328 citations · 1.2k across the 12 of their papers we have counts for
15 papers
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Zhilin Yang, Peng Qi, Saizheng Zhang +4
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HotpotQA, a new dataset with 113k…
A Deep Reinforcement Learning Chatbot (Short Version)
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain +15
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capa…
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Saizheng Zhang, Emily Dinan, Jack Urbanek +3
Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the…
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
Zhilin Yang, Saizheng Zhang, Jack Urbanek +5
Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose…
A Deep Reinforcement Learning Chatbot
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain +15
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capa…
Neural Models for Key Phrase Detection and Question Generation
Sandeep Subramanian, Tong Wang, Xingdi Yuan +3
We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human…
Machine Comprehension by Text-to-Text Neural Question Generation
Xingdi Yuan, Tong Wang, Caglar Gulcehre +5
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervis…
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Ying Zhang, Mohammad Pezeshki, Philemon Brakel +3
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition…
Professor Forcing: A New Algorithm for Training Recurrent Networks
Alex Lamb, Anirudh Goyal, Ying Zhang +3
The Teacher Forcing algorithm trains recurrent networks by supplying observed sequence values as inputs during training and using the network's own one-step-ahead predictions to do…
On Multiplicative Integration with Recurrent Neural Networks
Yuhuai Wu, Saizheng Zhang, Ying Zhang +2
We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
Architectural Complexity Measures of Recurrent Neural Networks
Saizheng Zhang, Yuhuai Wu, Tong Che +4
In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theo…
STDP as presynaptic activity times rate of change of postsynaptic activity
Yoshua Bengio, Thomas Mesnard, Asja Fischer +2
We introduce a weight update formula that is expressed only in terms of firing rates and their derivatives and that results in changes consistent with those associated with spike-t…
GSNs : Generative Stochastic Networks
Guillaume Alain, Yoshua Bengio, Li Yao +4
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework is based…
Difference Target Propagation
Dong-Hyun Lee, Saizheng Zhang, Asja Fischer +1
Back-propagation has been the workhorse of recent successes of deep learning but it relies on infinitesimal effects (partial derivatives) in order to perform credit assignment. Thi…