An Empirical Study of Smoothing Techniques for Language Modeling

Details An Empirical Study of Smoothing Techniques for Language Modeling An Empirical Study of Smoothing Techniques for Language Modeling

1996-06-11

arxiv.org/abs/cmp-lg/9606011v1

Proceedings of the 34th Meeting of the Association for Computational Linguistics (ACL '96)

Computer Science

Computation and Language

9 pages, LaTeX, uses aclap.sty

Scientific paper

We present an extensive empirical comparison of several smoothing techniques in the domain of language modeling, including those described by Jelinek and Mercer (1980), Katz (1987), and Church and Gale (1991). We investigate for the first time how factors such as training data size, corpus (e.g., Brown versus Wall Street Journal), and n-gram order (bigram versus trigram) affect the relative performance of these methods, which we measure through the cross-entropy of test data. In addition, we introduce two novel smoothing techniques, one a variation of Jelinek-Mercer smoothing and one a very simple linear interpolation technique, both of which outperform existing methods.

Affiliated with

Also associated with

No associations

Rating

An Empirical Study of Smoothing Techniques for Language Modeling 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 An Empirical Study of Smoothing Techniques for Language Modeling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and An Empirical Study of Smoothing Techniques for Language Modeling will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-100781