Driven Decoding for machine translation (Vers un d\'ecodage guid\'e pour la traduction automatique) [in French]

Avanc\'ees dans le domaine de la transcription automatique par d\'ecodage guid\'e (Improvements on driven decoding system combination) [in French]

Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation

We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a…

Trainable Greedy Decoding for Neural Machine Translation

Recent research in neural machine translation has largely focused on two aspects; neural network architectures and end-to-end learning algorithms. The problem of decoding, however, has received relatively little attentio…

Ensemble Self-Training for Unsupervised Machine Translation

We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but diff…

Saliency-driven Word Alignment Interpretation for Neural Machine Translation

Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments. In this paper, we s…