Results 11 to 20 of about 271,354 (322)
Cognitive rationalization in occupational fraud: structure exploration and scale development
Frontiers in Psychology, 2023 The structure and measurement of occupational fraud rationalization as one of the motivations for fraudulent behavior has been a major obstacle in theoretical research and practical problems.
Miao Yang, Yizao Chen
doaj +2 more sources
Behavioral and Brain Sciences, 2018 Abstract Rationalization occurs when a person has performed an action and then concocts the beliefs and desires that would have made it rational. Then, people often adjust their own beliefs and desires to match the concocted ones. While many studies demonstrate rationalization, and a few theories describe its underlying cognitive mechanisms, we have
Neil L Levy
openaire +5 more sources
Knowledge Graph Self-Supervised Rationalization for Recommendation [PDF]
Knowledge Discovery and Data Mining, 2023 In this paper, we introduce a new self-supervised rationalization method, called KGRec, for knowledge-aware recommender systems. To effectively identify informative knowledge connections, we propose an attentive knowledge rationalization mechanism that ...
Yuhao Yang +3 more
semanticscholar +1 more source
Rationalization for explainable NLP: a survey [PDF]
Frontiers Artif. Intell., 2023 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-
Sai Gurrapu +5 more
semanticscholar +1 more source
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models.
Marcos VinÃcius Treviso +3 more
semanticscholar +1 more source
Towards Trustworthy Explanation: On Causal Rationalization [PDF]
International Conference on Machine Learning, 2023 With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction.
Wenbo Zhang +4 more
semanticscholar +1 more source
Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint [PDF]
Knowledge Discovery and Data Mining, 2023 A self-explaining rationalization model is generally constructed by a cooperative game where a generator selects the most human-intelligible pieces from the input text as rationales, followed by a predictor that makes predictions based on the selected ...
Wei Liu +7 more
semanticscholar +1 more source
Enhancing the Rationale-Input Alignment for Self-explaining Rationalization [PDF]
IEEE International Conference on Data Engineering, 2023 Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions based on the ...
Wei Liu +6 more
semanticscholar +1 more source
Graph Rationalization with Environment-based Augmentations [PDF]
Knowledge Discovery and Data Mining, 2022 Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models. Rationale identification has improved the generalizability and interpretability of neural networks on vision and language data ...
Gang Liu +4 more
semanticscholar +1 more source
MGR: Multi-generator Based Rationalization [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization suffers from two
Wei Liu +6 more
semanticscholar +1 more source