Learning by Interpreting

Xuting Tang; Abdul Rafae Khan; Shusen Wang; Jia Xu

IJCAI 2022poster0 citations

Learning by Interpreting

Xuting Tang, Abdul Rafae Khan, Shusen Wang, Jia Xu

Abstract

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.

Natural Language Processing: Interpretability and Analysis of Models for NLPMachine Learning: Explainable/Interpretable Machine LearningMachine Learning: Attention ModelsAI Ethics, Trust, Fairness: Explainability and Interpretability

BibTeX

@inproceedings{ijcai2022p609,
  title     = {Learning by Interpreting},
  author    = {Tang, Xuting and Khan, Abdul Rafae and Wang, Shusen and Xu, Jia},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {4390--4396},
  year      = {2022},
  month     = {7},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2022/609},
  url       = {https://doi.org/10.24963/ijcai.2022/609},
}