• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher
  • 
    Year
  • 
    Medium
  • 
    Type:
    
    • Article (87)
    • Book (17)
    • Miscellaneous (16)
    • Journal (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 Page: 1 2 3 4 5...7 Hits 1 – 20 of 121 1 Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction ... Ryskina, Maria; Hovy, Eduard; Berg-Kirkpatrick, Taylor. - : arXiv, 2021 BASE Show details 2 Could you give me a hint? Generating inference graphs for defeasible reasoning ... Madaan, Aman; Rajagopal, Dheeraj; Tandon, Niket. - : arXiv, 2021 BASE Show details 3 Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction ... 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; Berg-Kirkpatrick, Taylor; Gormley, Matthew. - : Underline Science Inc., 2021 BASE Show details 4 Could you give me a hint ? Generating inference graphs for defeasible reasoning ... 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; Hovy, Eduard; Madaan, Aman. - : Underline Science Inc., 2021 BASE Show details 5 Investigating Robustness of Dialog Models to Popular Figurative Language Constructs ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berg-Kirkpatrick, Taylor; Gangal, Varun. - : Underline Science Inc., 2021 BASE Show details 6 Measuring and Improving Consistency in Pretrained Language Models ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Elazar, Yanai; Goldberg, Yoav. - : Underline Science Inc., 2021 BASE Show details 7 More Identifiable yet Equally Performant Transformers for Text Classification ... 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; Bhardwaj, Rishabh; Hovy, Eduard. - : Underline Science Inc., 2021 BASE Show details 8 Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation ... 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; Berg-Kirkpatrick, Taylor; Gangal, Varun Prashant. - : Underline Science Inc., 2021 BASE Show details 9 Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding ... 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; Hovy, Eduard; Kang, Dongyeop. - : Underline Science Inc., 2021 BASE Show details 10 SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Balachandran, Vidhisha; Hovy, Eduard. - : Underline Science Inc., 2021 BASE Show details 11 Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes ... Jo, Yohan; Bang, Seojin; Reed, Chris. - : arXiv, 2021 BASE Show details 12 StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer ... Lyu, Yiwei; Liang, Paul Pu; Pham, Hai. - : arXiv, 2021 BASE Show details 13 StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer ... NAACL 2021 2021; Hovy, Eduard; Liang, Paul Pu. - : Underline Science Inc., 2021 BASE Show details 14 Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes ... 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; Bang, Seojin; Hovy, Eduard. - : Underline Science Inc., 2021 BASE Show details 15 Extracting Implicitly Asserted Propositions in Argumentation ... Jo, Yohan; Visser, Jacky; Reed, Chris. - : arXiv, 2020 BASE Show details 16 Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? ... Ravichander, Abhilasha; Belinkov, Yonatan; Hovy, Eduard. - : arXiv, 2020 BASE Show details 17 Measuring Forecasting Skill from Text ... Zong, Shi; Ritter, Alan; Hovy, Eduard. - : arXiv, 2020 BASE Show details 18 On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT ... The 28th International Conference on Computational Linguistics 2020; Cheung, Jackie Chi Kit; Hovy, Eduard; Ravichander, Abhilasha; Suleman, Kaheer; Trischler, Adam. - : Underline Science Inc., 2020 Abstract: Contextualized word representations have become a driving force in NLP, motivating widespread interest in understanding their capabilities and the mechanisms by which they operate. Particularly intriguing is their ability to identify and encode conceptual abstractions. Past work has probed BERT representations (Devlin et al., 2019) for this competence, finding that BERT can correctly retrieve noun hypernyms in cloze tasks. In this work, we ask the question: do probing studies shed light on systematic knowledge in BERT representations? As a case study, we examine hypernymy knowledge encoded in BERT representations. In particular, we demonstrate through a simple consistency probe that the ability to correctly retrieve hypernyms in cloze tasks, as used in prior work, does not correspond to systematic knowledge in BERT. Our main conclusion is cautionary: even if BERT demonstrates high probing accuracy for a particular competence, it does not necessarily follow that BERT‘understands’ a concept, and it cannot be ... Keyword: Computer and Information Science; Information and Knowledge Engineering; Intelligent System; Natural Language Processing; Neural Network URL: https://dx.doi.org/10.48448/sa1q-9g43 https://underline.io/lecture/6663-on-the-systematicity-of-probing-contextualized-word-representations-the-case-of-hypernymy-in-bert BASE Hide details 19 On aligning OpenIE extractions with Knowledge Bases: A case study Gashteovski, Kiril; Gemulla, Rainer; Kotnis, Bhushan. - : Association for Computational Linguistics (ACL), 2020 BASE Show details 20 Discourse in Multimedia: A Case Study in Extracting Geometry Knowledge from Textbooks Sachan, Mrinmaya; Dubey, Avinava; Hovy, Eduard H.... In: Computational Linguistics, Vol 45, Iss 4, Pp 627-665 (2020) (2020) BASE Show details Page: 1 2 3 4 5...7

Mobile view All Catalogues UB Frankfurt Linguistik 8 IDS Mannheim 1 OLC Linguistik 8 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 2 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 27 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 4 IDS Konnektoren im Deutschen 1 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 7 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 72 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0