A
Adrià de Gispert
Researcher at Northeastern University
Publications - 67
Citations - 1633
Adrià de Gispert is an academic researcher from Northeastern University. The author has contributed to research in topics: Machine translation & Rule-based machine translation. The author has an hindex of 22, co-authored 62 publications receiving 1548 citations. Previous affiliations of Adrià de Gispert include University of Cambridge & Polytechnic University of Catalonia.
Papers
More filters
Journal ArticleDOI
N-gram-based Machine Translation
José B. Mariòo,Rafael E. Banchs,Josep Maria Crego,Adrià de Gispert,Patrik Lambert,José A. R. Fonollosa,Marta R. Costa-jussà +6 more
TL;DR: This article describes in detail an n-gram approach to statistical machine translation that consists of a log-linear combination of a translation model based on n- grams of bilingual units, which are referred to as tuples, along with four specific feature functions.
Journal ArticleDOI
Guidelines for Word Alignment Evaluation and Manual Alignment
TL;DR: Standard scoring metrics for full text alignment and explanations on how to use them better are reviewed, and it is shown that the ratio between ambiguous and unambiguous links in the reference has a great impact on scores measured with these metrics.
Journal ArticleDOI
Hierarchical phrase-based translation with weighted finite-state transducers and shallow-n grammars
TL;DR: HiFST, a lattice-based decoder for hierarchical phrase-based translation and alignment is described, finding that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search errors, better parameter optimization, and improved translation performance.
Proceedings ArticleDOI
An n-gram-based statistical machine translation decoder.
TL;DR: This paper describes MARIE, an Ngram-based statistical machine translation decoder implemented using a beam search strategy, with distortion (or reordering) capabilities, and reports translation accuracy results on three different translation tasks.
Proceedings ArticleDOI
Neural Machine Translation Decoding with Terminology Constraints
TL;DR: The authors describe an approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans, and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.