Explain and Predict, and then Predict Again

Abstract

A desirable property of learning systems is to be both effective and interpretable. Towards this goal, recent models have been proposed that first generate an extractive explanation from the input text and then generate a prediction on just the explanation called explain-then-predict models. These models primarily consider the task input as a supervision signal in learning an extractive explanation and do not effectively integrate rationales data as an additional inductive bias to improve task performance. We propose a novel yet simple approach ExPred, that uses multi-task learning in the explanation generation phase effectively trading-off explanation and prediction losses. And then we use another prediction network on just the extracted explanations for optimizing the task performance. We conduct an extensive evaluation of our approach on three diverse language datasets -- fact verification, sentiment classification, and QA -- and find that we substantially outperform existing approaches.

Accepted in the WSDM 2021

References in corpus (9)

• SMOTE: Synthetic Minority Over-sampling Technique
• A Unified Approach to Interpreting Model Predictions
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Understanding Black-box Predictions via Influence Functions
• Visualizing and Understanding Recurrent Networks
• Attention is not Explanation
• Understanding Neural Networks through Representation Erasure
• An Evaluation of the Human-Interpretability of Explanation
• Fine-grained Sentiment Analysis with Faithful Attention

Cited by in corpus (10)

• End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models
• Rationalization for Explainable NLP: A Survey
• Evaluating Generative Ad Hoc Information Retrieval
• Towards Axiomatic Explanations for Neural Ranking Models
• FaxPlainAC: A Fact-Checking Tool Based on EXPLAINable Models with HumAn Correction in the Loop
• SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals
• ExClaim: Explainable Neural Claim Verification Using Rationalization
• BERTnesia: Investigating the capture and forgetting of knowledge in BERT
• Exploiting Sentence-Level Representations for Passage Ranking
• Learnt Sparsification for Interpretable Graph Neural Networks