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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages


Aug 11, 2022
Paul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, R. Thomas McCoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao, Paul Smolensky

Add code

* Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021) 
* Revised edition to 4th Workshop on Technologies for MT of Low Resource Languages 

   Access Paper or Ask Questions

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

Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems


May 02, 2022
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao

Add code

* 21 pages, 6 figures. For a general AI audience: to appear in AI Magazine. A more extensive presentation of this work is "Neurocompositional computing in human and machine intelligence: A tutorial", Microsoft Technical Report MSR-TR-2022-5; see https://www.microsoft.com/en-us/research/publication/neurocompositional-computing-in-human-and-machine-intelligence-a-tutorial/ 

   Access Paper or Ask Questions

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

How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN


Nov 18, 2021
R. Thomas McCoy, Paul Smolensky, Tal Linzen, Jianfeng Gao, Asli Celikyilmaz

Add code

* 10 pages, plus 39 pages of appendices 

   Access Paper or Ask Questions

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

Distributed neural encoding of binding to thematic roles


Oct 24, 2021
Matthias Lalisse, Paul Smolensky

Add code

* Originally presented as a poster MACSIM 8 (2019) 

   Access Paper or Ask Questions

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

Scalable knowledge base completion with superposition memories


Oct 24, 2021
Matthias Lalisse, Eric Rosen, Paul Smolensky

Add code


   Access Paper or Ask Questions

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

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization


Jun 02, 2021
Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao

Add code

* NAACL 2021 (14 pages) 

   Access Paper or Ask Questions

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

Compositional Processing Emerges in Neural Networks Solving Math Problems


May 19, 2021
Jacob Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, Nebojsa Jojic, Paul Smolensky, Jianfeng Gao

Add code

* 7 pages, 2 figures, Accepted to CogSci 2021 for poster presentation 

   Access Paper or Ask Questions

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

Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language


Nov 18, 2020
Hassan Akbari, Hamid Palangi, Jianwei Yang, Sudha Rao, Asli Celikyilmaz, Roland Fernandez, Paul Smolensky, Jianfeng Gao, Shih-Fu Chang

Add code


   Access Paper or Ask Questions

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

Universal linguistic inductive biases via meta-learning


Jun 29, 2020
R. Thomas McCoy, Erin Grant, Paul Smolensky, Thomas L. Griffiths, Tal Linzen

Add code

* To appear in the Proceedings of the 42nd Annual Conference of the Cognitive Science Society 

   Access Paper or Ask Questions

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

Discovering the Compositional Structure of Vector Representations with Role Learning Networks


Nov 17, 2019
Paul Soulos, Tom McCoy, Tal Linzen, Paul Smolensky

Add code


   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
>>