Pith. sign in

REVIEW 5 cited by

Beyond English-Centric Multilingual 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 2010.11125 v1 pith:SHFFVNHG submitted 2020-10-21 cs.CL cs.LG

Angela Fan , Shruti Bhosale , Holger Schwenk , Zhiyi Ma , Ahmed El-Kishky , Siddharth Goyal , Mandeep Baines , Onur Celebi
show 9 more authors
Guillaume Wenzek Vishrav Chaudhary Naman Goyal Tom Birch Vitaliy Liptchinsky Sergey Edunov Edouard Grave Michael Auli Armand Joulin
This is my paper · ORCID
classification cs.CLcs.LG
keywords translationdatamodeltrainingmultilingualworkcreatedirections
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing work in translation demonstrated the potential of massively multilingual machine translation by training a single model able to translate between any pair of languages. However, much of this work is English-Centric by training only on data which was translated from or to English. While this is supported by large sources of training data, it does not reflect translation needs worldwide. In this work, we create a true Many-to-Many multilingual translation model that can translate directly between any pair of 100 languages. We build and open source a training dataset that covers thousands of language directions with supervised data, created through large-scale mining. Then, we explore how to effectively increase model capacity through a combination of dense scaling and language-specific sparse parameters to create high quality models. Our focus on non-English-Centric models brings gains of more than 10 BLEU when directly translating between non-English directions while performing competitively to the best single systems of WMT. We open-source our scripts so that others may reproduce the data, evaluation, and final M2M-100 model.

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. OpenAlex reports about 469 citations worldwide. Full citation record

  1. Noisy-Channel Minimum Bayes Risk Decoding

    cs.LG 2026-07 conditional novelty 6.0 of 10

    MBR decoding is reformulated via a noisy-channel decomposition into four weighted probabilistic terms, revealing that channel importance is metric-specific and task-agnostic, and that reweighting can improve performance.

  2. VN-MTEB: Vietnamese Massive Text Embedding Benchmark

    cs.CL 2025-07 conditional novelty 6.0 of 10

    VN-MTEB is a new 41-dataset Vietnamese benchmark for text embeddings, built by machine-translating MTEB datasets with embedding-based and LLM-based quality filters.

  3. GeNRe: A French Gender-Neutral Rewriting System Using Collective Nouns

    cs.CL 2025-05 conditional novelty 6.0 of 10

    GeNRe is the first French gender-neutral rewriting system to replace masculine plural member nouns with collective nouns, reaching 3.81% WER with its rule-based version.

  4. THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A hierarchical routing method that combines predicted task labels with context-aware token routing improves BLEU and reduces activated experts in translation MoE models.

  5. GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Fine-tuning SeamlessM4T-v2 directly for end-to-end speech translation is competitive, and ASR-encoder initialization adds about 1 to 5 BLEU for languages unseen by the base model.

Pith tools