pith. sign in

Vocabulary Selection Strategies for Neural Machine Translation

· 2016 · cs.CL · arXiv 1610.00072

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
open full Pith review browse 1 citing papers arXiv PDF
abstract

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by restricting the output vocabulary to a subset of likely candidates given the source. In this paper we experiment with context and embedding-based selection methods and extend previous work by examining speed and accuracy trade-offs in more detail. We show that decoding time on CPUs can be reduced by up to 90% and training time by 25% on the WMT15 English-German and WMT16 English-Romanian tasks at the same or only negligible change in accuracy. This brings the time to decode with a state of the art neural translation system to just over 140 msec per sentence on a single CPU core for English-German.

fields

cs.CL 1

years

2019 1

verdicts

UNVERDICTED 1

representative citing papers

Sharing Attention Weights for Fast Transformer

cs.CL · 2019-06-26 · unverdicted · novelty 4.0

Sharing attention weights in adjacent Transformer layers yields 1.3X inference speedup with negligible BLEU loss on ten WMT and NIST tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Sharing Attention Weights for Fast Transformer cs.CL · 2019-06-26 · unverdicted · none · ref 9 · internal anchor

    Sharing attention weights in adjacent Transformer layers yields 1.3X inference speedup with negligible BLEU loss on ten WMT and NIST tasks.