In this work, we propose two extensions of standard word lexicons in statistical machine translation: A discriminative word lexicon that uses sentence-level source information to predict the target words and a trigger-based lexicon model that extends IBM model 1 with a second trigger, allowing for a more fine-grained lexical choice of target words. The models capture dependencies that go beyond the scope of conventional SMT models such as phraseand language models. We show that the models improve translation quality by 1% in BLEU over a competitive baseline on a large-scale task. 1

In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show that deep belief networks have certain properties which are very interesting for transliteration and possibly also for translation and that a combination with conventional techniques leads to an improvement over both components on an Arabic-English transliteration task. 1

In this paper, we address the task of crosslingual semantic relatedness. We introduce a method that relies on the information extracted from Wikipedia, by exploiting the interlanguage links available between Wikipedia versions in multiple languages. Through experiments performed on several language pairs, we show that the method performs well, with a performance comparable to monolingual measures of relatedness. 1

We describe a freely available open source memory-based machine translation system, mbmt. Its translation model is a fast approximate memory-based classifier, trained to map trigrams of sourcelanguage words onto trigrams of target-language words. In a second decoding step, the predicted trigrams are rearranged according to their overlap, and candidate output sequences are ranked according to a memory-based language model. We report on the scaling abilities of the memory-based approach, observing fast training and testing times, and linear scaling behavior in speed and memory costs. �e system is released as an open source so�ware package, for which we provide a first reference guide. 1.