Title | ||
---|---|---|
Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension. |
Abstract | ||
---|---|---|
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 input with relation embedding from the graph of general knowledge ConceptNet (Speer et al., 2017). As a result, our system achieves 2nd place with 83.95% accuracy on the official test data. Code is publicly available at this https URL |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/s18-1120 | SemEval@NAACL-HLT |
DocType | Volume | Citations |
Conference | abs/1803.00191 | 5 |
PageRank | References | Authors |
0.45 | 14 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liang Wang | 1 | 1567 | 158.46 |
Meng Sun | 2 | 94 | 22.65 |
Wei Zhao | 3 | 81 | 19.49 |
Kewei Shen | 4 | 5 | 0.45 |
Jingming Liu | 5 | 5 | 0.45 |