Translation Speed
Related Papers
Bilingual segmentation for phrasetable pruning in Statistical Machine Translation
Statistical machine translation systems have greatly improved in the last years. However, this boost in performance usu- ally comes at a high computational cost, yielding systems that are often not …...
Improved beam search with constrained softmax for NMT
We propose an improved beam search decoding algorithm with constrained softmax operations for neural machine translation (NMT). NMT is a newly emerging approach to predict the best translation by building …...
Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task
AbstractWe describe the joint submission of the University of Edinburgh and Charles University, Prague, to the Czech/English track in the WMT 2020 Shared Task on News Translation. Our fast and …...
Neural Machine Translation with Inflected Lexicon
AbstractThe paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which …...
Revisiting Locality Sensitive Hashing for Vocabulary Selection in Fast Neural Machine Translation
AbstractNeural machine translation models often contain large target vocabularies. The calculation of logits, softmax and beam search is computationally costly over so many classes. We investigate the use of locality …...