Aligning Faithful Interpretations with their Social Attribution

Autor Alon Jacovi, Yoav Goldberg
Vydáno 2021-01-01

Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

Autor Yanai Elazar, Shauli Ravfogel, Alon Jacovi, Yoav Goldberg
Vydáno 2021-01-01

Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes

Autor Ofer Sabo, Yanai Elazar, Yoav Goldberg, Ido Dagan
Vydáno 2021-01-01

Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?

Autor William Merrill, Yoav Goldberg, Roy Schwartz, Noah A. Smith
Vydáno 2021-01-01

Measuring and Improving Consistency in Pretrained Language Models

Autor Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg
Vydáno 2021-01-01