C
Chris Hokamp
Researcher at Dublin City University
Publications - 34
Citations - 1578
Chris Hokamp is an academic researcher from Dublin City University. The author has contributed to research in topics: Machine translation & Task (project management). The author has an hindex of 12, co-authored 33 publications receiving 1317 citations. Previous affiliations of Chris Hokamp include University of Sheffield & University of North Texas.
Papers
More filters
Proceedings ArticleDOI
Improving efficiency and accuracy in multilingual entity extraction
TL;DR: This paper discusses some implementation and data processing challenges encountered while developing a new multilingual version of DBpedia Spotlight that is faster, more accurate and easier to configure, and compares the solution to the previous system.
Proceedings ArticleDOI
Findings of the 2015 Workshop on Statistical Machine Translation
Ondřej Bojar,Rajen Chatterjee,Christian Federmann,Barry Haddow,Matthias Huck,Chris Hokamp,Philipp Koehn,Varvara Logacheva,Christof Monz,Matteo Negri,Matt Post,Carolina Scarton,Lucia Specia,Marco Turchi +13 more
TL;DR: The WMT15 shared task as discussed by the authors included a standard news translation task, a metrics task, tuning task, and a task for run-time estimation of machine translation quality, and an automatic post-editing task.
Posted Content
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search
Chris Hokamp,Qun Liu +1 more
TL;DR: Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, it can be used to achieve significant gains in performance in domain adaptation scenarios.
Proceedings ArticleDOI
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search
Chris Hokamp,Qun Liu +1 more
TL;DR: The authors extend beam search to allow the inclusion of pre-specified lexical constraints, such as phrases or words that must be present in the output sequence, which can be used to incorporate auxiliary knowledge into a model's output without requiring any modification of the parameters or training data.
Journal ArticleDOI
Pushing the Limits of Translation Quality Estimation
André F. T. Martins,Marcin Junczys-Dowmunt,Fabio Natanael Kepler,Ramón Fernandez Astudillo,Chris Hokamp,Roman Grundkiewicz +5 more
TL;DR: A new, carefully engineered, neural model is stacked into a rich feature-based word-level quality estimation system and the output of an automatic post-editing system is used as an extra feature, obtaining striking results on WMT16.