paper-with-me

Papers

Rationalization for Explainable NLP: A Survey

2023-01-21 · Sai Gurrapu, Ajay Kulkarni, Lifu Huang, Ismini Lourentzou, Laura Freeman, Feras A. Batarseh

Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expense of model explainability. Black-box models make it difficult to understand the internals of a system and the process it takes to arrive at an output. Numerical (LIME, Shapley) and visualization (saliency heatmap) explainability techniques are helpful; however, they are insufficient because they require specialized knowledge. These factors led rationalization to emerge as a more accessible explainable technique in NLP. Rationalization justifies a model's output by providing a natural language explanation (rationale). Recent improvements in natural language generation have made rationalization an attractive technique because it is intuitive, human-comprehensible, and accessible to non-technical users. Since rationalization is a relatively new field, it is disorganized. As the first survey, rationalization literature in NLP from 2007-2022 is analyzed. This survey presents available methods, explainable evaluations, code, and datasets used across various NLP tasks that use rationalization. Further, a new subfield in Explainable AI (XAI), namely, Rational AI (RAI), is introduced to advance the current state of rationalization. A discussion on observed insights, challenges, and future directions is provided to point to promising research opportunities.

📄 PDF Abstract BibTeX arXiv:2301.08912

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable Artificial Intelligence (XAI)Question AnsweringSurveytext-classificationText ClassificationText Generation

Similar Papers 제목 키워드 기반

Adversarial Attack for Explanation Robustness of Rationalization Models

2024-08-20 · Yuankai Zhang, Lingxiao Kong, Haozhao Wang, Ruixuan Li 외

Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. H…

Adversarial AttackExplainable artificial intelligence

ExClaim: Explainable Neural Claim Verification Using Rationalization

2023-01-21 · Sai Gurrapu, Lifu Huang, Feras A. Batarseh

With the advent of deep learning, text generation language models have improved dramatically, with text at a similar level as human-written text. This can lead to rampant misinformation because content can now be created…

Claim VerificationDecision MakingExplainable Artificial Intelligence (XAI)Misinformation+1

Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation

2024-10-05 · Jing Yang, Anderson Rocha

Computational methods to aid journalists in the task often require adapting a model to specific domains and generating explanations. However, most automated fact-checking methods rely on three-class datasets, which do no…

Explanation GenerationFact CheckingFact VerificationMisinformation+2

Explainable Recommendation: A Survey and New Perspectives

2018-04-30 · Yongfeng Zhang, Xu Chen

Explainable recommendation attempts to develop models that generate not only high-quality recommendations but also intuitive explanations. The explanations may either be post-hoc or directly come from an explainable mode…

Explainable RecommendationPersuasivenessProduct RecommendationRecommendation Systems+1

How Human-Centered Explainable AI Interface Are Designed and Evaluated: A Systematic Survey

2024-03-21 · Thu Nguyen, Alessandro Canossa, Jichen Zhu

Despite its technological breakthroughs, eXplainable Artificial Intelligence (XAI) research has limited success in producing the {\em effective explanations} needed by users. In order to improve XAI systems' usability, p…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Survey