• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Poerner, Nina (2)
    • Schütze, Hinrich (2)
    • Cole, Jennifer (1)
    • Gurevych, Iryna (1)
    • Miyao, Yusuke (1)
    • Nowack, Dianne (1)
    • Pörner, Nina (1)
    • Pörner, Nina Mareike [Verfasser] (1)
    • Reichel, Uwe D. (1)
    • Roth, Benjamin (1)
    •   more
  • 
    Year
  • 
    Medium:
    
    • Online (3)
    • Print (1)
  • 
    Type:
    
    • Article (3)
    • Book (1)
  • 
    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 – 4 of 4 1 Combining contextualized and non-contextualized embeddings for domain adaptation and beyond Pörner, Nina Mareike [Verfasser]; Schütze, Hinrich [Akademischer Betreuer]. - München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2021 DNB Subject Category Language Show details 2 Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity ... Poerner, Nina; Waltinger, Ulli; Schütze, Hinrich. - : Association for Computational Linguistics, 2020 BASE Show details 3 Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement Miyao, Yusuke; Poerner, Nina; Roth, Benjamin; Gurevych, Iryna; Schütze, Hinrich. - : Ludwig-Maximilians-Universität München, 2018 Abstract: The behavior of deep neural networks (DNNs) is hard to understand. This makes it necessary to explore post hoc explanation methods. We conduct the first comprehensive evaluation of explanation methods for NLP. To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems. Both paradigms require no manual annotation and are therefore broadly applicable.We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP. We show empirically that LIMSSE, LRP and DeepLIFT are the mosteffective explanation methods and recommend them for explaining DNNs in NLP. Keyword: ddc:000; ddc:004; ddc:400; ddc:410 URL: http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-61866-4 https://epub.ub.uni-muenchen.de/61866/ https://doi.org/10.5282/ubm/epub.61866 https://epub.ub.uni-muenchen.de/61866/1/1801.06422.pdf BASE Hide details 4 Analysis and classification of cooperative and competitive dialogs Reichel, Uwe D.; Pörner, Nina; Nowack, Dianne. - 2015 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 1 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