Explorations in Automatic Thesaurus Discovery
Explorations in Automatic Thesaurus Discovery
A systematic comparison of various statistical alignment models
Computational Linguistics
Word sense disambiguation vs. statistical machine translation
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Word-sense disambiguation for machine translation
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Moses: open source toolkit for statistical machine translation
ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
A hybrid relational approach for WSD: first results
COLING ACL '06 Proceedings of the 21st International Conference on computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Data-driven semantic analysis for multilingual WSD and lexical selection in translation
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Extending statistical machine translation with discriminative and trigger-based lexicon models
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
CICLing'08 Proceedings of the 9th international conference on Computational linguistics and intelligent text processing
SemEval-2010 task 2: Cross-lingual lexical substitution
SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
SemEval-2010 task 3: Cross-lingual word sense disambiguation
SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
Local lexical adaptation in machine translation through triangulation: SMT helping SMT
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
| Hi-index | 0.00 |
We integrate semantic information at two stages of the translation process of a state-of-the-art SMT system. A Word Sense Disambiguation (WSD) classifier produces a probability distribution over the translation candidates of source words which is exploited in two ways. First, the probabilities serve to rerank a list of n-best translations produced by the system. Second, the WSD predictions are used to build a supplementary language model for each sentence, aimed to favor translations that seem more adequate in this specific sentential context. Both approaches lead to significant improvements in translation performance, highlighting the usefulness of source side disambiguation for SMT.