Science Question Answering using Instructional Materials
Computation and Language
2016-04-06 v2 Artificial Intelligence
Information Retrieval
Machine Learning
Abstract
We provide a solution for elementary science test using instructional materials. We posit that there is a hidden structure that explains the correctness of an answer given the question and instructional materials and present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs and instructional materials), and uses what it learns to answer novel elementary science questions. Our evaluation shows that our framework outperforms several strong baselines.
Cite
@article{arxiv.1602.04375,
title = {Science Question Answering using Instructional Materials},
author = {Mrinmaya Sachan and Avinava Dubey and Eric P. Xing},
journal= {arXiv preprint arXiv:1602.04375},
year = {2016}
}
Comments
Corrected that the science QA dataset is NOT freely available