• Refine your search:
  • 
    Keyword:
    
    • Neural Network (26)
    • Language Models (25)
    • Natural Language Processing (25)
    • Computational Linguistics (24)
    • Machine Learning (24)
    • Machine Learning and Data Mining (23)
    • Conversational Agent (7)
    • Machine translation (3)
    • Deep Learning (2)
    • Natural language generation (2)
    •   more
  • 
    Creator / Publisher
  • 
    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 Page: 1 2 Hits 1 – 20 of 26 1 Towards the Early Detection of Child Predators in Chat Rooms: A BERT-based Approach ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Kumbale, Sinchana; Singh, Smriti. - : Underline Science Inc., 2021 BASE Show details 2 End-to-end style-conditioned poetry generation: What does it take to learn from examples alone? ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Eger, Steffen. - : Underline Science Inc., 2021 BASE Show details 3 To what extent do human explanations of model behavior align with actual model behavior? ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Prasad, Grusha. - : Underline Science Inc., 2021 Abstract: Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case study, we investigate the extent to which human-generated explanations of models' inference decisions align with how models actually make these decisions. More specifically, we define three alignment metrics that quantify how well natural language explanations align with model sensitivity to input words, as measured by integrated gradients. Then, we evaluate eight different models (the base and large versions of BERT, RoBERTa and ELECTRA, as well as anRNN and bag-of-words model), and find that the BERT-base model has the highest alignment with human-generated explanations, for all alignment metrics. Focusing in on transformers, we find that the base versions tend to have higher alignment with human-generated explanations than their larger counterparts, suggesting that increasing the number of ... Keyword: Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Neural Network URL: https://dx.doi.org/10.48448/r05t-rn44 https://underline.io/lecture/39893-to-what-extent-do-human-explanations-of-model-behavior-align-with-actual-model-behaviorquestion BASE Hide details 4 Elementary-Level Math Word Problem Generation using Pre-Trained Transformers ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Savindu; Athapaththu, Dineth. - : Underline Science Inc., 2021 BASE Show details 5 What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Adam; Asthana, Kalyani. - : Underline Science Inc., 2021 BASE Show details 6 EM ALBERT: a step towards equipping Manipuri for NLP ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Huidrom, Rudali; Lepage, Yves. - : Underline Science Inc., 2021 BASE Show details 7 Language, Brains & Interpretability ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Zuidema, Willem. - : Underline Science Inc., 2021 BASE Show details 8 Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Chen, Gang; Huang, Kaiyu. - : Underline Science Inc., 2021 BASE Show details 9 Coral: An Approach for Conversational Agents in Mental Health Applications ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Shubham; Parekh, Saloni. - : Underline Science Inc., 2021 BASE Show details 10 #WhyDidTheyStay: An NLP-driven approach to analyzing the factors that affect domestic violence victims ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Sai Kavya, Marthala; Singh, Smriti. - : Underline Science Inc., 2021 BASE Show details 11 SciBERT-based Multitasking Deep Neural Architecture to identify Contribution Statements from Scientific articles ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Tirthankar; Ahmad, Ammaar. - : Underline Science Inc., 2021 BASE Show details 12 "I don't know who she is": Discourse and Knowledge Driven Coreference Resolution ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Phillip; Li, Cecilia. - : Underline Science Inc., 2021 BASE Show details 13 Certified Robustness to Programmable Transformations in LSTMs ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Zhang, Yuhao. - : Underline Science Inc., 2021 BASE Show details 14 Sinhala-English Code-mixed and Code-switched Data Classification ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Raveesha; Rathnayake, Himashi. - : Underline Science Inc., 2021 BASE Show details 15 Exploring Pre-Trained Transformers and Bilingual Transfer Learning for Arabic Coreference Resolution ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Min, Bonan. - : Underline Science Inc., 2021 BASE Show details 16 Adverse Drug Reaction Classification of Tweets with Fusion of Text and Drug Representations ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Sakhovskiy, Andrey; Tutubalina, Elena. - : Underline Science Inc., 2021 BASE Show details 17 Learning Cross-lingual Representations for Event Coreference Resolution with Multi-view Alignment and Optimal Transport ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Hieu Minh; Nguyen, Thien Huu. - : Underline Science Inc., 2021 BASE Show details 18 VisualSem: a high-quality knowledge graph for vision and language ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Liu, Yibo. - : Underline Science Inc., 2021 BASE Show details 19 Specializing Multilingual Language Models: An Empirical Study ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Chau, Ethan; Smith, Noah. - : Underline Science Inc., 2021 BASE Show details 20 On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Claudia; Gatt, Albert. - : Underline Science Inc., 2021 BASE Show details Page: 1 2

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 26 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0