Logic Traps in Evaluating Attribution Scores
Yiming Ju | Yuanzhe Zhang | Zhao Yang | Zhongtao Jiang | Kang Liu | Jun Zhao
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict.This goal is usually approached with attribution method, which assesses the influence of features on model predictions. As an explanation method, the evaluation criteria of attribution methods is how accurately it reflects the actual reasoning process of the model (faithfulness). Meanwhile, since the reasoning process of deep models is inaccessible, researchers design various evaluation methods to demonstrate their arguments.However, some crucial logic traps in these evaluation methods are ignored in most works, causing inaccurate evaluation and unfair comparison.This paper systematically reviews existing methods for evaluating attribution scores and summarizes the logic traps in these methods.We further conduct experiments to demonstrate the existence of each logic trap.Through both theoretical and experimental analysis, we hope to increase attention on the inaccurate evaluation of attribution scores. Moreover, with this paper, we suggest stopping focusing on improving performance under unreliable evaluation systems and starting efforts on reducing the impact of proposed logic traps.
Alignment Rationale for Natural Language Inference
Zhongtao Jiang | Yuanzhe Zhang | Zhao Yang | Jun Zhao | Kang Liu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors. Existing explanation methods usually pick prominent features such as words or phrases from the input text. However, for NLI, alignments among words or phrases are more enlightening clues to explain the model. To this end, this paper presents AREC, a post-hoc approach to generate alignment rationale explanations for co-attention based models in NLI. The explanation is based on feature selection, which keeps few but sufficient alignments while maintaining the same prediction of the target model. Experimental results show that our method is more faithful and human-readable compared with many existing approaches. We further study and re-evaluate three typical models through our explanation beyond accuracy, and propose a simple method that greatly improves the model robustness.