TY - GEN
T1 - Exploring interpretability in event extraction
T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Student Research Workshop, SRW 2020
AU - Tang, Zheng
AU - Hahn-Powell, Gustave
AU - Surdeanu, Mihai
N1 - Funding Information:
This work was supported by the Defense Advanced Research Projects Agency (DARPA) under grant #W911NF1810014. Mihai Surdeanu and Gus Hahn-Powell declare a financial interest in lum.ai. This interest has been properly disclosed to the University of Arizona Institutional Review Committee and is managed in accordance with its conflict of interest policies.
Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - We propose an interpretable approach for event extraction that mitigates the tension between generalization and interpretability by jointly training for the two goals. Our approach uses an encoder-decoder architecture, which jointly trains a classifier for event extraction, and a rule decoder that generates syntactico-semantic rules that explain the decisions of the event classifier. We evaluate the proposed approach on three biomedical events and show that the decoder generates interpretable rules that serve as accurate explanations for the event classifier’s decisions, and, importantly, that the joint training generally improves the performance of the event classifier. Lastly, we show that our approach can be used for semi-supervised learning, and that its performance improves when trained on automatically-labeled data generated by a rule-based system.
AB - We propose an interpretable approach for event extraction that mitigates the tension between generalization and interpretability by jointly training for the two goals. Our approach uses an encoder-decoder architecture, which jointly trains a classifier for event extraction, and a rule decoder that generates syntactico-semantic rules that explain the decisions of the event classifier. We evaluate the proposed approach on three biomedical events and show that the decoder generates interpretable rules that serve as accurate explanations for the event classifier’s decisions, and, importantly, that the joint training generally improves the performance of the event classifier. Lastly, we show that our approach can be used for semi-supervised learning, and that its performance improves when trained on automatically-labeled data generated by a rule-based system.
UR - http://www.scopus.com/inward/record.url?scp=85117671624&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117671624&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85117671624
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 169
EP - 175
BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
PB - Association for Computational Linguistics (ACL)
Y2 - 5 July 2020 through 10 July 2020
ER -