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 Johannes Welbl

Challenges in Detoxifying Language Models


Sep 15, 2021
Johannes Welbl, Amelia Glaese, Jonathan Uesato, Sumanth Dathathri, John Mellor, Lisa Anne Hendricks, Kirsty Anderson, Pushmeet Kohli, Ben Coppin, Po-Sen Huang

* 23 pages, 6 figures, published in Findings of EMNLP 2021 

  Access Paper or Ask Questions

Evaluating the Apperception Engine


Jul 09, 2020
Richard Evans, Jose Hernandez-Orallo, Johannes Welbl, Pushmeet Kohli, Marek Sergot

* arXiv admin note: substantial text overlap with arXiv:1910.02227 

  Access Paper or Ask Questions

Undersensitivity in Neural Reading Comprehension


Feb 15, 2020
Johannes Welbl, Pasquale Minervini, Max Bartolo, Pontus Stenetorp, Sebastian Riedel

* 15 pages, 4 figures 

  Access Paper or Ask Questions

Beat the AI: Investigating Adversarial Human Annotations for Reading Comprehension


Feb 02, 2020
Max Bartolo, Alastair Roberts, Johannes Welbl, Sebastian Riedel, Pontus Stenetorp

* 21 pages including appendices 

  Access Paper or Ask Questions

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation


Nov 08, 2019
Po-Sen Huang, Huan Zhang, Ray Jiang, Robert Stanforth, Johannes Welbl, Jack Rae, Vishal Maini, Dani Yogatama, Pushmeet Kohli


  Access Paper or Ask Questions

Making sense of sensory input


Oct 05, 2019
Richard Evans, Jose Hernandez-Orallo, Johannes Welbl, Pushmeet Kohli, Marek Sergot


  Access Paper or Ask Questions

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation


Sep 03, 2019
Po-Sen Huang, Robert Stanforth, Johannes Welbl, Chris Dyer, Dani Yogatama, Sven Gowal, Krishnamurthy Dvijotham, Pushmeet Kohli

* Accepted in EMNLP 2019 

  Access Paper or Ask Questions

Jack the Reader - A Machine Reading Framework


Jun 20, 2018
Dirk Weissenborn, Pasquale Minervini, Tim Dettmers, Isabelle Augenstein, Johannes Welbl, Tim Rocktäschel, Matko Bošnjak, Jeff Mitchell, Thomas Demeester, Pontus Stenetorp, Sebastian Riedel

* Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2018), System Demonstrations 

  Access Paper or Ask Questions

Constructing Datasets for Multi-hop Reading Comprehension Across Documents


Jun 11, 2018
Johannes Welbl, Pontus Stenetorp, Sebastian Riedel

* Transactions of the Association for Computational Linguistics (TACL), Vol 6 (2018), pages 287-302 
* This paper directly corresponds to the TACL version (https://transacl.org/ojs/index.php/tacl/article/view/1325) apart from minor changes in wording, additional footnotes, and appendices 

  Access Paper or Ask Questions

Neural Random Forests


Apr 03, 2018
GĂ©rard Biau, Erwan Scornet, Johannes Welbl


  Access Paper or Ask Questions

Knowledge Graph Completion via Complex Tensor Factorization


Nov 26, 2017
Théo Trouillon, Christopher R. Dance, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard

* 38 pages, accepted in JMLR. This is an extended version of the article "Complex embeddings for simple link prediction" (ICML 2016) 

  Access Paper or Ask Questions

Crowdsourcing Multiple Choice Science Questions


Jul 19, 2017
Johannes Welbl, Nelson F. Liu, Matt Gardner

* accepted for the Workshop on Noisy User-generated Text (W-NUT) 2017 

  Access Paper or Ask Questions

Frustratingly Short Attention Spans in Neural Language Modeling


Feb 15, 2017
Michał Daniluk, Tim Rocktäschel, Johannes Welbl, Sebastian Riedel

* Published as a conference paper at ICLR 2017 

  Access Paper or Ask Questions

Complex Embeddings for Simple Link Prediction


Jun 20, 2016
Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard

* 10+2 pages, accepted at ICML 2016 

  Access Paper or Ask Questions

A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion


Apr 20, 2016
Johannes Welbl, Guillaume Bouchard, Sebastian Riedel

* accepted for AKBC 2016 workshop, 6pages 

  Access Paper or Ask Questions