• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access:
    • free (20.397)
    • subject to license (447)

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...18 19 20 21 22 23 24 25 26...1.020 Hits 421 – 440 of 20.397 421 How to Train BERT with an Academic Budget ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Berchansky, Moshe; Izsak, Peter. - : Underline Science Inc., 2021 BASE Show details 422 Improving Span Representation for Domain-adapted Coreference Resolution ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Field, Anjalie; Gandhi, Nupoor. - : Underline Science Inc., 2021 BASE Show details 423 Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level ... 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; Ghosh, Dhruba; Klein, Dan; Steinhardt, Jacob; Zhong, Ruiqi. - : Underline Science Inc., 2021 Abstract: Read paper: https://www.aclanthology.org/2021.findings-acl.334 Abstract: Larger language models have higher accuracy on average, but are they better on every single instance (datapoint)? Some work suggests larger models have higher out-of-distribution robustness, while other work suggests they have lower accuracy on rare subgroups. To understand these differences, we investigate these models at the level of individual instances. However, one major challenge is that individual predictions are highly sensitive to noise in the randomness in training. We develop statistically rigorous methods to address this, and after accounting for pretraining and finetuning noise, we find that our BERT-Large is worse than BERT-Mini on at least 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%. We also find that finetuning noise increases with model size, and that instance-level accuracy has momentum: improvement from BERT-Mini to BERT-Medium correlates with improvement from ... Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics URL: https://dx.doi.org/10.48448/yyy2-1q93 https://underline.io/lecture/26425-are-larger-pretrained-language-models-uniformly-betterquestion-comparing-performance-at-the-instance-level BASE Hide details 424 Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021. - : Underline Science Inc., 2021 BASE Show details 425 An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Chen, Yi. - : Underline Science Inc., 2021 BASE Show details 426 Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Bernardi, Raffaella; Testoni, Alberto. - : Underline Science Inc., 2021 BASE Show details 427 Context Sensitivity Estimation in Toxicity 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; Androutsopoulos, Ion; Pavlopoulos, John. - : Underline Science Inc., 2021 BASE Show details 428 MRF-Chat: Improving Dialogue with Markov Random Fields ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Grover, Ishaan; Huggins, Matthew. - : Underline Science Inc., 2021 BASE Show details 429 Exploring Metaphoric Paraphrase Generation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Stowe, Kevin. - : Underline Science Inc., 2021 BASE Show details 430 CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Piyush; Akula, Arjun. - : Underline Science Inc., 2021 BASE Show details 431 Latent Hatred: A Benchmark for Understanding Implicit Hate Speech ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Anupindi, Vaishnavi; De Choudhury, Munmun. - : Underline Science Inc., 2021 BASE Show details 432 HypMix: Hyperbolic Interpolative Data Augmentation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Agarwal, Shivam; Flek, Lucie. - : Underline Science Inc., 2021 BASE Show details 433 Risk Minimization for Zero-shot Sequence Labeling ... 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; Hu, Zechuan; Jiang, Yong. - : Underline Science Inc., 2021 BASE Show details 434 STaCK: Sentence Ordering with Temporal Commonsense Knowledge ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Ghosal, Deepanway; Majumder, Navonil. - : Underline Science Inc., 2021 BASE Show details 435 ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Bansal, Mohit; Bauer, Lisa. - : Underline Science Inc., 2021 BASE Show details 436 GTM: A Generative Triple-wise Model for Conversational Question Generation ... 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; Shen, Lei. - : Underline Science Inc., 2021 BASE Show details 437 Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text ... 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; Bennett, Paul; Hearst, Marti. - : Underline Science Inc., 2021 BASE Show details 438 GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling ... 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; Che, Wanxiang; Liu, Ting. - : Underline Science Inc., 2021 BASE Show details 439 Discovering Dialog Structure Graph for Coherent Dialog Generation ... 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; Xu, Jun. - : Underline Science Inc., 2021 BASE Show details 440 Time-implicit Hierarchies in Different Languages ... Anonymous. - : Zenodo, 2021 BASE Show details Page: 1...18 19 20 21 22 23 24 25 26...1.020

Mobile view All Catalogues UB Frankfurt Linguistik 1.723 IDS Mannheim 275 OLC Linguistik 963 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 8 Institut für Empirische Sprachwissenschaft 151 Leibniz-Centre General Linguistics (ZAS) 126 Bibliographies BLLDB 7.546 BDSL 8 IDS Bibliografie zur deutschen Grammatik 182 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 10 IDS Präpositionen im Deutschen 3 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 49 MPI for Psycholinguistics 73 Linked Open Data catalogues Annohub 0 Online resources Link directory 559 Journal directory 96 Database directory 37 Dictionary directory 3 Open access documents BASE 10.995 Linguistik-Repository 115 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0