Large language models in machine translation (2007)
| Venue: | In EMNLP |
| Citations: | 78 - 2 self |
BibTeX
@INPROCEEDINGS{Brants07largelanguage,
author = {Thorsten Brants and Ashok C. Popat and Peng Xu and Franz J. Och and Jeffrey Dean and Google Inc},
title = {Large language models in machine translation},
booktitle = {In EMNLP},
year = {2007},
pages = {858--867}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper reports on the benefits of largescale statistical language modeling in machine translation. A distributed infrastructure is proposed which we use to train on up to 2 trillion tokens, resulting in language models having up to 300 billion n-grams. It is capable of providing smoothed probabilities for fast, single-pass decoding. We introduce a new smoothing method, dubbed Stupid Backoff, that is inexpensive to train on large data sets and approaches the quality of Kneser-Ney Smoothing as the amount of training data increases. 1
Citations
| 892 | Mathematics of Statistical Machine Translation: Parameter Estimation - Brown, Pietra, et al. - 1993 |
| 631 | J: An Empirical Study of Smoothing Techniques for Language Modeling - SF, Goodman - 1996 |
| 574 | Estimation of probabilities from sparse data for the language model component of a speech recognizer - Katz - 1987 |
| 286 | Interpolated estimation of Markov source parameters from sparse data - Jelinek, Mercer - 1980 |
| 245 | The alignment template approach to statistical machine translation - Och, Ney - 2004 |
| 179 | Improved backing-off for m-gram language modeling - Kneser, Ney - 1995 |
| 102 | Statistical Significance Tests for Machine Translation Evaluation - Koehn - 2004 |
| 70 | A bit of progress in language modeling - Goodman - 2001 |
| 70 | Computer-Intensive Methods for Testing Hypotheses - Noreen - 1989 |
| 30 | Dynamic programming search for continuous speech recognition - Ney, Ortmanns - 1999 |
