We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
Previous work has shown that high quality phrasal paraphrases can be extracted from bilingual parallel corpora. However, it is not clear whether bitexts are an appropriate resourc...
Juri Ganitkevitch, Chris Callison-Burch, Courtney ...
The MT system described in this paper combines hand-built analysis and generation components with automatically learned example-based transfer patterns. Up to now, the transfer co...
Many existing methods for bilingual lexicon learning from comparable corpora are based on similarity of context vectors. These methods suffer from noisy vectors that greatly affec...
Manually constructing an inventory of word senses has suffered from problems including high cost, arbitrary assignment of meaning to words, and mismatch to domains. To overcome th...