It has long been observed that monolingual text exhibits a tendency toward “one sense per discourse,” and it has been argued that a related “one translation per discourse” constraint is operative in bilingual contexts as well. In this paper, we introduce a novel method using forced decoding to confirm the validity of this constraint, and we demonstrate that it can be exploited in order to impro...

The tourist flows between the Arabic-speaking world and the West have strengthened the need to develop several Arabic websites, brochures, guidebooks etc. in order to be closer to Arabic speaking visitors to Western countries. In the field of tourism, English has a predominant role and the Arabic language, through different strategies of word-formation, is reacting to Western influence by gener...

The present paper describes the experience gained at LDC in the collection and transcription of conversational dialectal Arabic. The paper will cover the following: (a) Arabic language background; (b) objectives. principles, and methodological choices of dialectal Arabic transcription, (c) design features of LDC‟s „Arabic MultiDialectal Transcription Tool‟ (AMADAT) and metalanguage transcriptio...

Automatic metrics for the evaluation of machine translation (MT) compute scores that characterize globally certain aspects of MT quality such as adequacy and fluency. This paper introduces a reference-based metric that is focused on a particular class of function words, namely discourse connectives, of particular importance for text structuring, and rather challenging for MT. To measure the acc...