activity
20192022
most citedLingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

184 citations · 204 across the 4 of their papers we have counts for

collaborators

10 papers

cs.CL202219 cited

Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning

Aditya Siddhant, Ankur Bapna, Orhan Firat +4

Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one s…

cs.CL2020

Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus

Isaac Caswell, Theresa Breiner, Daan van Esch +1

Large text corpora are increasingly important for a wide variety of Natural Language Processing (NLP) tasks, and automatic language identification (LangID) is a core technology nee…

cs.CL2020

BLEU might be Guilty but References are not Innocent

Markus Freitag, David Grangier, Isaac Caswell

The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice…

cs.CL2019

Translationese as a Language in "Multilingual" NMT

Parker Riley, Isaac Caswell, Markus Freitag +1

Machine translation has an undesirable propensity to produce "translationese" artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by t…

cs.CL2019

Investigating Multilingual NMT Representations at Scale

Sneha Reddy Kudugunta, Ankur Bapna, Isaac Caswell +2

Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly underst…

cs.CL2019

Learning a Multi-Domain Curriculum for Neural Machine Translation

Wei Wang, Ye Tian, Jiquan Ngiam +3

Most data selection research in machine translation focuses on improving a single domain. We perform data selection for multiple domains at once. This is achieved by carefully intr…