TY - GEN
T1 - Four-way Bidirectional Attention for Multiple-choice Reading Comprehension
AU - Hu, Lei
AU - Zou, Dongsheng
AU - Guo, Xiwang
AU - Qi, Liang
AU - Tang, Ying
AU - Song, Haohao
AU - Yuan, Jieying
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - As one of the crucial tasks of natural language processing, machine reading comprehension has gained increased attention in recent years. In this paper, we propose a four-way bidirectional attention network for a multiple-choice reading comprehension task, where every question comes with a set of candidate options and only one correct answer. Current methods on such tasks usually judge options independently and ignore their relations. Thus, this work designs a four-way bidirectional attention strategy to formulate the interactions among the passage, questions and candidate options. In particular, the relations among options are well represented. This enables the model to leverage the option correlation information for inferring the final answer accurately. The experimental evaluations on the CosmosQA dataset demonstrate the competitive performance of our model, and confirm the effectiveness of the option comparison strategy.
AB - As one of the crucial tasks of natural language processing, machine reading comprehension has gained increased attention in recent years. In this paper, we propose a four-way bidirectional attention network for a multiple-choice reading comprehension task, where every question comes with a set of candidate options and only one correct answer. Current methods on such tasks usually judge options independently and ignore their relations. Thus, this work designs a four-way bidirectional attention strategy to formulate the interactions among the passage, questions and candidate options. In particular, the relations among options are well represented. This enables the model to leverage the option correlation information for inferring the final answer accurately. The experimental evaluations on the CosmosQA dataset demonstrate the competitive performance of our model, and confirm the effectiveness of the option comparison strategy.
UR - http://www.scopus.com/inward/record.url?scp=85124274003&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124274003&partnerID=8YFLogxK
U2 - 10.1109/SMC52423.2021.9658632
DO - 10.1109/SMC52423.2021.9658632
M3 - Conference contribution
AN - SCOPUS:85124274003
T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
SP - 238
EP - 243
BT - 2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021
Y2 - 17 October 2021 through 20 October 2021
ER -