This paper describes our system for SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. We use Three-way Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment the input with relation embedding from the graph of general knowledge ConceptNet (Speer et al., 2017). As a result, our system achieves state-of-the-art performance with 83.95% accuracy on the official test data. Code is publicly available at https://github.com/intfloat/commonsense-rc
@article{arxiv.1803.00191,
title = {Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension},
author = {Liang Wang and Meng Sun and Wei Zhao and Kewei Shen and Jingming Liu},
journal= {arXiv preprint arXiv:1803.00191},
year = {2018}
}
Comments
5 pages, 1 figure, Accepted to International Workshop on Semantic Evaluation 2018