• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Berant, Jonathan (7)
    • The 2021 Conference on Empirical Methods in Natural Language Processing 2021 (7)
    • Geva, Mor (2)
    • Gupta, Ankit (2)
    • ., Shaya (1)
    • Ben-Arie, Aviv (1)
    • Bogin, Ben (1)
    • Ciprut, David (1)
    • Dar, Guy (1)
    • Gardner, Matt (1)
    •   more
  • 
    Year:
    
    • 2021 (7)
  • 
    Medium:
    
    • Online (7)
  • 
    Type
  • 
    BLLDB-Access:
    • free (7)
    • subject to license (0)

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 – 7 of 7 1 Value-aware Approximate Attention ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berant, Jonathan; Gupta, Ankit. - : Underline Science Inc., 2021 Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.753/ Abstract: Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. However, all approximations thus far have ignored the contribution of the value vectors to the quality of approximation. In this work, we argue that research efforts should be directed towards approximating the true output of the attention sub-layer, which includes the value vectors. We propose a valueaware objective, and show theoretically and empirically that an optimal approximation of a value-aware objective substantially outperforms an optimal approximation that ignores values, in the context of language modeling. Moreover, we show that the choice of kernel function for computing attention similarity can substantially affect the quality of sparse approximations, where kernel functions that are less skewed are more affected by the value vectors. ... Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing URL: https://underline.io/lecture/37465-value-aware-approximate-attention https://dx.doi.org/10.48448/tfks-ze53 BASE Hide details 2 Memory-efficient Transformers via Top-k Attention ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Shaya; Berant, Jonathan. - : Underline Science Inc., 2021 BASE Show details 3 Achieving Model Robustness through Discrete Adversarial Training ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berant, Jonathan; Ivgi, Maor. - : Underline Science Inc., 2021 BASE Show details 4 COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berant, Jonathan; Bogin, Ben. - : Underline Science Inc., 2021 BASE Show details 5 Transformer Feed-Forward Layers Are Key-Value Memories ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berant, Jonathan; Geva, Mor. - : Underline Science Inc., 2021 BASE Show details 6 What's in Your Head? Emergent Behaviour in Multi-Task Transformer Models ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Ben-Arie, Aviv; Berant, Jonathan. - : Underline Science Inc., 2021 BASE Show details 7 Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berant, Jonathan; Herzig, Jonathan. - : Underline Science Inc., 2021 BASE Show 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 7 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0