• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Aletras, Nikolaos (28)
    • Fomicheva, Marina (6)
    • Specia, Lucia (6)
    • Jin, Mali (5)
    • The 2021 Conference on Empirical Methods in Natural Language Processing 2021 (5)
    • Alva-Manchego, Fernando (4)
    • Blain, Frédéric (4)
    • Chrysostomou, George (4)
    • Gajbhiye, Amit (4)
    • Obamuyide, Abiola (4)
    •   more
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access:
    • free (28)
    • subject to license (0)

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 28 1 How does the pre-training objective affect what large language models learn about linguistic properties? ... Alajrami, Ahmed; Aletras, Nikolaos. - : arXiv, 2022 BASE Show details 2 Automatic Identification and Classification of Bragging in Social Media ... Jin, Mali; Preoţiuc-Pietro, Daniel; Doğruöz, A. Seza. - : arXiv, 2022 BASE Show details 3 Analyzing Online Political Advertisements ... Villegas, Danae Sánchez; Mokaram, Saeid; Aletras, Nikolaos. - : arXiv, 2021 BASE Show details 4 Modeling the Severity of Complaints in Social Media ... Jin, Mali; Aletras, Nikolaos. - : arXiv, 2021 BASE Show details 5 Translation Error Detection as Rationale Extraction ... Fomicheva, Marina; Specia, Lucia; Aletras, Nikolaos. - : arXiv, 2021 BASE Show details 6 Knowledge Distillation for Quality Estimation ... Gajbhiye, Amit; Fomicheva, Marina; Alva-Manchego, Fernando. - : arXiv, 2021 BASE Show details 7 Frustratingly Simple Pretraining Alternatives to Masked Language Modeling ... Yamaguchi, Atsuki; Chrysostomou, George; Margatina, Katerina. - : arXiv, 2021 BASE Show details 8 Analyzing Online Political Advertisements ... 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; Aletras, Nikolaos; Mokaram, Saeid. - : Underline Science Inc., 2021 BASE Show details 9 Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ... 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; Aletras, Nikolaos; Chrysostomou, George. - : Underline Science Inc., 2021 Abstract: Read paper: https://www.aclanthology.org/2021.acl-long.40 Abstract: Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various tasks, while its weights have been extensively used as explanations for model predictions. Recent studies (Jain and Wallace, 2019; Serrano and Smith, 2019; Wiegreffe and Pinter, 2019) have showed that it cannot generally be considered as a faithful explanation (Jacovi and Goldberg, 2020) across encoders and tasks. In this paper, we seek to improve the faithfulness of attention-based explanations for text classification. We achieve this by proposing a new family of Task-Scaling (TaSc) mechanisms that learn task-specific non-contextualised information to scale the original attention weights. Evaluation tests for explanation faithfulness, show that the three proposed variants of TaSc improve attention-based ... Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics URL: https://underline.io/lecture/25394-improving-the-faithfulness-of-attention-based-explanations-with-task-specific-information-for-text-classification https://dx.doi.org/10.48448/q32p-7d89 BASE Hide details 10 Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Aletras, Nikolaos; Chrysostomou, George. - : Underline Science Inc., 2021 BASE Show details 11 Modeling the Severity of Complaints in Social Media ... NAACL 2021 2021; Aletras, Nikolaos; Jin, Mali. - : Underline Science Inc., 2021 BASE Show details 12 Active Learning by Acquiring Contrastive Examples ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Aletras, Nikolaos; Barrault, Loïc. - : Underline Science Inc., 2021 BASE Show details 13 In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering ... 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; Aletras, Nikolaos; Barrault, Loïc. - : Underline Science Inc., 2021 BASE Show details 14 Frustratingly Simple Pretraining Alternatives to Masked Language Modeling ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Aletras, Nikolaos; Chrysostomou, George. - : Underline Science Inc., 2021 BASE Show details 15 Knowledge Distillation for Quality Estimation ... 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; Aletras, Nikolaos; Alva-Manchego, Fernando. - : Underline Science Inc., 2021 BASE Show details 16 Machine Extraction of Tax Laws from Legislative Texts Han, Luyang; Guillot, Malka; Ash, Elliott In: Proceedings of the Natural Legal Language Processing Workshop 2021 (2021) BASE Show details 17 Point-of-Interest Type Prediction using Text and Images ... Villegas, Danae Sánchez; Aletras, Nikolaos. - : arXiv, 2021 BASE Show details 18 Point-of-Interest Type Prediction using Text and Images ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Aletras, Nikolaos; Sanchez Villegas, Danae. - : Underline Science Inc., 2021 BASE Show details 19 An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Aletras, Nikolaos; Mensah, Samuel. - : Underline Science Inc., 2021 BASE Show details 20 Knowledge distillation for quality estimation Gajbhiye, Amit; Fomicheva, Marina; Alva-Manchego, Fernando. - : Association for Computational Linguistics, 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 28 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0