This paper presents the results of the WMT16 shared tasks, which included five machine translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three evaluation tasks (metrics, tuning, run-time estimation of MT quality), and an automatic post-editing task and bilingual document alignment task. This year, 102 MT systems from 24 institutions (plus 36 anonymized online s...

Speech-to-speech translation technology enables natural oral communication between different language speaking people. Many research projects have addressed speech-to-speech translation (S2ST) technology, such as ATR [1], VERBMOBIL [2], C-STAR [3], NESPOLE! [4], BABYLON [5], GALE [6], and EU-bridge [7]. The speechto-speech translation system is normally composed of automatic speech recognition ...

When multilingual communication through a speech-to-speech translation system is supported by multimodal features, e.g. pen-based gestures, the following issues arise concerning the nature of the supported communication: a) to what extend does multilingual communication differ from ‘ordinary’ monolingual communication with respect to the dialogue structure and the communicative strategies used ...

This paper describes the ITSVox speech-to-speech translation prototype currently under development at LATL in collaboration with IDIAP. The ITSVox project aims at a general, interactive, multimodal translation system with the following characterics : (i) it is not restricted to a particular subdomain, (ii) it can be used either as a fully automatic system or as an interactive system, (iii I it ...

The attention mechanism is an important part of the neural machine translation (NMT) where it was reported to produce richer source representation compared to fixed-length encoding sequence-to-sequence models. Recently, the effectiveness of attention has also been explored in the context of image captioning. In this work, we assess the feasibility of a multimodal attention mechanism that simult...

We present a novel neural machine translation (NMT) architecture associating visual and textual features for translation tasks with multiple modalities. Transformed global and regional visual features are concatenated with text to form attendable sequences which are dissipated over parallel long short-term memory (LSTM) threads to assist the encoder generating a representation for attention-bas...