• Refine your search:
  • 
    Keyword:
    
    • Computational Linguistics (6)
    • Condensed Matter Physics (5)
    • FOS Physical sciences (5)
    • Neural Network (5)
    • Semantics (5)
    • Deep Learning (4)
    • Electromagnetism (4)
    • Information and Knowledge Engineering (4)
    • Computation and Language cs.CL (3)
    • FOS Computer and information sciences (3)
    •   more
  • 
    Creator / Publisher:
    
    • Balasubramanian, Niranjan (11)
    • 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 (5)
    • Chambers, Nathanael (3)
    • Schwartz, H. Andrew (3)
    • ., Harsh (2)
    • Ferdman, Michael (2)
    • Jain, Shraddhan (2)
    • Ji, Tianchu (2)
    • Lal, Yash Kumar (2)
    • Milder, Peter (2)
    •   more
  • 
    Year
  • 
    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 Hits 1 – 11 of 11 1 On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in 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; Balasubramanian, Niranjan; Ferdman, Michael. - : Underline Science Inc., 2021 BASE Show details 2 Don't Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models ... 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; Balasubramanian, Niranjan; Chambers, Nathanael. - : Underline Science Inc., 2021 BASE Show details 3 TellMeWhy: A Dataset for Answering Why-Questions in Narratives ... 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; Balasubramanian, Niranjan; Chambers, Nathanael. - : Underline Science Inc., 2021 BASE Show details 4 IrEne: Interpretable Energy Prediction for 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; ., Harsh; Balasubramanian, Niranjan. - : Underline Science Inc., 2021 BASE Show details 5 On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in 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; Balasubramanian, Niranjan; Ferdman, Michael; Jain, Shraddhan; Ji, Tianchu; Milder, Peter; Schwartz, H. Andrew. - : Underline Science Inc., 2021 Abstract: How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can be discretized to fewer values with minimal loss to task accuracies. However, this requires retraining or even creating entirely new models, both of which can be expensive and carbon-emitting. Focused on optimizations that do not require training, we systematically study the full range of typical attention values necessary. This informs the design of an inference-time quantization technique using both pruning and log-scaled mapping which produces only a few (e.g. 2^3) unique values. Over the tasks of question answering and sentiment analysis, we find nearly 80% of attention values can be pruned to zeros with minimal (< 1.0%) relative loss in accuracy. We use this pruning technique in conjunction with quantizing the attention values to only a 3-bit format, without ... Keyword: Computational Linguistics; Condensed Matter Physics; FOS Physical sciences; Information and Knowledge Engineering; Machine Learning; Neural Network; Semantics URL: https://underline.io/lecture/29879-on-the-distribution,-sparsity,-and-inference-time-quantization-of-attention-values-in-transformers https://dx.doi.org/10.48448/jn9k-w368 BASE Hide details 6 Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Harsh; Balasubramanian, Niranjan. - : Underline Science Inc., 2021 BASE Show details 7 Modeling Label Semantics for Predicting Emotional Reactions ... Gaonkar, Radhika; Kwon, Heeyoung; Bastan, Mohaddeseh. - : arXiv, 2020 BASE Show details 8 Residualized Factor Adaptation for Community Social Media Prediction Tasks ... Zamani, Mohammadzaman; Schwartz, H. Andrew; Lynn, Veronica E.. - : arXiv, 2018 BASE Show details 9 The Fine Line between Linguistic Generalization and Failure in Seq2Seq-Attention Models ... Weber, Noah; Shekhar, Leena; Balasubramanian, Niranjan. - : arXiv, 2018 BASE Show details 10 Generating Coherent Event Schemas at Scale Balasubramanian, Niranjan; Soderland,Stephen; Mausam,. - 2013 BASE Show details 11 Improved Document Representation for Classification Tasks for the Intelligence Community Liddy, Elizabeth D.; Yilmazel, Ozgur; Symonenko, Svetlana... In: School of Information Studies - Faculty Scholarship (2005) 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 11 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0