• Refine your search:
  • 
    Keyword:
    
    • Computational Linguistics (18)
    • Machine Learning (18)
    • Machine Learning and Data Mining (18)
    • Natural Language Inference (18)
    • Natural Language Processing (18)
    • Language Models (3)
    • Neural Network (2)
    • Machine translation (1)
    • Natural Language Understanding (1)
    • Sentiment Analysis (1)
  • 
    Creator / Publisher
  • 
    Year
  • 
    Medium:
    
    • Online (18)
  • 
    Type:
    
    • Article (18)
  • 
    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 – 18 of 18 1 Automatic Fact-Checking with Document-level Annotations using BERT and Multiple Instance Learning ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Park, Joonsuk; Sathe, Aalok. - : Underline Science Inc., 2021 BASE Show details 2 FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Bansal, Mohit; Guo, Han; Hase, Peter; Rajani, Nazneen; Xiong, Caiming. - : Underline Science Inc., 2021 Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.808/ Abstract: Influence functions approximate the "influences" of training data-points for test predictions and have a wide variety of applications. Despite the popularity, their computational cost does not scale well with model and training data size. We present FastIF, a set of simple modifications to influence functions that significantly improves their run-time. We use k-Nearest Neighbors (kNN) to narrow the search space down to a subset of good candidate data points, identify the configurations that best balance the speed-quality trade-off in estimating the inverse Hessian-vector product, and introduce a fast parallel variant. Our proposed method achieves about 80X speedup while being highly correlated with the original influence values. With the availability of the fast influence functions, we demonstrate their usefulness in four applications. First, we examine whether influential data-points can "explain" test time behavior using the ... Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Inference; Natural Language Processing URL: https://underline.io/lecture/37878-fastif-scalable-influence-functions-for-efficient-model-interpretation-and-debugging https://dx.doi.org/10.48448/z3hp-d992 BASE Hide details 3 Open Aspect Target Sentiment Classification with Natural Language Prompts ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Birle, Ian; Chang, Haw-Shiuan. - : Underline Science Inc., 2021 BASE Show details 4 Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Schuff, Hendrik. - : Underline Science Inc., 2021 BASE Show details 5 ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; D. Manning, Christopher; Koreeda, Yuta. - : Underline Science Inc., 2021 BASE Show details 6 IndoNLI: A Natural Language Inference Dataset for Indonesian ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Aji, Alham Fikri; Louvan, Samuel. - : Underline Science Inc., 2021 BASE Show details 7 Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Tan, Chenhao; Zhou, Yangqiaoyu. - : Underline Science Inc., 2021 BASE Show details 8 Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Amirkhani, Hossein; Pilehvar, Mohammad Taher. - : Underline Science Inc., 2021 BASE Show details 9 Continual Few-Shot Learning for Text Classification ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Ramakanth; Bansal, Mohit. - : Underline Science Inc., 2021 BASE Show details 10 Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021. - : Underline Science Inc., 2021 BASE Show details 11 Scheduled Sampling Based on Decoding Steps for Neural Machine Translation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Liu, Yijin. - : Underline Science Inc., 2021 BASE Show details 12 Pairwise Supervised Contrastive Learning of Sentence Representations ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Zhang, Dejiao. - : Underline Science Inc., 2021 BASE Show details 13 Finding a Balanced Degree of Automation for Summary Evaluation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Bansal, Mohit; Zhang, Shiyue. - : Underline Science Inc., 2021 BASE Show details 14 A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; de Lhoneux, Miryam; Hartmann, Mareike. - : Underline Science Inc., 2021 BASE Show details 15 Universal Sentence Representation Learning with Conditional Masked Language Model ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Cer, Daniel; Darve, Eric. - : Underline Science Inc., 2021 BASE Show details 16 BARThez: a Skilled Pretrained French Sequence-to-Sequence Model ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Kamal Eddine, Moussa; Tixier, Antoine. - : Underline Science Inc., 2021 BASE Show details 17 Nearest Neighbour Few-Shot Learning for Cross-lingual Classification ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Bari, M Saiful; Haidar, Batool. - : Underline Science Inc., 2021 BASE Show details 18 Subword Mapping and Anchoring across Languages ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021. - : Underline Science Inc., 2021 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 18 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0