Marasović, Ana

Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks

Gururangan, S., Marasović, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Topic ModelingDomain Adaptation and Few-Shot Learning

Cited by 2,103

Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI

Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency

Explainable Artificial Intelligence (XAI)Ethics and Social Impacts of AI

Cited by 545

Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus

Dodge, J., Sap, M., Marasović, A., Agnew, W., Ilharco, G., Groeneveld, D., Mitchell, M., & Gardner, M. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Natural Language Processing TechniquesTopic Modeling

Cited by 306

Measuring Association Between Labels and Free-Text Rationales

Wiegreffe, S., Marasović, A., & Smith, N. A. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Explainable Artificial Intelligence (XAI)Topic Modeling

Cited by 119

Measuring Association Between Labels and Free-Text Rationales

Wiegreffe, S., Marasović, A., & Smith, N. A. (2020) · arXiv

Explainable Artificial Intelligence (XAI)Topic Modeling

Cited by 106