Pith. sign in

REVIEW 5 cited by

Sockeye: A Toolkit for Neural Machine Translation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1712.05690 v2 pith:Y36RE322 submitted 2017-12-15 cs.CL cs.LGstat.ML

Felix Hieber , Tobias Domhan , Michael Denkowski , David Vilar , Artem Sokolov , Ann Clifton , Matt Post This is my paper · ORCID
classification cs.CLcs.LGstat.ML
keywords sockeyetoolkittrainingmachineneuraltranslationarchitecturesinference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We describe Sockeye (version 1.12), an open-source sequence-to-sequence toolkit for Neural Machine Translation (NMT). Sockeye is a production-ready framework for training and applying models as well as an experimental platform for researchers. Written in Python and built on MXNet, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural networks, self-attentional transformers, and fully convolutional networks. Sockeye also supports a wide range of optimizers, normalization and regularization techniques, and inference improvements from current NMT literature. Users can easily run standard training recipes, explore different model settings, and incorporate new ideas. In this paper, we highlight Sockeye's features and benchmark it against other NMT toolkits on two language arcs from the 2017 Conference on Machine Translation (WMT): English-German and Latvian-English. We report competitive BLEU scores across all three architectures, including an overall best score for Sockeye's transformer implementation. To facilitate further comparison, we release all system outputs and training scripts used in our experiments. The Sockeye toolkit is free software released under the Apache 2.0 license.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Discriminative Neural Model for Cross-Lingual Word Alignment

    cs.CL 2019-09 conditional novelty 6.0 of 10

    A discriminative alignment module, trained on 1.7K to 4.9K labeled sentence pairs and plugged into a Transformer MT model, outperforms FastAlign and attention baselines by 11 to 27 F1 points and improves projected NER.

  2. Encoders Help You Disambiguate Word Senses in Neural Machine Translation

    cs.CL 2019-08 conditional novelty 6.0 of 10

    Encoder hidden states in NMT encode far more word-sense disambiguation information than word embeddings, with higher layers and self-attention focusing on context contributing most.

  3. Real-Time Multilingual Sign Language Processing

    cs.CL 2024-12 conditional novelty 5.0 of 10

    A thesis argues that SignWriting should be the pivot representation for sign language translation and production, with published component results but no end-to-end proof that the pivot outperforms glosses.

  4. uniblock: Scoring and Filtering Corpus with Unicode Block Information

    cs.CL 2019-08 conditional novelty 5.0 of 10

    A Gaussian mixture model over normalized Unicode block counts can score and filter noisy text corpora without hand-written character rules.

  5. Problems with automating translation of movie/TV show subtitles

    cs.CL 2019-09 conditional novelty 4.0 of 10

    A catalogue of 27 subtitle translation failure modes, with measured frequencies of 16 error types for six language pairs, shows that current NMT engines still require post-processing.

Pith tools