XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners

TL;DR

XAL introduces an explainable active learning framework that enhances low-resource text classification by integrating rationales and explanation scoring, leading to improved performance and interpretability.

Contribution

The paper proposes a novel XAL framework that combines explanation generation with active learning, addressing over-confidence and exploration issues in low-resource classification.

Findings

XAL outperforms 9 strong baselines across six datasets.

The method generates meaningful explanations for predictions.

Incorporating explanation scores improves data selection quality.

Abstract

Active learning (AL), which aims to construct an effective training set by iteratively curating the most formative unlabeled data for annotation, has been widely used in low-resource tasks. Most active learning techniques in classification rely on the model's uncertainty or disagreement to choose unlabeled data, suffering from the problem of over-confidence in superficial patterns and a lack of exploration. Inspired by the cognitive processes in which humans deduce and predict through causal information, we take an initial attempt towards integrating rationales into AL and propose a novel Explainable Active Learning framework (XAL) for low-resource text classification, which aims to encourage classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations. Specifically, besides using a pre-trained bi-directional encoder for classification, we employ a pre-trained uni-directional decoder to generate and score the explanation. We further facilitate the alignment of the model with human reasoning preference through a proposed ranking loss. During the selection of unlabeled data, the predicted uncertainty of the encoder and the explanation score of the decoder complement each other as the final metric to acquire informative data. Extensive experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines. Analysis indicates that the proposed method can generate corresponding explanations for its predictions.