• Refine your search:
  • 
    Keyword:
    
    • Computation and Language cs.CL (7)
    • FOS Computer and information sciences (7)
    • Artificial Intelligence cs.AI (1)
  • 
    Creator / Publisher:
    
    • Rudzicz, Frank (7)
    • Zhu, Zining (7)
    • Xu, Yang (3)
    • Li, Bai (2)
    • Thomas, Guillaume (2)
    • Abdalla, Mohamed (1)
    • Balagopalan, Aparna (1)
    • Ghassemi, Marzyeh (1)
    • Novikova, Jekaterina (1)
    • Pan, Chuer (1)
  • 
    Year
  • 
    Medium:
    
    • Online (7)
  • 
    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 – 7 of 7 1 Neural reality of argument structure constructions ... Li, Bai; Zhu, Zining; Thomas, Guillaume. - : arXiv, 2022 BASE Show details 2 Quantifying the Task-Specific Information in Text-Based Classifications ... Zhu, Zining; Balagopalan, Aparna; Ghassemi, Marzyeh. - : arXiv, 2021 BASE Show details 3 How is BERT surprised? Layerwise detection of linguistic anomalies ... Li, Bai; Zhu, Zining; Thomas, Guillaume; Xu, Yang; Rudzicz, Frank. - : arXiv, 2021 Abstract: Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density estimation at intermediate layers of three language models (BERT, RoBERTa, and XLNet), and evaluate our method on BLiMP, a grammaticality judgement benchmark. In lower layers, surprisal is highly correlated to low token frequency, but this correlation diminishes in upper layers. Next, we gather datasets of morphosyntactic, semantic, and commonsense anomalies from psycholinguistic studies; we find that the best performing model RoBERTa exhibits surprisal in earlier layers when the anomaly is morphosyntactic than when it is semantic, while commonsense anomalies do not exhibit surprisal at any intermediate layer. These results suggest that language models employ separate mechanisms to detect different types of linguistic anomalies. ... : ACL 2021 (Long Paper) ... Keyword: Computation and Language cs.CL; FOS Computer and information sciences URL: https://arxiv.org/abs/2105.07452 https://dx.doi.org/10.48550/arxiv.2105.07452 BASE Hide details 4 Semantic coordinates analysis reveals language changes in the AI field ... Zhu, Zining; Xu, Yang; Rudzicz, Frank. - : arXiv, 2020 BASE Show details 5 An information theoretic view on selecting linguistic probes ... Zhu, Zining; Rudzicz, Frank. - : arXiv, 2020 BASE Show details 6 Examining the rhetorical capacities of neural language models ... Zhu, Zining; Pan, Chuer; Abdalla, Mohamed. - : arXiv, 2020 BASE Show details 7 Detecting cognitive impairments by agreeing on interpretations of linguistic features ... Zhu, Zining; Novikova, Jekaterina; Rudzicz, Frank. - : arXiv, 2018 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