Cite Score
8
AI summary
This paper introduces dialog-based language learning using the bAbI dataset and large-scale question answering from the MovieQA dataset. It evaluates baseline strategies and introduces a novel model incorporating predictive lookahead, achieving correct question answering without reward-based supervision.
Main Contributions
Abstract
A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of [30] and large-scale question answering from [4]. We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.
Citation Graph
References [32]
R. Williams - 1992
11 papers in library cite
K. Xu, Jimmy Lei Ba, R. Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, R. Zemel, Yoshua Bengio - 2015
12 papers in library cite
S. Sukhbaatar, A. Szlam, Jason Weston, Rob Fergus - 2015
18 papers in library cite
Jason Weston, S. Chopra, Antoine Bordes - 2015
18 papers in library cite
Jason Weston, Antoine Bordes, S. Chopra, Tomas Mikolov - 2015
11 papers in library cite
F. Hill, Antoine Bordes, S. Chopra, Jason Weston - 2015
14 papers in library cite
Marc'aurelio Ranzato, S. Chopra, Michael Auli, Wojciech Zaremba - 2015
6 papers in library cite
A. Sordoni, M. Galley, Michael Auli, Chris Brockett, Yangfeng Ji, M. Mitchell, J. Y. Nie, Jianfeng Gao, B. Dolan - 2015
4 papers in library cite
Antoine Bordes, Nicolas Usunier, S. Chopra, Jason Weston - 2015
5 papers in library cite
K. Narasimhan, T. Kulkarni, R. Barzilay - 2015
2 papers in library cite
J. Dodge, A. Gane, X. Zhang, Antoine Bordes, S. Chopra, A. Miller, A. Szlam, Jason Weston - 2015
4 papers in library cite
G. Kuhlmann, P. Stone, R. Mooney, J. Shavlik - 2004
2 papers in library cite
Tomas Mikolov, Armand Joulin, M. Baroni - 2015
1 paper in library cites
J. Schatzmann, K. Weilhammer, M. Stuttle, S. Young - 2006
1 paper in library cites
J. Oh, X. Guo, Honglak Lee, R. L. Lewis, Shivalika Singh - 2015
1 paper in library cites
I. Lenz, R. Knepper, A. Saxena - 2015
1 paper in library cites
J. Clarke, D. Goldwasser, M. W. Chang, Dan Roth - 2010
1 paper in library cites
P. K. Kuhl - 2004
1 paper in library cites
G. Wayne, L. Abbott - 2014
1 paper in library cites
B. C. Stadie, Sergey Levine, P. Abbeel - 2015
1 paper in library cites
M. G. Werts, M. Wolery, A. Holcombe, D. L. Gast - 1995
1 paper in library cites
M. A. Bassiri - 2011
1 paper in library cites
D. Goldwasser, Dan Roth - 2014
1 paper in library cites
B. Hixon, Peter Clark, Hananneh Hajishirzi - 2015
1 paper in library cites
A. S. Latham - 1997
1 paper in library cites
Jürgen Schmidhuber, R. Huber - 1991
1 paper in library cites
S. Sukhbaatar, A. Szlam, Gabriel Synnaeve, S. Chintala, Rob Fergus - 2015
1 paper in library cites
G. F. Marcus - 1993
1 paper in library cites
A. Pappu, Alex Rudnicky - 2013
1 paper in library cites
V. Rieser, O. Lemon - 2011
1 paper in library cites
P. H. Su, D. Vandyke, M. Gasic, N. Mrksic, T. H. Wen, S. Young - 2015
1 paper in library cites
R. Higgins, P. Hartley, A. Skelton - 2002
1 paper in library cites
Cited by
1
papers in your library
Cites
11
papers in your library
Read
on October 31, 2025
Your review
Tags
Paper Aliases
No aliases