Machine Translation

Machine Translation is an excellent example of how cutting-edge research and world-class infrastructure come together at Google. We focus our research efforts on developing statistical translation techniques that improve with more data and generalize well to new languages. Our large scale computing infrastructure allows us to rapidly experiment with new models trained on web-scale data to significantly improve translation quality. This research backs the translations served at translate.google.com, allowing our users to translate text, web pages and even speech. Deployed within a wide range of Google services like GMail, Books, Android and web search, Google Translate is a high-impact, research-driven product that bridges language barriers and makes it possible to explore the multilingual web in 90 languages. Exciting research challenges abound as we pursue human quality translation and develop machine translation systems for new languages.

Recent publications

All publications in this area

Non-Autoregressive Machine Translation with Latent Alignments

This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a simple CTC model can achieve state-of-the-art for single-step non-autoregressive machine translation, contrary to what prior work indicates. In addition, we adapt the Imputer model...

View details

Non-Autoregressive Machine Translation with Latent Alignments

Chitwan Saharia, Mohammad Norouzi, Saurabh Saxena, William Chan

EMNLP (2020)

Human-Paraphrased References Improve Neural Machine Translation

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al (2020). When used in place of original references, the paraphrased versions produce metric scores that correlate better with human judgment. This effect holds for a variety of different automatic metrics, and tends to favor natural...

View details

Human-Paraphrased References Improve Neural Machine Translation

Markus Freitag, George Foster, David Grangier, Colin Cherry

Proceedings of the Fifth Conference on Machine Translation (Volume 1: Research Papers) (2020)

Complete Multilingual Neural Machine Translation

Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). While direct data between two languages that are non-English is explicitly available at times, its use is not common. In this paper, we first take a step back and look at the commonly used...

View details

Complete Multilingual Neural Machine Translation

Markus Freitag, Orhan Firat

Proceedings of the Fifth Conference on Machine Translation (Volume 1: Research Papers) (2020)

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages

Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. "Low-resourced"-ness is a complex problem going beyond data availability and reflects systemic problems in society. In this paper, we focus on the task of Machine Translation (MT), that plays a crucial role for information accessibility and...

View details

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages

∀‎‎‏‏‎ ‎‏‏‎ ‎‏‏‎ ‎, Abdallah Bashir, Adewale Akinfaderin, Alp Öktem, Arshath Ramkilowan, Ayodele Olabiyi, Blessing Bassey, Blessing Sibanda, Bonaventure Dossou, Chris Emezue, Christopher Onyefuluchi, Daniel Whitenack, Elan van Biljon, Espoir Murhabazi, Ghollah Kioko, Goodness Duru, Hady Elsahar, Herman Kamper, Idris Abdulkadir Dangana, Ignatius Ezeani, Iroro Orife, Jade Abbott, Jamiil Toure Ali, Julia Kreutzer, Kathleen Siminyu, Kelechi Ogueji, Kevin Degila, Kolawole Tajudeen, Laura Jane Martinus, Lawrence Okegbemi, Masabata Mokgesi-Selinga, Mofetoluwa Adeyemi, Musie Meressa, Orevaoghene Ahia, Perez Ogayo, Ricky Macharm, Rubungo Andre Niyongabo, Sackey Freshia, Salomey Osei, Salomon Kabongo Kabenamualu, Shamsuddeen Muhammad, Solomon Oluwole Akinola, Taiwo Fagbohungbe, Timi Fasubaa, Tshinondiwa Matsila, Vukosi Marivate, Wilhelmina Nekoto, Wole Akin

Findings of the 2020 Conference on Empirical Methods in Natural Language Processing, Virtual (2020) (to appear)

Inference Strategies for Machine Translation with Conditional Masking

Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clear what the best inference strategy is. We formulate masked inference as a factorization of conditional probabilities of partial sequences, show that this does not harm...

View details

Inference Strategies for Machine Translation with Conditional Masking

Julia Kreutzer, George Foster, Colin Cherry

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (to appear)

Some of our teams

Google Brain Team

Join Us

Our researchers work across the world

Together, our research teams tackle tough problems.

Explore opportunities