• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access:
    • free (4)
    • 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 Hits 1 – 4 of 4 1 Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Chang, Kai-Wei; Hsieh, Cho-Jui. - : Underline Science Inc., 2021 BASE Show details 2 Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble ... 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; Chang, Kai-Wei; Hsieh, Cho-Jui; Huang , Xuanjing; Zheng, Xiaoqing; Zhou, Yi. - : Underline Science Inc., 2021 Abstract: Read paper: https://www.aclanthology.org/2021.acl-long.426 Abstract: Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples. We propose Dirichlet Neighborhood Ensemble (DNE), a randomized method for training a robust model to defense synonym substitution-based attacks. During training, DNE forms virtual sentences by sampling embedding vectors for each word in an input sentence from a convex hull spanned by the word and its synonyms, and it augments them with the training data. In such a way, the model is robust to adversarial attacks while maintaining the performance on the original clean data. DNE is agnostic to the network architectures and scales to large models (e.g., BERT) for NLP applications. Through extensive experimentation, we demonstrate that our method consistently outperforms recently proposed defense methods by a significant margin across different network architectures and multiple data sets. ... Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics URL: https://dx.doi.org/10.48448/1f5y-5d60 https://underline.io/lecture/25854-defense-against-synonym-substitution-based-adversarial-attacks-via-dirichlet-neighborhood-ensemble BASE Hide details 3 Efficient Contextual Representation Learning With Continuous Outputs Li, Liunian Harold; Chen, Patrick H.; Hsieh, Cho-Jui... In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 611-624 (2019) (2019) BASE Show details 4 Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning ... Chen, Hongge; Zhang, Huan; Chen, Pin-Yu. - : arXiv, 2017 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 4 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0