Abstract | ||
---|---|---|
One of the problems facing translation systems that automatically extract transfer mappings (rules or examples) from bilingual corpora is the trade-off between contextual specificity and general applicability of the mappings, which typically results in conflicting mappings without distinguishing context. We present a machine-learning approach to choosing between such mappings, using classifiers that, in effect, selectively expand the context for these mappings using features available in a linguistic representation of the source language input. We show that using these classifiers in our machine translation system significantly improves the quality of the translated output. Additionally, the set of distinguishing features selected by the classifiers provides insight into the relative importance of the various linguistic features in choosing the correct contextual translation. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1007/3-540-45820-4_13 | AMTA |
Keywords | Field | DocType |
distinguishing feature,better contextual translation,translation system,bilingual corpus,machine learning,correct contextual translation,various linguistic feature,distinguishing context,contextual specificity,machine translation system,conflicting mapping,linguistic representation,machine translation,feature selection | Decision tree,Computer science,Multilingualism,Machine translation system,Speech recognition,Transfer-based machine translation,Natural language processing,Artificial intelligence,Automatic translation,Machine learning | Conference |
Volume | ISSN | ISBN |
2499 | 0302-9743 | 3-540-44282-0 |
Citations | PageRank | References |
2 | 0.44 | 12 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arul Menezes | 1 | 470 | 29.57 |