• Refine your search:
  • 
    Keyword:
    
    • Computational Linguistics (9)
    • Condensed Matter Physics (5)
    • Deep Learning (5)
    • Electromagnetism (5)
    • FOS Physical sciences (5)
    • Information and Knowledge Engineering (5)
    • Neural Network (5)
    • Semantics (5)
    • Machine Learning (3)
    • Machine Learning and Data Mining (3)
    •   more
  • 
    Creator / Publisher
  • 
    Year
  • 
    Medium:
    
    • Online (16)
  • 
    Type:
    
    • Article (16)
  • 
    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 – 16 of 16 1 Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality ... Thrush, Tristan; Jiang, Ryan; Bartolo, Max. - : arXiv, 2022 BASE Show details 2 ANLIzing the Adversarial Natural Language Inference Dataset Williams, Adina; Thrush, Tristan; Kiela, Douwe In: Proceedings of the Society for Computation in Linguistics (2022) BASE Show details 3 Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection ... 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; Kiela, Douwe; Talat, Zeerak. - : Underline Science Inc., 2021 BASE Show details 4 I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling ... 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; Bansal, Mohit; Kiela, Douwe. - : Underline Science Inc., 2021 BASE Show details 5 Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Bartolo, Max; Jia, Robin. - : Underline Science Inc., 2021 BASE Show details 6 Reservoir Transformers ... 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; Kiela, Douwe; Shen, Sheng. - : Underline Science Inc., 2021 BASE Show details 7 Gradient-based Adversarial Attacks against Text Transformers ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Guo, Chuan; Jégou, Hervé. - : Underline Science Inc., 2021 BASE Show details 8 DynaSent: A Dynamic Benchmark for Sentiment Analysis ... 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; Geiger, Atticus; Kiela, Douwe. - : Underline Science Inc., 2021 BASE Show details 9 On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study ... 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; Kaushik, Divyansh; Kiela, Douwe. - : Underline Science Inc., 2021 BASE Show details 10 Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Dieuwke; Jia, Robin; Kiela, Douwe; Pineau, Joelle; Sinha, Koustuv; Williams, Adina. - : Underline Science Inc., 2021 Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.230/ Abstract: A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines. In this paper, we propose a different explanation: MLMs succeed on downstream tasks almost entirely due to their ability to model higher-order word co-occurrence statistics. To demonstrate this, we pre-train MLMs on sentences with randomly shuffled word order, and show that these models still achieve high accuracy after fine-tuning on many downstream tasks -- including on tasks specifically designed to be challenging for models that ignore word order. Our models perform surprisingly well according to some parametric syntactic probes, indicating possible deficiencies in how we test representations for syntactic information. Overall, our results show that purely distributional information largely explains the success of ... Keyword: Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Natural Language Processing URL: https://dx.doi.org/10.48448/3r0a-fw32 https://underline.io/lecture/37423-masked-language-modeling-and-the-distributional-hypothesis-order-word-matters-pre-training-for-little BASE Hide details 11 Deep Artificial Neural Networks Reveal a Distributed Cortical Network Encoding Propositional Sentence-Level Meaning Anderson, Andrew James; Kiela, Douwe; Binder, Jeffrey R.... In: J Neurosci (2021) BASE Show details 12 Inferring concept hierarchies from text corpora via hyperbolic embeddings ... Le, Matthew; Roller, Stephen; Papaxanthos, Laetitia. - : ETH Zurich, 2019 BASE Show details 13 Inferring concept hierarchies from text corpora via hyperbolic embeddings Roller, Stephen; Le, Matthew; Papaxanthos, Laetitia... In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) (2019) BASE Show details 14 Visually Grounded and Textual Semantic Models Differentially Decode Brain Activity Associated with Concrete and Abstract Nouns ... Anderson, AJ; Kiela, Douwe; Clark, Stephen. - : Apollo - University of Cambridge Repository, 2017 BASE Show details 15 Adaptive Communication: Languages with More Non-Native Speakers Tend to Have Fewer Word Forms. Bentz, Christian; Verkerk, Annemarie; Kiela, Douwe. - : Public Library of Science (PLoS), 2015. : PLoS One, 2015 BASE Show details 16 Adaptive Communication: Languages with More Non-Native Speakers Tend to Have Fewer Word Forms Bentz, Christian; Verkerk, Annemarie; Kiela, Douwe. - : Public Library of Science, 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 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 16 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0