• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Elazar, Yanai (3)
    • Goldberg, Yoav (3)
    • Jacovi, Alon (3)
    • Ravfogel, Shauli (3)
    • Choi, Yejin (1)
    • Swayamdipta, Swabha (1)
    • The 2021 Conference on Empirical Methods in Natural Language Processing 2021 (1)
    • The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing 2021 (1)
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Hits 1 – 3 of 3 1 Contrastive Explanations for Model Interpretability ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Choi, Yejin; Elazar, Yanai. - : Underline Science Inc., 2021 BASE Show details 2 Amnesic Probing: Behavioral Explanation With Amnesic Counterfactuals ... The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing 2021; Elazar, Yanai; Goldberg, Yoav. - : Underline Science Inc., 2021 BASE Show details 3 Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals ... Elazar, Yanai; Ravfogel, Shauli; Jacovi, Alon; Goldberg, Yoav. - : arXiv, 2020 Abstract: A growing body of work makes use of probing to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, we point out the inability to infer behavioral conclusions from probing results and offer an alternative method that focuses on how the information is being used, rather than on what information is encoded. Our method, Amnesic Probing, follows the intuition that the utility of a property for a given task can be assessed by measuring the influence of a causal intervention that removes it from the representation. Equipped with this new analysis tool, we can ask questions that were not possible before, e.g. is part-of-speech information important for word prediction? We perform a series of analyses on BERT to answer these types of questions. Our findings demonstrate that conventional probing performance is not correlated to task importance, and we call for increased scrutiny of claims that ... : TACL journal. Initial title was: "When Bert Forgets How To POS: Amnesic Probing of Linguistic Properties and MLM Predictions" ... Keyword: Computation and Language cs.CL; FOS Computer and information sciences URL: https://arxiv.org/abs/2006.00995 https://dx.doi.org/10.48550/arxiv.2006.00995 BASE Hide details

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 3 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0