M.L.: Exploring the use of targetlanguage information to train the part-of-speech tagger of machine translation systems (2004)
| Venue: | In: Advances in Natural Language Processing, Proceedings of 4th International Conference EsTAL. Volume 3230 of Lecture Notes in Computer Science. Springer-Verlag (2004) 137–148 F. Sánchez-Martínez, J.A. Pérez-Ortiz, and M.L. Forcada |
| Citations: | 6 - 4 self |
BibTeX
@INPROCEEDINGS{Sánchez-martínez04m.l.:exploring,
author = {Felipe Sánchez-martínez and Juan Antonio Pérez-ortiz and Mikel L. Forcada and Departament De Llenguatges I Sistemes},
title = {M.L.: Exploring the use of targetlanguage information to train the part-of-speech tagger of machine translation systems},
booktitle = {In: Advances in Natural Language Processing, Proceedings of 4th International Conference EsTAL. Volume 3230 of Lecture Notes in Computer Science. Springer-Verlag (2004) 137–148 F. Sánchez-Martínez, J.A. Pérez-Ortiz, and M.L. Forcada},
year = {2004},
pages = {137--148}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract. When automatically translating between related languages, one of the main sources of machine translation errors is the incorrect resolution of part-of-speech (PoS) ambiguities. Hidden Markov models (HMM) are the standard statistical approach to try to properly resolve such ambiguities. The usual training algorithms collect statistics from source-language texts in order to adjust the parameters of the HMM, but if the HMM is to be embedded in a machine translation system, target-language information may also prove valuable. We study how to use a target-language model (in addition to source-language texts) to improve the tagging and translation performance of a statistical PoS tagger of an otherwise rule-based, shallow-transfer machine translation engine, although other architectures may be considered as well. The method may also be used to customize the machine translation engine to a particular target language, text type, or subject, or to statistically “retune ” it after introducing new transfer rules. 1
Citations
| 3116 | A tutorial on hidden Markov models and selected applications in speech recognition - Rabiner - 1989 |
| 612 | Statistical Methods for Speech Recognition - Jelinek - 1997 |
| 325 | A Practical Part-of-Speech Tagger - Cutting, Kupiec, et al. - 1991 |
| 276 | An Introduction to Machine Translation - Hutchins, Somers - 1992 |
| 177 | Robust part-of-speech tagging using hidden Markov model - Kupiec - 1992 |
| 20 | Good-Turing Smoothing Without Tears - Gale - 1995 |
| 13 | The Spanish–Catalan machine translation system interNOSTRUM - Canals-Marote, Esteve-Guillen, et al. - 2001 |
| 12 | Tagging the Teleman corpus - Brants, Samuelsson - 1995 |
| 11 | Improving part-of-speech tagging using lexicalized HMMs - Pla, Molina - 2004 |
