Explaining NLP Models via Minimal Contrastive Editing (MiCE)
Alexis Ross,Ana Marasovi,Matthew E. Peters +2 more
- pp 3840-3852
About:
This article is published in Meeting of the Association for Computational Linguistics.The article was published on 2021-08-01 and is currently open access. It has received 15 citations till now.read more
Citations
More filters
Posted Content
Contrastive Explanations for Model Interpretability
TL;DR: This article proposed a method to generate contrastive explanations for classification models by modifying the representation to disregard non-contrastive information, and modifying model behavior to only be based on contrastive reasoning.
Journal ArticleDOI
Post-hoc Interpretability for Neural NLP: A Survey
TL;DR: A survey of post-hoc interpretability methods for NLP NLP is presented in this article , which provides a categorization of interpretability techniques and how they communicate explanations to humans.
Journal ArticleDOI
A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned, and Perspectives
TL;DR: Recently, contrastive self-supervised training objectives have enabled successes in image representation pretraining by learning to contrast input-input pairs of augmented images as either similar or dissimilar as mentioned in this paper .
Proceedings ArticleDOI
Explainable Cross-Topic Stance Detection for Search Results
Tim Draws,Karthikeyan Natesan Ramamurthy,Ioana Baldini,Amit Dhurandhar,Inkit Padhi,Benjamin Timmermans,Nava Tintarev +6 more
TL;DR: In this article , the authors present a study into the feasibility of using current stance detection approaches to assist users in their web search on debated topics and investigate the quality of stance detection explanations created using different explainability methods and explanation visualization techniques.
Book ChapterDOI
Towards Generating Counterfactual Examples as Automatic Short Answer Feedback
TL;DR: In this paper , counterfactual explanation methods are used to generate feedback from short answer grading models automatically for short answer questions, and the results highlight the general weakness of neural networks to adversarial examples and recommend further research with more reliable grading models, for example by including external knowledge sources or training adversarially.
References
More filters
Posted Content
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yinhan Liu,Myle Ott,Naman Goyal,Jingfei Du,Mandar Joshi,Danqi Chen,Omer Levy,Michael Lewis,Luke Zettlemoyer,Veselin Stoyanov +9 more
TL;DR: It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.
MonographDOI
Causality: models, reasoning, and inference
TL;DR: The art and science of cause and effect have been studied in the social sciences for a long time as mentioned in this paper, see, e.g., the theory of inferred causation, causal diagrams and the identification of causal effects.
Proceedings ArticleDOI
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Proceedings Article
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
TL;DR: In this paper, the gradient of the class score with respect to the input image is computed to compute a class saliency map, which can be used for weakly supervised object segmentation using classification ConvNets.
Proceedings ArticleDOI
Transformers: State-of-the-Art Natural Language Processing
Thomas Wolf,Lysandre Debut,Victor Sanh,Julien Chaumond,Clement Delangue,Anthony Moi,Pierric Cistac,Clara Ma,Yacine Jernite,Julien Plu,Canwen Xu,Teven Le Scao,Sylvain Gugger,Mariama Drame,Quentin Lhoest,Alexander M. Rush +15 more
TL;DR: Transformers is an open-source library that consists of carefully engineered state-of-the art Transformer architectures under a unified API and a curated collection of pretrained models made by and available for the community.