paper-with-me

Papers

Massively Multilingual Neural Machine Translation

2019-02-28 · NAACL 2019 6 · Roee Aharoni, Melvin Johnson, Orhan Firat

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.

📄 PDF Abstract BibTeX arXiv:1903.00089

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

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

2019-09-01 · Aditya Siddhant, Melvin Johnson, Henry Tsai, Naveen Arivazhagan 외

The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation perf…

Cross-Lingual TransferMachine TranslationNMTTransfer Learning+1

Simple, Scalable Adaptation for Neural Machine Translation

2019-09-18 · IJCNLP 2019 11 · Ankur Bapna, Naveen Arivazhagan, Orhan Firat

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target …

Domain AdaptationMachine TranslationNMTTranslation

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

2020-04-24 · ACL 2020 6 · Biao Zhang, Philip Williams, Ivan Titov, Rico Sennrich

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve …

Machine TranslationNMTTranslation

An Analysis of Massively Multilingual Neural Machine Translation for Low-Resource Languages

2020-05-01 · LREC 2020 5 · Aaron Mueller, Garrett Nicolai, Arya D. McCarthy, Dylan Lewis 외

In this work, we explore massively multilingual low-resource neural machine translation. Using translations of the Bible (which have parallel structure across languages), we train models with up to 1,107 source languages…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationTranslation

SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages

2022-10-20 · Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard, Caroline Brun 외

In recent years, multilingual machine translation models have achieved promising performance on low-resource language pairs by sharing information between similar languages, thus enabling zero-shot translation. To overco…

Machine TranslationTranslation