Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Aditya Barua

Aditya Barua
Alert button

Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation


May 25, 2022
Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, Noah Constant

Add code
Alert button

Figure 1 for Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
Figure 2 for Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
Figure 3 for Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
Figure 4 for Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ByT5: Towards a token-free future with pre-trained byte-to-byte models


May 28, 2021
Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel

Add code
Alert button

Figure 1 for ByT5: Towards a token-free future with pre-trained byte-to-byte models
Figure 2 for ByT5: Towards a token-free future with pre-trained byte-to-byte models
Figure 3 for ByT5: Towards a token-free future with pre-trained byte-to-byte models
Figure 4 for ByT5: Towards a token-free future with pre-trained byte-to-byte models

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


Oct 23, 2020
Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel

Add code
Alert button

Figure 1 for mT5: A massively multilingual pre-trained text-to-text transformer
Figure 2 for mT5: A massively multilingual pre-trained text-to-text transformer
Figure 3 for mT5: A massively multilingual pre-trained text-to-text transformer
Figure 4 for mT5: A massively multilingual pre-trained text-to-text transformer

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LAReQA: Language-agnostic answer retrieval from a multilingual pool


Apr 11, 2020
Uma Roy, Noah Constant, Rami Al-Rfou, Aditya Barua, Aaron Phillips, Yinfei Yang

Add code
Alert button

Figure 1 for LAReQA: Language-agnostic answer retrieval from a multilingual pool
Figure 2 for LAReQA: Language-agnostic answer retrieval from a multilingual pool
Figure 3 for LAReQA: Language-agnostic answer retrieval from a multilingual pool
Figure 4 for LAReQA: Language-agnostic answer retrieval from a multilingual pool

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email