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 Alessandro Sordoni

Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge

Dec 16, 2021
Ian Porada, Alessandro Sordoni, Jackie Chi Kit Cheung

  Access Paper or Ask Questions

Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU

Sep 17, 2021
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata Mukherjee

* To Appear in EMNLP 2021 

  Access Paper or Ask Questions

The Emergence of the Shape Bias Results from Communicative Efficiency

Sep 15, 2021
Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche

* Accepted at CoNLL 2021 

  Access Paper or Ask Questions

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Jun 25, 2021
Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Phil Bachman, Remi Tachet

* ICML 2021 

  Access Paper or Ask Questions

Understanding by Understanding Not: Modeling Negation in Language Models

May 07, 2021
Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R Devon Hjelm, Alessandro Sordoni, Aaron Courville

  Access Paper or Ask Questions

Linguistic dependencies and statistical dependence

Apr 18, 2021
Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du, Timothy J. O'Donnell

* 8 pages, plus references and appendices 

  Access Paper or Ask Questions

Recursive Top-Down Production for Sentence Generation with Latent Trees

Oct 09, 2020
Shawn Tan, Yikang Shen, Timothy J. O'Donnell, Alessandro Sordoni, Aaron Courville

  Access Paper or Ask Questions

Exploring and Predicting Transferability across NLP Tasks

May 02, 2020
Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer

* Preprint, 44 pages, 3 figures, 33 tables 

  Access Paper or Ask Questions

Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation

Mar 06, 2020
Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

* Presented at [email protected] 2020 

  Access Paper or Ask Questions

Robust Natural Language Inference Models with Example Forgetting

Nov 10, 2019
Yadollah Yaghoobzadeh, Remi Tachet, T. J. Hazen, Alessandro Sordoni

  Access Paper or Ask Questions

Ordered Memory

Nov 03, 2019
Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville

* Published in NeurIPS 2019 

  Access Paper or Ask Questions

Metalearned Neural Memory

Jul 23, 2019
Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler

* 24 pages 

  Access Paper or Ask Questions

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Dec 12, 2018
Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoffrey J. Gordon

  Access Paper or Ask Questions

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks

Oct 22, 2018
Yikang Shen, Shawn Tan, Alessandro Sordoni, Aaron Courville

* Under review as a conference paper 

  Access Paper or Ask Questions

VFunc: a Deep Generative Model for Functions

Jul 11, 2018
Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed

* To be presented at the ICML 2018 workshop on Prediction and Generative Modeling in Reinforcement Learning 

  Access Paper or Ask Questions

Counting to Explore and Generalize in Text-based Games

Jun 29, 2018
Xingdi Yuan, Marc-Alexandre C么t茅, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

  Access Paper or Ask Questions

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

Jun 18, 2018
Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

* ICML 2018 

  Access Paper or Ask Questions

Focused Hierarchical RNNs for Conditional Sequence Processing

Jun 12, 2018
Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal

* To appear at ICML 2018 

  Access Paper or Ask Questions

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

Jun 11, 2018
Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, Yoshua Bengio

* Published at ACL2018 

  Access Paper or Ask Questions

Twin Networks: Matching the Future for Sequence Generation

Feb 23, 2018
Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Adam Trischler, Chris Pal, Yoshua Bengio

* 12 pages, 3 figures, published at ICLR 2018 

  Access Paper or Ask Questions

Z-Forcing: Training Stochastic Recurrent Networks

Nov 16, 2017
Anirudh Goyal, Alessandro Sordoni, Marc-Alexandre C么t茅, Nan Rosemary Ke, Yoshua Bengio

* To appear in NIPS'17 

  Access Paper or Ask Questions

Learning Algorithms for Active Learning

Jul 31, 2017
Philip Bachman, Alessandro Sordoni, Adam Trischler

* Accepted for publication at ICML 2017 

  Access Paper or Ask Questions

Machine Comprehension by Text-to-Text Neural Question Generation

May 15, 2017
Xingdi Yuan, Tong Wang, Caglar Gulcehre, Alessandro Sordoni, Philip Bachman, Sandeep Subramanian, Saizheng Zhang, Adam Trischler

  Access Paper or Ask Questions

NewsQA: A Machine Comprehension Dataset

Feb 07, 2017
Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman

  Access Paper or Ask Questions

Towards Information-Seeking Agents

Dec 08, 2016
Philip Bachman, Alessandro Sordoni, Adam Trischler

* Under review for ICLR 2017 

  Access Paper or Ask Questions

Iterative Alternating Neural Attention for Machine Reading

Nov 09, 2016
Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio

  Access Paper or Ask Questions

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Jun 14, 2016
Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, Yoshua Bengio

* 15 pages, 5 tables, 4 figures 

  Access Paper or Ask Questions

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

Apr 06, 2016
Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, Joelle Pineau

* 8 pages with references; Published in AAAI 2016 (Special Track on Cognitive Systems) 

  Access Paper or Ask Questions