TY - GEN
T1 - MULTI-ROLE EVENT ARGUMENT EXTRACTION AS MACHINE READING COMPREHENSION WITH ARGUMENT MATCH OPTIMIZATION
AU - Tao, Jingcong
AU - Pan, Youcheng
AU - Li, Xinyu
AU - Hu, Baotian
AU - Peng, Weihua
AU - Han, Cuiyun
AU - Wang, Xiaolong
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - Extracting arguments for the pre-defined roles is a crucial step for event extraction. Recently, there are some insightful works that view it as a machine reading comprehension problem and achieve significant progress. However, most of them need multi-turns to extract the arguments of each role independently, which ignores the relationships among roles in the same event. To alleviate this problem, we propose a novel Multi-Role Argument Extraction method named MRAE which can exploit the relationship of event roles by extracting all arguments for an event simultaneously. To force MRAE to locate more arguments accurately, we propose an argument match optimization loss based on the minimum risk training to exploit sentence-level F1 score. We conduct experiments on the widely used ACE2005 dataset. The experimental results demonstrate that MRAE outperforms the competitor methods by at least +1.2% F1 score on argument extraction, and also shows superiority on data scarce scenarios.
AB - Extracting arguments for the pre-defined roles is a crucial step for event extraction. Recently, there are some insightful works that view it as a machine reading comprehension problem and achieve significant progress. However, most of them need multi-turns to extract the arguments of each role independently, which ignores the relationships among roles in the same event. To alleviate this problem, we propose a novel Multi-Role Argument Extraction method named MRAE which can exploit the relationship of event roles by extracting all arguments for an event simultaneously. To force MRAE to locate more arguments accurately, we propose an argument match optimization loss based on the minimum risk training to exploit sentence-level F1 score. We conduct experiments on the widely used ACE2005 dataset. The experimental results demonstrate that MRAE outperforms the competitor methods by at least +1.2% F1 score on argument extraction, and also shows superiority on data scarce scenarios.
KW - data scarce
KW - machine reading comprehension
KW - minimum risk training
KW - multi-role event argument extraction
UR - https://www.scopus.com/pages/publications/85131258011
U2 - 10.1109/ICASSP43922.2022.9746923
DO - 10.1109/ICASSP43922.2022.9746923
M3 - 会议稿件
AN - SCOPUS:85131258011
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6347
EP - 6351
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Y2 - 22 May 2022 through 27 May 2022
ER -