Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

@article{Weston2015TowardsAQ,
  title={Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks},
  author={Jason Weston and Antoine Bordes and Sumit Chopra and Tomas Mikolov},
  journal={CoRR},
  year={2015},
  volume={abs/1502.05698}
}
One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent. To measure progress towards that goal, we argue for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering. Our tasks measure understanding in several ways: whether a system is able to answer questions via chaining facts, simple induction, deduction and many more. The tasks… CONTINUE READING
Highly Influential
This paper has highly influenced 59 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 548 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 184 times over the past 90 days. VIEW TWEETS

3 Figures & Tables

Topics

Statistics

01002002015201620172018
Citations per Year

549 Citations

Semantic Scholar estimates that this publication has 549 citations based on the available data.

See our FAQ for additional information.