• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Schütze, Hinrich (121)
    • The Pennsylvania State University CiteSeerX Archives (62)
    • Hinrich Schütze (56)
    • Ehlers, Klaas-Hinrich (51)
    • Dufter, Philipp (31)
    • Hudde, Hinrich (23)
    • Michael Walsh (11)
    • Zhao, Mengjie (11)
    • Roth, Klaus-Hinrich (10)
    • Hofmann, Valentin (9)
    •   more
  • 
    Year:
    
    • 2022 (5)
    • 2021 (26)
    • 2020 (30)
    • 2019 (20)
    • 2018 (19)
    • 2017 (10)
    • 2016 (5)
    • 2015 (9)
    • 2014 (4)
    • 2013 (9)
    •   more
  • 
    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 Page: 1 2 3 4 5...18 Hits 1 – 20 of 360 1 Graph Neural Networks for Multiparallel Word Alignment ... Imani, Ayyoob; Şenel, Lütfi Kerem; Sabet, Masoud Jalili. - : arXiv, 2022 BASE Show details 2 CaMEL: Case Marker Extraction without Labels ... Weissweiler, Leonie; Hofmann, Valentin; Sabet, Masoud Jalili. - : arXiv, 2022 BASE Show details 3 Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments ... Maronikolakis, Antonis; Wisiorek, Axel; Nann, Leah. - : arXiv, 2022 BASE Show details 4 Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization ... Karn, Sanjeev Kumar; Liu, Ning; Schuetze, Hinrich. - : arXiv, 2022 BASE Show details 5 Geographic Adaptation of Pretrained Language Models ... Hofmann, Valentin; Glavaš, Goran; Ljubešić, Nikola. - : arXiv, 2022 BASE Show details 6 Distributed representations for multilingual language processing Dufter, Philipp [Verfasser]; Schütze, Hinrich [Akademischer Betreuer]. - München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2021 DNB Subject Category Language Show details 7 Domain adaptation in Natural Language Processing Sedinkina, Marina [Verfasser]; Schütze, Hinrich [Akademischer Betreuer]. - München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2021 DNB Subject Category Language Show details 8 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 9 Graph Algorithms for Multiparallel Word Alignment Imani, Ayyoob; Sabet, Masoud,; Keremşenel, Lütfi... In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; The 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-03424044 ; The 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2021, Punta Cana, Dominica ; https://2021.emnlp.org/ (2021) BASE Show details 10 Static Embeddings as Efficient Knowledge Bases? ... Dufter, Philipp; Kassner, Nora; Schütze, Hinrich. - : arXiv, 2021 BASE Show details 11 Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models ... Senel, Lutfi Kerem; Schütze, Hinrich. - : arXiv, 2021 BASE Show details 12 Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words ... 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; ., Hinrich; Hofmann, Valentin. - : Underline Science Inc., 2021 BASE Show details 13 Discrete and Soft Prompting for Multilingual Models ... Zhao, Mengjie; Schütze, Hinrich. - : arXiv, 2021 BASE Show details 14 ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ... Imani, Ayyoob; Sabet, Masoud Jalili; Dufter, Philipp. - : arXiv, 2021 BASE Show details 15 Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models ... Kassner, Nora; Dufter, Philipp; Schütze, Hinrich. - : arXiv, 2021 BASE Show details 16 Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages ... Maronikolakis, Antonis; Dufter, Philipp; Schütze, Hinrich. - : arXiv, 2021 BASE Show details 17 Graph Algorithms for Multiparallel Word Alignment ... Imani, Ayyoob; Sabet, Masoud Jalili; Şenel, Lütfi Kerem. - : arXiv, 2021 BASE Show details 18 Locating Language-Specific Information in Contextualized Embeddings ... Liang, Sheng; Dufter, Philipp; Schütze, Hinrich. - : arXiv, 2021 BASE Show details 19 Dynamic Contextualized Word Embeddings ... 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; ., Hinrich; Hofmann, Valentin. - : Underline Science Inc., 2021 BASE Show details 20 Measuring and Improving Consistency in Pretrained Language Models ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Elazar, Yanai; Goldberg, Yoav; Hovy, Eduard; Kassner, Nora; Ravfogel, Shauli; Ravichander, Abhilasha; Schütze, Hinrich. - : Underline Science Inc., 2021 Abstract: Consistency of a model — that is, the invariance of its behavior under meaning preserving alternations in its input — is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge? To this end, we create PARAREL , a high-quality resource of cloze-style query English paraphrases. It contains a total of 328 paraphrases for 38 relations. Using PARAREL , we show that the consistency of all PLMs we experiment with is poor – though with high variance between relations. Our analysis of the representational spaces of PLMs suggests that they have a poor structure and are currently not suitable for representing knowledge robustly. Finally, we propose a method for improving model consistency and experimentally demonstrate its effectiveness. ... Keyword: Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Natural Language Processing URL: https://underline.io/lecture/38196-measuring-and-improving-consistency-in-pretrained-language-models https://dx.doi.org/10.48448/rb2w-8959 BASE Hide details Page: 1 2 3 4 5...18

Mobile view All Catalogues UB Frankfurt Linguistik 19 IDS Mannheim 21 OLC Linguistik 23 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 25 Institut für Empirische Sprachwissenschaft 1 Leibniz-Centre General Linguistics (ZAS) 6 Bibliographies BLLDB 55 BDSL 2 IDS Bibliografie zur deutschen Grammatik 3 IDS Bibliografie zur Gesprächsforschung 2 IDS Konnektoren im Deutschen 1 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 9 Linked Open Data catalogues Annohub 0 Online resources Link directory 1 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 218 Linguistik-Repository 0 IDS Publikationsserver 1 Online dissertations 2 Language Description Heritage 0