In this paper, we demonstrate that accurate machine translation is possible without the concept of “words,” treating MT as a problem of transformation between character string...
Graham Neubig, Taro Watanabe, Shinsuke Mori, Tatsu...
Parallel data in the domain of interest is the key resource when training a statistical machine translation (SMT) system for a specific purpose. Since ad-hoc manual translation c...
Prasanth Kolachina, Nicola Cancedda, Marc Dymetman...
Although much work on relation extraction has aimed at obtaining static facts, many of the target relations are actually fluents, as their validity is naturally anchored to a cer...
Java has emerged as one of the most dynamic programming languages today. During the past eight years it has become a leading choice as the programming language for an introductory...
Abstract. Quantitative languages are an extension of boolean languages that assign to each word a real number. Mean-payoff automata are finite automata with numerical weights on tr...
Krishnendu Chatterjee, Laurent Doyen, Herbert Edel...