This paper presents our systems for the three Subtasks of SemEval Task4:Reading Comprehension of Abstract Meaning (ReCAM) We explain the algorithms used to learn our models and the process of tuning the algorithms and selecting the best model . Our models achieve the 4th rank on both official test sets of Subtask 1 and Subtask 2 with an accuracy of 87.9% and 92.8% . We further conduct comprehensive modelanalysis and observe interesting error cases, which may promote futureresearches .

Author(s) : Xin Xie, Xiangnan Chen, Xiang Chen, Yong Wang, Ningyu Zhang, Shumin Deng, Huajun Chen

Links : PDF - Abstract

Code :
Coursera

Keywords : task - semeval - reading - comprehension - abstract -

Leave a Reply

Your email address will not be published. Required fields are marked *