Panlingual Translation
Scaling existing translation technology to all language-pairs in the world is not feasible due to the lack of aligned parallel corpora and other resources needed by statistical machine translation algorithms. This project seeks to combine all existing translation dictionaries present in the world into a single resource, translation graph and to perform probabilistic inference on this graph to automatically infer translations between language-pairs for which no dictionary exists.
We have compiled the largest translation dictionary, PanDictionary, that contains over 4 times the number of translations compared to the English Wiktionary.
People
Publications
- Panlingual Lexical Translation via Probabilistic Inference (2010)
- Panlingual Lexical Translation via Probabilistic Inference (2010)
- A Rose is a Roos is a Ruusu: Querying Translations for Web Image Search (2009)
- Compiling a Massive, Multilingual Dictionary via Probabilistic Inference (2009)
- Lemmatic Machine Translation (2009)
- Lexical Translation with Application to Image Search on the Web (2007)
- Ambiguity Reduction for Machine Translation: Human-Computer Collaboration (2006)
Research Groups
Last changed Fri, 2012-11-16 11:28

cs.