R
Rico Sennrich
Researcher at University of Zurich
Publications - 200
Citations - 18997
Rico Sennrich is an academic researcher from University of Zurich. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 48, co-authored 185 publications receiving 14563 citations. Previous affiliations of Rico Sennrich include University of Edinburgh.
Papers
More filters
TraMOOC - Translation for Massive Open Online Courses: Recent Developments in Machine Translation
Rico Sennrich,Antonio Valerio Miceli Barone,Joss Moorkens,Sheila Castilho,Andy Way,Federico Gaspari,Valia Kordoni,Markus Egg,Maja Popović,Yota Georgakopoulou,Maria Gialama,Menno van Zaanen +11 more
TL;DR: A comparative human evaluation of phrase-based SMT and NMT for four language pairs to compare educational domain output from both systems using a variety of metrics shows a preference for NMT in side-byside ranking for all language pairs, texts, and segment lengths.
Proceedings ArticleDOI
Beyond Sentence-Level End-to-End Speech Translation: Context Helps
TL;DR: The authors proposed a concatenation-based context-aware end-to-end speech translation model with adaptive feature selection on speech encodings for computational efficiency, which achieves better translation quality compared to sentence-level ST.
Proceedings Article
How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?
Chantal Amrhein,Rico Sennrich +1 more
TL;DR: The authors designed a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting, and compared how well machine translation models trained on subword-and character-level can translate these morphology phenomena.
Promoting Flexible Translations in Statistical Machine Translation
TL;DR: It is argued that flexible phrase pairs should be preferred over inflexible ones, and experiments with phrase-based and hierarchical translation models in which performance gains of up to 0.9 BLEU points are presented.