Telegraphic messages with numerous instances of omission pose a new challenge to parsing in that a sentence with omission causes a higher degree of ambi6uity than a sentence witho...
Young-Suk Lee, Clifford J. Weinstein, Stephanie Se...
Traditional 1-best translation pipelines suffer a major drawback: the errors of 1best outputs, inevitably introduced by each module, will propagate and accumulate along the pipeli...
We present the newest implementation of the LINGSTAT machine-aided translation system. The moat signiflcsat change from earlier versions is a new set of modules that produce a dra...
Jonathan Yamron, James Cant, Anne Demedts, Taiko D...
We propose several techniques for improving statistical machine translation between closely-related languages with scarce resources. We use character-level translation trained on ...
In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forestto-string rule is capable of capturing nonsyntactic ...