Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/association-for-computing-machinery/a-word-to-phrase-statistical-translation-model-NrgQm0a2yI
References (34)
-
I. Witten, T. Bell (1991)
The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compressionIEEE Trans. Inf. Theory, 37
-
(2005)
ACM Transactions on Speech and Language Processing -
C. Tillmann, S. Vogel, H. Ney, A. Zubiaga (1997)
A DP-based Search Using Monotone Alignments in Statistical Translation -
A. Dempster, N. Laird, D. Rubin (1977)
Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper -
T. Cormen, C. Leiserson, R. Rivest, C. Stein (2001)
Introduction to Algorithms, 2nd edition. -
D. Marcu, Daniel Wong (2002)
A Phrase-Based,Joint Probability Model for Statistical Machine Translation -
(2001)
A syntactic-based statistical translation model -
Richard Zens, F. Och, H. Ney (2002)
Phrase-Based Statistical Machine Translation -
Bertoldi -
T. Takezawa, E. Sumita, F. Sugaya, H. Yamamoto, Seiichi Yamamoto (2002)
Toward a Broad-coverage Bilingual Corpus for Speech Translation of Travel Conversations in the Real World -
D. Marcu (2001)
Towards a Unified Approach to Memory- and Statistical-Based Machine Translation -
C. Tillmann (2003)
A Projection Extension Algorithm for Statistical Machine Translation -
F. Och, H. Ney (2003)
A Systematic Comparison of Various Statistical Alignment ModelsComputational Linguistics, 29
-
Dekai Wu (1996)
A Polynomial-Time Algorithm for Statistical Machine Translation -
Y. Zhang, S. Vogel (2004)
Measuring confidence intervals for the machine translation evaluation metricsIEEE Transactions on Medical Imaging
-
(1995)
Method and system for natural language translation -
C. Tillmann, H. Ney (2003)
Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine TranslationComputational Linguistics, 29
-
P. Brown, S. Pietra, V. Pietra, R. Mercer (1993)
The Mathematics of Statistical Machine Translation: Parameter EstimationComput. Linguistics, 19
-
Dempster A. P. (1977)
Maximum-likelihood from incomplete data via the EM algorithmJ. Royal Statist. Soc., B, 39
-
Ye-Yi Wang (2001)
Grammar Inference and Statistical Machine Translation -
F. Och (2003)
Minimum Error Rate Training in Statistical Machine Translation -
S. Vogel, Y. Zhang, Fei Huang, Fei Huang, A. Tribble, Ashish Venugopal, Bing Zhao, A. Waibel (2003)
The CMU statistical machine translation system -
Gregor Leusch, Nicola Ueffing, H. Ney (2003)
A novel string-to-string distance measure with applications to machine translation evaluation -
Philipp Koehn, F. Och, Daniel Marcu (2003)
Statistical Phrase-Based Translation -
Ye-Yi Wang, A. Waibel (1997)
Decoding Algorithm in Statistical Machine Translation -
F. Och, D. Gildea, S. Khudanpur, Anoop Sarkar, Kenji Yamada, Alexander Fraser, Shankar Kumar, Libin Shen, David Smith, Katherine Eng, Viren Jain, Zhenglin Jin, Dragomir Radev (2004)
A Smorgasbord of Features for Statistical Machine Translation -
F. Och, C. Tillmann, H. Ney (1999)
Improved Alignment Models for Statistical Machine Translation -
F. Och, H. Ney (2000)
A Comparison of Alignment Models for Statistical Machine Translation -
F. Jelinek (1997)
Statistical methods for speech recognition -
Federico M. (1998)
Language modelling. In Spoken Dialogues with Computers, R. D. Mori, Ed. Academy Press, London, UKChapter, 7
-
Ulrich Germann, Michael Jahr, Kevin Knight, D. Marcu, Kenji Yamada (2001)
Fast Decoding and Optimal Decoding for Machine Translation -
T. Cormen, C. Leiserson, R. Rivest (1990)
Introduction to Algorithms -
K. Papineni, Salim Roukos, T. Ward, Wei-Jing Zhu (2002)
Bleu: a Method for Automatic Evaluation of Machine Translation -
Kevin Knight (1999)
Decoding complexity in word-replacement translation modelsComput. Linguistics, 25
- Publisher
- Association for Computing Machinery
- Copyright
- Copyright © 2005 by ACM Inc.
- ISSN
- 1550-4875
- DOI
- 10.1145/1115686.1115687
- Publisher site
- See Article on Publisher Site
Abstract
This article addresses the development of statistical models for phrase-based machine translation (MT) which extend a popular word-alignment model proposed by IBM in the early 90s. A novel decoding algorithm is directly derived from the optimization criterion which defines the statistical MT approach. Efficiency in decoding is achieved by applying dynamic programming, pruning strategies, and word reordering constraints. It is known that translation performance can be boosted by exploiting phrase (or multiword) translation pairs automatically extracted from a parallel corpus. New phrase-based models are obtained by introducing extra multiwords in the target language vocabulary and by estimating the corresponding parameters from either: (i) a word-based model, (ii) phrase-based statistics computed on the parallel corpus, or (iii) the interpolation of the two previous estimates. Word-based and phrase-based MT models are evaluated on a traveling domain task in two translation directions: Chinese-English (12k-word vocabulary) and Italian-English (16k-word vocabulary). Phrase-based models show Bleu score improvements over the word-based model by 19% and 13% relative, respectively.
Journal
ACM Transactions on Speech and Language Processing (TSLP) – Association for Computing Machinery
Published: Dec 1, 2005