We present in this paper, an automatic query translation system in cross-language information retrieval (ArabicFrench). For the lexical disambiguation, our system combines between two resources: a bilingual dictionary and a parallel corpus. To select the best translation, our method is based on a correspondence measure between two semantic networks. The first one represents the senses of ambigu...

Statistical MT is limited by reliance on large parallel corpora. We propose Lemmatic MT, a new paradigm that extendsMT to a far broader set of languages, but requires substantial manual encoding effort. We present PANLINGUAL TRANSLATOR, a prototype Lemmatic MT system with high translation adequacy on 59% to 99% of sentences (average 84%) on a sample of 6 language pairs that Google Translate (GT...

ReCompounder is a working prototype for automatic translation of compounds by using the web as language model and a comprehensive bilingual dictionary as translation model. Evaluation shows this strategy is viable also with current search engine technologies. In addition to a detailed overview of the system, there is a discussion of the current capabilities of the search engines used (Google an...

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder–decoders and encode a s...