sentences 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 Improving Language Models by Clustering Training Sentences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Improving Language Models by Clustering Training Sentences will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-232507