Building end-to-end dialogue systems using generative hierarchical neural network models I Serban, A Sordoni, Y Bengio, A Courville, J Pineau Proceedings of the AAAI Conference on Artificial Intelligence 30 (1), 2016 | 1513* | 2016 |

A neural network approach to context-sensitive generation of conversational responses A Sordoni, M Galley, M Auli, C Brockett, Y Ji, M Mitchell, JY Nie, J Gao, ... arXiv preprint arXiv:1506.06714, 2015 | 812 | 2015 |

A hierarchical latent variable encoder-decoder model for generating dialogues I Serban, A Sordoni, R Lowe, L Charlin, J Pineau, A Courville, Y Bengio Proceedings of the AAAI Conference on Artificial Intelligence 31 (1), 2017 | 794 | 2017 |

Newsqa: A machine comprehension dataset A Trischler, T Wang, X Yuan, J Harris, A Sordoni, P Bachman, K Suleman arXiv preprint arXiv:1611.09830, 2016 | 426 | 2016 |

A hierarchical recurrent encoder-decoder for generative context-aware query suggestion A Sordoni, Y Bengio, H Vahabi, C Lioma, J Grue Simonsen, JY Nie Proceedings of the 24th ACM International on Conference on Information and …, 2015 | 416 | 2015 |

Augmented cyclegan: Learning many-to-many mappings from unpaired data A Almahairi, S Rajeshwar, A Sordoni, P Bachman, A Courville International Conference on Machine Learning, 195-204, 2018 | 250 | 2018 |

Ordered neurons: Integrating tree structures into recurrent neural networks Y Shen, S Tan, A Sordoni, A Courville arXiv preprint arXiv:1810.09536, 2018 | 174 | 2018 |

deltableu: A discriminative metric for generation tasks with intrinsically diverse targets M Galley, C Brockett, A Sordoni, Y Ji, M Auli, C Quirk, M Mitchell, J Gao, ... arXiv preprint arXiv:1506.06863, 2015 | 147 | 2015 |

Z-forcing: Training stochastic recurrent networks A Goyal, A Sordoni, MA Côté, NR Ke, Y Bengio arXiv preprint arXiv:1711.05411, 2017 | 116 | 2017 |

Machine comprehension by text-to-text neural question generation X Yuan, T Wang, C Gulcehre, A Sordoni, P Bachman, S Subramanian, ... arXiv preprint arXiv:1705.02012, 2017 | 116 | 2017 |

Learning algorithms for active learning P Bachman, A Sordoni, A Trischler international conference on machine learning, 301-310, 2017 | 114 | 2017 |

Iterative alternating neural attention for machine reading A Sordoni, P Bachman, A Trischler, Y Bengio arXiv preprint arXiv:1606.02245, 2016 | 107 | 2016 |

Natural language comprehension with the epireader A Trischler, Z Ye, X Yuan, K Suleman arXiv preprint arXiv:1606.02270, 2016 | 89 | 2016 |

An Empirical Study of Example Forgetting during Deep Neural Network Learning M Toneva, A Sordoni, R Tachet, A Trischler, Y Bengio, G Gordon International Conference on Learning Representations, 2019 | 84 | 2019 |

Modeling term dependencies with quantum language models for ir A Sordoni, JY Nie, Y Bengio Proceedings of the 36th international ACM SIGIR conference on Research and …, 2013 | 70 | 2013 |

Twin networks: Matching the future for sequence generation D Serdyuk, NR Ke, A Sordoni, A Trischler, C Pal, Y Bengio arXiv preprint arXiv:1708.06742, 2017 | 55* | 2017 |

Straight to the tree: Constituency parsing with neural syntactic distance Y Shen, Z Lin, AP Jacob, A Sordoni, A Courville, Y Bengio arXiv preprint arXiv:1806.04168, 2018 | 48 | 2018 |

Learning concept embeddings for query expansion by quantum entropy minimization A Sordoni, Y Bengio, JY Nie Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014 | 48 | 2014 |

Towards text generation with adversarially learned neural outlines S Subramanian, S Rajeswar, A Sordoni, A Trischler, A Courville, C Pal Proceedings of the 32nd International Conference on Neural Information …, 2018 | 30 | 2018 |

Counting to explore and generalize in text-based games X Yuan, MA Côté, A Sordoni, R Laroche, RT Combes, M Hausknecht, ... arXiv preprint arXiv:1806.11525, 2018 | 29 | 2018 |