Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification

Yang, Linyi; Kenny, Eoin M.; Ng, Tin Lok James; Yang, Yi; Smyth, Barry; Dong, Ruihai

doi:10.18653/v1/2020.coling-main.541

Cited by 37 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Russell et al [47] propose a mixed integer programming based approach to address the difficulty with generating sensible explanations regarding categorical features. In addition to generic models, counterfactual explanations are also designed in applications like Computer Vision [9,20,27], Natural Language Processing [61,64], and Graph Neural Networks [65,66].…”

Section: Counterfactual Machine Learningmentioning

confidence: 99%

Counterfactually Evaluating Explanations in Recommender Systems

Yao¹,

Wang²,

Li³

2022

Preprint

View full text Add to dashboard Cite

Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a significant challenge for researchers and practitioners. Prior work mainly conducts human study to evaluate explanation quality, which is usually expensive, time-consuming, and prone to human bias. In this paper, we propose an offline evaluation method that can be computed without human involvement. To evaluate an explanation, our method quantifies its counterfactual impact on the recommendation. To validate the effectiveness of our method, we carry out an online user study. We show that, compared to conventional methods, our method can produce evaluation scores more correlated with the real human judgments, and therefore can serve as a better proxy for human evaluation. In addition, we show that explanations with high evaluation scores are considered better by humans. Our findings highlight the promising direction of using the counterfactual approach as one possible way to evaluate recommendation explanations.

show abstract

Section: Counterfactual Machine Learningmentioning

confidence: 99%

Counterfactually Evaluating Explanations in Recommender Systems

Yao¹,

Wang²,

Li³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Jacovi and Goldberg (2020) define contrastive highlights, which are determined by the inclusion of contrastive features; in contrast, our contrastive edits specify how to edit (vs. whether to include) features and can insert new text. 13 Li et al (2020a) generate counterfactuals using linguistically-informed transformations (LIT), and Yang et al (2020) generate counterfactuals for binary financial text classification using grammatically plausible single-word edits (REP-SCD). Because both methods rely on manually curated, task-specific rules, they cannot be easily extended to tasks without predefined label spaces, such as RACE.…”

Section: Related Workmentioning

confidence: 99%

Explaining NLP Models via Minimal Contrastive Editing (MiCE)

Ross¹,

Marasovi²,

Peters³

2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Humans have been shown to give contrastive explanations, which explain why an observed event happened rather than some other counterfactual event (the contrast case).Despite the influential role that contrastivity plays in how humans explain, this property is largely missing from current methods for explaining NLP models. We present MIN-IMAL CONTRASTIVE EDITING (MICE), a method for producing contrastive explanations of model predictions in the form of edits to inputs that change model outputs to the contrast case. Our experiments across three tasks-binary sentiment classification, topic classification, and multiple-choice question answering-show that MICE is able to produce edits that are not only contrastive, but also minimal and fluent, consistent with human contrastive edits. We demonstrate how MICE edits can be used for two use cases in NLP system development-debugging incorrect model outputs and uncovering dataset artifacts-and thereby illustrate that producing contrastive explanations is a promising research direction for model interpretability.

show abstract

“…This has been explored more in the field of CV Kenny and Keane, 2021), but investigated less in NLP. Recent work (Jacovi and Goldberg, 2020) highlight explanations of a given causal format, and Yang et al (2020a) generate counterfactuals for explaining the prediction of financial text classification. We propose a similar but different research question, that is, whether the automatically generated counterfactual can be used for data augmentation to build more robust models, which has not been considered by the previous methods in XAI (Pedreschi et al, 2019;Slack et al, 2020b;Yang et al, 2020b;Ding et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis

Yang¹,

Li²,

Cunningham³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data. Such issues come to be manifest in performance problems when faced with out-ofdistribution data in the field. One recent solution has been to use counterfactually augmented datasets in order to reduce any reliance on spurious patterns that may exist in the original data. Producing high-quality augmented data can be costly and time-consuming as it usually needs to involve human feedback and crowdsourcing efforts. In this work, we propose an alternative by describing and evaluating an approach to automatically generating counterfactual data for the purpose of data augmentation and explanation. A comprehensive evaluation on several different datasets and using a variety of state-of-the-art benchmarks demonstrate how our approach can achieve significant improvements in model performance when compared to models training on the original data and even when compared to models trained with the benefit of human-generated augmented data.

show abstract

Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification

Cited by 37 publications

References 20 publications

Counterfactually Evaluating Explanations in Recommender Systems

Counterfactually Evaluating Explanations in Recommender Systems

Explaining NLP Models via Minimal Contrastive Editing (MiCE)

Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis

Contact Info

Product

Resources

About