TY - GEN
T1 - Learning by Interpreting
AU - Tang, Xuting
AU - Khan, Abdul Rafae
AU - Wang, Shusen
AU - Xu, Jia
N1 - Publisher Copyright:
© 2022 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2022
Y1 - 2022
N2 - This paper introduces a novel way of enhancing NLP prediction accuracy by incorporating model interpretation insights. Conventional efforts often focus on balancing the trade-offs between accuracy and interpretability, for instance, sacrificing model performance to increase the explainability. Here, we take a unique approach and show that model interpretation can ultimately help improve NLP quality. Specifically, we employ our learned interpretability results using attention mechanisms, LIME, and SHAP to train our model. We demonstrate a significant increase in accuracy of up to +3.4 BLEU points on NMT and up to +4.8 points on GLUE tasks, verifying our hypothesis that it is possible to achieve better model learning by incorporating model interpretation knowledge.
AB - This paper introduces a novel way of enhancing NLP prediction accuracy by incorporating model interpretation insights. Conventional efforts often focus on balancing the trade-offs between accuracy and interpretability, for instance, sacrificing model performance to increase the explainability. Here, we take a unique approach and show that model interpretation can ultimately help improve NLP quality. Specifically, we employ our learned interpretability results using attention mechanisms, LIME, and SHAP to train our model. We demonstrate a significant increase in accuracy of up to +3.4 BLEU points on NMT and up to +4.8 points on GLUE tasks, verifying our hypothesis that it is possible to achieve better model learning by incorporating model interpretation knowledge.
UR - http://www.scopus.com/inward/record.url?scp=85137894743&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137894743&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137894743
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 4390
EP - 4396
BT - Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
A2 - De Raedt, Luc
A2 - De Raedt, Luc
T2 - 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
Y2 - 23 July 2022 through 29 July 2022
ER -