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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation


May 30, 2022
Verna Dankers, Christopher G. Lucas, Ivan Titov

* Published at ACL 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sparse Interventions in Language Models with Differentiable Masking


Dec 13, 2021
Nicola De Cao, Leon Schmid, Dieuwke Hupkes, Ivan Titov

* 12 pages, 4 figures, 6 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Opinion Summarizers by Selecting Informative Reviews


Sep 09, 2021
Arthur Bražinskas, Mirella Lapata, Ivan Titov

* EMNLP 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Highly Parallel Autoregressive Entity Linking with Discriminative Correction


Sep 08, 2021
Nicola De Cao, Wilker Aziz, Ivan Titov

* Accepted at EMNLP2021 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Code at https://github.com/nicola-decao/efficient-autoregressive-EL . 8 pages, 1 figure, 3 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT


Sep 03, 2021
Elena Voita, Rico Sennrich, Ivan Titov

* EMNLP 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Meta-Learning to Compositionally Generalize


Jun 29, 2021
Henry Conklin, Bailin Wang, Kenny Smith, Ivan Titov

* ACL2021 Camera Ready; fix a small typo 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Exploring Unsupervised Pretraining Objectives for Machine Translation


Jun 10, 2021
Christos Baziotis, Ivan Titov, Alexandra Birch, Barry Haddow

* Findings of ACL 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Structured Reordering for Modeling Latent Alignments in Sequence Transduction


Jun 08, 2021
Bailin Wang, Mirella Lapata, Ivan Titov

* 13 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>