This paper presents a new learning method for automatic acquisition of translation knowledge from parallel corpora. We apply this learning method to automatic extraction of bilingu...
CLIR resources, such as dictionaries and parallel corpora, are scarce for special domains. Obtaining comparable corpora automatically for such domains could be an answer to this p...
Building NLG systems, in particular statistical ones, requires parallel data (paired inputs and outputs) which do not generally occur naturally. In this paper, we investigate the ...
When translating among languages that differ substantially in word order, machine translation (MT) systems benefit from syntactic preordering—an approach that uses features fro...
Paraphrase detection can be seen as the task of aligning sentences that convey the same information but yet are written in different forms. Such resources are important to automat...