Rico Sennrich

TL;DR: This work argues that the need to represent and propagate lexical features in each layer limits the model’s capacity for learning and representing other information relevant to the task and introduces gated shortcut connections between the embedding layer and each subsequent layer within the encoder and decoder to alleviate this bottleneck.

TL;DR: The authors introduce a new evaluation method based on an idiom-specific blacklist of literal translations, based on the insight that the occurrence of any blacklisted words in the translation output indicates a likely translation error.

TL;DR: This paper presented a contrastive evaluation suite for English-German MT that uses machine-generated text, as opposed to human-written references, for a good approximation of deployment-time decoding.

TL;DR: This article explored methods of decode-time integration of attention-based neural translation models with phrase-based statistical machine translation and achieved state-of-the-art performance for English-Russian news translation.

TL;DR: The first prototype of the SUMMA Platform is presented: an integrated platform for multilingual media monitoring that contains a rich suite of low-level and high-level natural language processing technologies.