Följ
Sarah Wiegreffe
Sarah Wiegreffe
Allen Institute for AI & University of Washington
Verifierad e-postadress på allenai.org - Startsida
Titel
Citeras av
Citeras av
År
Attention is not not Explanation
S Wiegreffe, Y Pinter
Empirical Methods in Natural Language Processing (EMNLP) 2019, 2019
9582019
Explainable Prediction of Medical Codes from Clinical Text
J Mullenbach, S Wiegreffe, J Duke, J Sun, J Eisenstein
North American Association for Computational Linguistics (NAACL) 2018, 2018
6012018
Self-refine: Iterative refinement with self-feedback
A Madaan, N Tandon, P Gupta, S Hallinan, L Gao, S Wiegreffe, U Alon, ...
Neural Information Processing Systems (NeurIPS) 2023, 2023
4122023
Learning to Faithfully Rationalize by Construction
S Jain, S Wiegreffe, Y Pinter, BC Wallace
Association for Computational Linguistics (ACL) 2020, 2020
1622020
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing
S Wiegreffe, A Marasovic
Thirty-fifth Conference on Neural Information Processing Systems Datasets …, 2021
161*2021
Measuring Association Between Labels and Free-Text Rationales
S Wiegreffe, A Marasovic, NA Smith
Empirical Methods in Natural Language Processing (EMNLP) 2021, 2020
1272020
Reframing Human-AI Collaboration for Generating Free-Text Explanations
S Wiegreffe, J Hessel, S Swayamdipta, M Riedl, Y Choi
NAACL 2022, 2021
1032021
Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning
X Peng, S Li, S Wiegreffe, M Riedl
Findings of EMNLP 2022, 2022
272022
Editing Common Sense in Transformers
A Gupta, D Mondal, AK Sheshadri, W Zhao, XL Li, S Wiegreffe, N Tandon
Empirical Methods in Natural Language Processing (EMNLP) 2023, 2023
16*2023
Clinical Concept Extraction for Document-Level Coding
S Wiegreffe, E Choi, S Yan, J Sun, J Eisenstein
Proceedings of the 18th BioNLP Workshop and Shared Task at ACL 2019, 261–272, 2019
142019
Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes
K Xie, S Wiegreffe, M Riedl
Findings of EMNLP 2022, 2022
102022
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
P Hase, M Bansal, P Clark, S Wiegreffe
arXiv preprint arXiv:2401.06751, 2024
12024
Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy
S Wiegreffe, M Finlayson, O Tafjord, P Clark, A Sabharwal
Empirical Methods in Natural Language Processing (EMNLP) 2023, 2023
12023
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
Y Elazar, B Paranjape, H Peng, S Wiegreffe, K Raghavi, V Srikumar, ...
arXiv preprint arXiv:2311.09605, 2023
12023
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
J Bastings, Y Belinkov, Y Elazar, D Hupkes, N Saphra, S Wiegreffe
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting …, 2022
12022
Interpreting Neural Networks for and with Natural Language
SA Wiegreffe
Georgia Institute of Technology, 2022
2022
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–16