Pith. sign in

REVIEW 5 cited by

Massively Multilingual 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 1903.00089 v3 pith:JGX2LXY6 submitted 2019-02-28 cs.CL

Roee Aharoni , Melvin Johnson , Orhan Firat This is my paper · ORCID
classification cs.CL
keywords multilinguallanguagesmassivelytranslationmodelstrainingenglishexperiments
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Multilingual neural machine translation (NMT) enables training a single model that supports translation from multiple source languages into multiple target languages. In this paper, we push the limits of multilingual NMT in terms of number of languages being used. We perform extensive experiments in training massively multilingual NMT models, translating up to 102 languages to and from English within a single model. We explore different setups for training such models and analyze the trade-offs between translation quality and various modeling decisions. We report results on the publicly available TED talks multilingual corpus where we show that massively multilingual many-to-many models are effective in low resource settings, outperforming the previous state-of-the-art while supporting up to 59 languages. Our experiments on a large-scale dataset with 102 languages to and from English and up to one million examples per direction also show promising results, surpassing strong bilingual baselines and encouraging future work on massively multilingual NMT.

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. Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation

    cs.CL 2019-09 conditional novelty 6.0 of 10

    A massively multilingual NMT encoder beats multilingual BERT in zero-shot cross-lingual transfer on 4 of 5 NLP tasks, but loses badly on named entity recognition.

  2. Investigating Multilingual NMT Representations at Scale

    cs.CL 2019-09 conditional novelty 5.0 of 10

    SVCCA analysis of a 103-language translation model shows encoder representations cluster by linguistic family, diverge by target language, and high-resource or related languages are more robust to fine-tuning.

  3. Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

    cs.CL 2019-07 unverdicted novelty 5.0 of 10

    A single multilingual NMT model for 103 languages trained on 25B examples demonstrates transfer learning benefits for low-resource languages.

  4. Comparative analysis of subword tokenization approaches for Indian languages

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Across SMT and NMT models for 11 Indian languages, SentencePiece gives the highest BLEU for most language pairs, while BPE wins in the multilingual model.

  5. Understanding and Analyzing Model Robustness and Knowledge-Transfer in Multilingual Neural Machine Translation using TX-Ray

    cs.CL 2024-12 conditional novelty 4.0 of 10

    Sequential transfer with English-English pre-training yields a small BLEU gain for English-Spanish only, and neuron pruning consistently hurts low-resource NMT.

Pith tools