Employing External Rich Knowledge for Machine Comprehension
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2929-2924.
Abstract
Recently proposed machine comprehension (MC) application is an effort to deal with natural language understanding problem. However, the small size of machine comprehension labeled data confines the application of deep neural networks architectures that have shown advantage in semantic inference tasks. Previous methods use a lot of NLP tools to extract linguistic features but only gain little improvement over simple baseline. In this paper, we build an attention-based recurrent neural network model, train it with the help of external knowledge which is semantically relevant to machine comprehension, and achieves a new state-of-art result.
@inproceedings{ijcai2016p416,
title = {Employing External Rich Knowledge for Machine Comprehension},
author = {Wang, Bingning and Guo, Shangmin and Liu, Kang and He, Shizhu and Zhao, Jun},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {2929--2924},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/416},
}
TY - CPAPER TI - Employing External Rich Knowledge for Machine Comprehension AU - Wang, Bingning AU - Guo, Shangmin AU - Liu, Kang AU - He, Shizhu AU - Zhao, Jun T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 2929 EP - 2924 UR - https://ijcai.org/proceedings/2016/416 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
