Stephan Vogel
ABSTRACT
In this paper, we describe a new model for word alignment in statistical translation and present experimental results. The idea of the model is to make the alignment probabilities dependent on the differences in the alignment positions rather than on the absolute positions. To achieve this goal, the approach uses a first-order Hidden Markov model (HMM) for the word alignment problem as they are used successfully in speech recognition for the time alignment problem. The difference to the time alignment HMM is that there is no monotony constraint for the possible word orderings. We describe the details of the model and test the model on several bilingual corpora.
- L. E. Baum. 1972. An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process. Inequalities, 3:1--8.Google Scholar
- Peter F. Brown, Vincent J. Della Pietra, Stephen A. Della Pietra, and Robert L. Mercer. 1993. The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics, 19(2):263--311. Google ScholarDigital Library
- Ido Dagan, Ken Church, and William A. Gale. 1993. Robust Bilingual Word Alignment for Machine Aided Translation Proceedings of the Workshop on Very Large Corpora, Columbus, Ohio, 1--8Google Scholar
- ECI/MCI: The European Corpus Initiative Multilingual Corpus I. 1994. Association for Computational Linguistics.Google Scholar
- EnTrans. The Definition of a MT Task. Technical Report, EnTrans Project. 1996(Foruthcomming). Depto. de Sistemas Informaticos y Computacion (DSIC), Universidad Politecnica de Valencia.Google Scholar
- Pascale Fung, and Kenneth Ward Church. 1994. K-vec: A new approach for aligning parallel texts. Proceedings of COLING 94, 1096--1102, Kyoto, Japan. Google ScholarDigital Library
- Frederik Jelinek. 1976. Speech Recognition by Statistical Methods. Proceedings of the IEEE, Vol. 64, 532--556, April 1976.Google ScholarCross Ref
- Martin Kay, and Martin Röscheisen. 1993. Text-Translation Alignment. Computational Linguistics, 19(1):121--142 Google ScholarDigital Library
- Wolfgang Wahlster. 1993. Verbmobil: Translation of Face-to-Face Dialogs. Proceedings of the MT Summit IV, 127--135, Kobe, Japan.Google Scholar
- HMM-based word alignment in statistical translation
Recommendations
HMM Word and Phrase Alignment for Statistical Machine Translation
Estimation and alignment procedures for word and phrase alignment hidden Markov models (HMMs) are developed for the alignment of parallel text. The development of these models is motivated by an analysis of the desirable features of IBM Model 4, one of ...
English to Tamil statistical machine translation and alignment using HMM
ICNVS'10: Proceedings of the 12th international conference on Networking, VLSI and signal processingThis paper describes English to Tamil statistical machine translation and its alignment using Hidden Markov Model (HMM).Statistical machine translation is a part of natural language processing and is based on probability distribution. Machine ...
HMM word and phrase alignment for statistical machine translation
HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language ProcessingHMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently. We find that Chinese-English word alignment performance is comparable to ...
Comments