Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2017

Abstract

Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans through crowdsourcing. SQuAD provides a challenging testbed for evaluating machine comprehension algorithms, partly because compared with previous datasets, in SQuAD the answers do not come from a small set of candidate answers and they have variable lengths. We propose an end-to-end neural architecture for the task. The architecture is based on match-LSTM, a model we proposed previously for textual entailment, and Pointer Net, a sequence-to-sequence model proposed by Vinyals et al.(2015) to constrain the output tokens to be from the input sequences. We propose two ways of using Pointer Net for our task. Our experiments show that both of our two models substantially outperform the best results obtained by Rajpurkar et al.(2016) using logistic regression and manually crafted features.

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

ICLR 2017: International Conference on Learning Representations, Toulon, France, April 24-26: Proceedings

First Page

1

Last Page

15

Publisher

ICLR

City or Country

Amherst, MA

Copyright Owner and License

Authors

Additional URL

https://openreview.net/forum?id=B1-q5Pqxl

Download

Share

COinS