This paper investigates the combination of word-alignments computed with the competitive linking algorithm and well-established IBM models. New training methods for phrase-based st...
Topics in prior-art patent search are typically full patent applications and relevant items are patents often taken from sources in different languages. Cross language patent retr...
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...
Searching online information is increasingly a daily activity for many people. The multilinguality of online content is also increasing (e.g. the proportion of English web users, ...
Yaser Al-Onaizan, Radu Florian, Martin Franz, Hany...
Abstract. We describe OpenMaTrEx, a free/open-source examplebased machine translation (EBMT) system based on the marker hypothesis, comprising a marker-driven chunker, a collection...
Sandipan Dandapat, Mikel L. Forcada, Declan Groves...