Unsupervised Machine Translation On Dravidian Languages

Koneru, Sai; Liu, Danni; Niehues, Jan

doi:10.48550/arxiv.2103.15877

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A major challenge in machine translation, particularly as the field shifts its focus to low-resource languages, is the lack of availability of evaluation benchmarks. Much recent work has focused on the creation of training corpora (Auguste Tapo et al, 2021;Ali et al, 2021;Adelani et al, 2021;Gezmu et al, 2021;Nyoni and Bassett, 2021;Chauhan et al, 2021) and development of models (Koneru et al, 2021;Nagoudi et al, 2021;Aulamo et al, 2021), but evaluation is critical to being able to assess and improve translation quality.…”

Section: Related Workmentioning

confidence: 99%

The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Goyal

Gao

Chaudhary

et al. 2022

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the Flores-101 evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional translators through a carefully controlled process. The resulting dataset enables better assessment of model quality on the long tail of low-resource languages, including the evaluation of many-to-many multilingual translation systems, as all translations are fully aligned. By publicly releasing such a high-quality and high-coverage dataset, we hope to foster progress in the machine translation community and beyond.

show abstract

Section: Related Workmentioning

confidence: 99%

The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Goyal

Gao

Chaudhary

et al. 2022

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

Alternative Input Signals Ease Transfer in Multilingual Machine Translation

Sun¹,

Fan²,

Cross³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages, particularly cases where higher-resourced languages can benefit lower-resourced ones. While training an MMT model, the supervision signals learned from one language pair can be transferred to the other via the tokens shared by multiple source languages. However, the transfer is inhibited when the token overlap among source languages is small, which manifests naturally when languages use different writing systems. In this paper, we tackle inhibited transfer by augmenting the training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. We test these signals on Indic and Turkic languages, two language families where the writing systems differ but languages still share common features. Our results indicate that a straightforward multisource self-ensemble -training a model on a mixture of various signals and ensembling the outputs of the same model fed with different signals during inference -outperforms strong ensemble baselines by 1.3 BLEU on both language families. Further, we find that incorporating alternative inputs via self-ensemble can be particularly effective in low-resource settings, leading to +5 BLEU when only 5% of the total training data is accessible. Finally, our analysis demonstrates that including alternative signals yields more consistency and translates named entities more accurately, which is crucial for increased factuality of automated systems.

show abstract

The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Goyal¹,

Gao²,

Chaudhary³

et al. 2021

Preprint

View full text Add to dashboard Cite

One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the FLORES-101 evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional translators through a carefully controlled process. The resulting dataset enables better assessment of model quality on the long tail of low-resource languages, including the evaluation of many-to-many multilingual translation systems, as all translations are multilingually aligned. By publicly releasing such a highquality and high-coverage dataset, we hope to foster progress in the machine translation community and beyond.

show abstract

Unsupervised Machine Translation On Dravidian Languages

Cited by 3 publications

References 13 publications

The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Alternative Input Signals Ease Transfer in Multilingual Machine Translation

The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Contact Info

Product

Resources

About