activity
20182021
most citedMultilingual Universal Sentence Encoder for Semantic Retrieval

67 citations · 93 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

15 papers · 1 filter

cs.CL20211 cited

Towards Universality in Multilingual Text Rewriting

Xavier Garcia, Noah Constant, Mandy Guo +1

In this work, we take the first steps towards building a universal rewriter: a model capable of rewriting text in any language to exhibit a wide variety of attributes, including st…

cs.CL20211 cited

nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?

Mihir Kale, Aditya Siddhant, Noah Constant +3

Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In…

cs.CL2021

The Power of Scale for Parameter-Efficient Prompt Tuning

Brian Lester, Rami Al-Rfou, Noah Constant

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unl…

cs.CL2021

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation

Sebastian Ruder, Noah Constant, Jan Botha +8

Machine learning has brought striking advances in multilingual natural language processing capabilities over the past year. For example, the latest techniques have improved the sta…

cs.CL2021

Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution

Xavier Garcia, Noah Constant, Ankur P. Parikh +1

We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual lea…

cs.CL2020

mT5: A massively multilingual pre-trained text-to-text transformer

Linting Xue, Noah Constant, Adam Roberts +5

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP t…