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 Roland Fernandez

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

* NAACL 2021 (14 pages) 

  Access Paper or Ask Questions

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

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

  Access Paper or Ask Questions

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


  Access Paper or Ask Questions

A System for Real-Time Interactive Analysis of Deep Learning Training


Jan 07, 2020
Shital Shah, Roland Fernandez, Steven Drucker

* Accepted at ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS 2019). Code available as TensorWatch project at https://github.com/microsoft/tensorwatch 

  Access Paper or Ask Questions

Working Memory Graphs


Nov 17, 2019
Ricky Loynd, Roland Fernandez, Asli Celikyilmaz, Adith Swaminathan, Matthew Hausknecht

* 9 pages, 6 figures, 6 page appendix 

  Access Paper or Ask Questions

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving


Oct 15, 2019
Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao


  Access Paper or Ask Questions

Learning and analyzing vector encoding of symbolic representations


Mar 10, 2018
Roland Fernandez, Asli Celikyilmaz, Rishabh Singh, Paul Smolensky


  Access Paper or Ask Questions