• Publications
  • Influence
(Meta-) Evaluation of Machine Translation
An extensive human evaluation was carried out not only to rank the different MT systems, but also to perform higher-level analysis of the evaluation process, revealing surprising facts about the most commonly used methodologies.
Further Meta-Evaluation of Machine Translation
This paper analyzes the translation quality of machine translation systems for 10 language pairs translating between Czech, English, French, German, Hungarian, and Spanish and uses the human judgments of the systems to analyze automatic evaluation metrics for translation quality.
Experiments in Domain Adaptation for Statistical Machine Translation
This paper gives a description of the submission of the University of Edinburgh to the WMT 2007 shared task, and experiments with various ways of adapting a statistical machine translation systems to a special domain.
Findings of the 2009 Workshop on Statistical Machine Translation
A large-scale manual evaluation of 87 machine translation systems and 22 system combination entries is conducted, which used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of translation quality, for more than 20 metrics.
Scaling Phrase-Based Statistical Machine Translation to Larger Corpora and Longer Phrases
A novel data structure for phrase-based statistical machine translation which allows for the retrieval of arbitrarily long phrases while simultaneously using less memory than is required by current decoder implementations is described.
Word Lattices for Multi-Source Translation
It is demonstrated how multi-source translation can be adapted for multiple monolingual inputs, and a novel method of input combination to generate lattices for multi- source translation within a single translation model is presented.
Proceedings of the Fourth Workshop on Statistical Machine Translation, WMT@EACL 2009, Athens, Greece, March 30-31, 2009
The EACL 2009 Workshop on Statistical Machine Translation (WMT09) took place on March 30 and 31 in Athens, Greece, immediately preceding the 12th Conference of the European Chapter of the Association
Proceedings of the Third Workshop on Statistical Machine Translation
The ACL 2008 Workshop on Statistical Machine Translation (WMT-08) took place on Thursday, June 19 in Columbus, Ohio, United States, immediately following the annual meeting of the Association for
Improving statistical translation through editing
How Linear B’s phrase-based translation models are learned from a parallel corpus is described, and how the quality of the translations produced by the system can be improved over time through editing is shown.