Statistical Phrase-Based Translation
- Philipp Koehn, F. Och, D. Marcu
- Computer ScienceNorth American Chapter of the Association for…
- 27 May 2003
The empirical results suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translation.
A Systematic Comparison of Various Statistical Alignment Models
An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models.
Minimum Error Rate Training in Statistical Machine Translation
- F. Och
- Computer ScienceAnnual Meeting of the Association for…
- 7 July 2003
It is shown that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.
Improved Statistical Alignment Models
It is shown that models with a first-order dependence and a fertility model lead to significantly better results than the simple models IBM-1 or IBM-2, which are not able to go beyond zero-order dependencies.
Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics
- Chin-Yew Lin, F. Och
- Computer ScienceAnnual Meeting of the Association for…
- 21 July 2004
Two new objective automatic evaluation methods for machine translation based on longest common subsequence between a candidate translation and a set of reference translations and relaxes strict n-gram matching to skip-bigram matching are described.
The Alignment Template Approach to Statistical Machine Translation
A phrase-based statistical machine translation approach the alignment template approach is described, which allows for general many-to-many relations between words and is easier to extend than classical statistical machinetranslation systems.
Large Language Models in Machine Translation
- T. Brants, Ashok Popat, P. Xu, F. Och, J. Dean
- Computer ScienceConference on Empirical Methods in Natural…
- 22 June 2007
Systems, methods, and computer program products for machine translation are provided for backoff score determination as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.
Discriminative Training and Maximum Entropy Models for Statistical Machine Translation
A framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case and shows that a baseline statistical machinetranslation system is significantly improved using this approach.
ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation
- Chin-Yew Lin, F. Och
- Computer ScienceInternational Conference on Computational…
- 23 August 2004
A new evaluation method, Orange, is introduced for evaluating automatic machine translation evaluation metrics automatically without extra human involvement other than using a set of reference translations.
Improved Alignment Models for Statistical Machine Translation
- F. Och, C. Tillmann, H. Ney
- Computer ScienceConference on Empirical Methods in Natural…
- 1999
Improved alignment models for statistical machine translation are described and experimental results are presented using the Verbmobil task (German-English, 6000word vocabulary) which is a limited-domain spoken-language task.
...
...