Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension
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 data. Code is publicly available at https://github.com/intfloat/commonsense-rc.
READ FULL TEXT