• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher:
    
    • Zhou, Jie (32)
    • Meng, Fandong (9)
    • 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 (8)
    • Chen, Yufeng (7)
    • ., Fandong (6)
    • Liang, Yunlong (5)
    • Xu, Jinan (5)
    • Li, Peng (4)
    • Lin, Yankai (4)
    • Liu, Yijin (3)
    •   more
  • 
    Year
  • 
    Medium
  • 
    Type:
    
    • Article (21)
    • Miscellaneous (11)
    • Book (2)
  • 
    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 34 1 Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation ... Lai, Siyu; Yang, Zhen; Meng, Fandong. - : arXiv, 2022 BASE Show details 2 Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ... Zhang, Songming; Liu, Yijin; Meng, Fandong. - : arXiv, 2022 BASE Show details 3 MSCTD: A Multimodal Sentiment Chat Translation Dataset ... Liang, Yunlong; Meng, Fandong; Xu, Jinan. - : arXiv, 2022 BASE Show details 4 ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization ... Wang, Jiaan; Meng, Fandong; Lu, Ziyao. - : arXiv, 2022 BASE Show details 5 A Survey on Cross-Lingual Summarization ... Wang, Jiaan; Meng, Fandong; Zheng, Duo. - : arXiv, 2022 BASE Show details 6 Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ... Xu, Yangyifan; Liu, Yijin; Meng, Fandong. - : arXiv, 2021 BASE Show details 7 Modeling Bilingual Conversational Characteristics for Neural Chat Translation ... Liang, Yunlong; Meng, Fandong; Chen, Yufeng. - : arXiv, 2021 BASE Show details 8 Sequence-Level Training for Non-Autoregressive Neural Machine Translation ... Shao, Chenze; Feng, Yang; Zhang, Jinchao. - : arXiv, 2021 BASE Show details 9 Competence-based Curriculum Learning for Multilingual Machine Translation ... Zhang, Mingliang; Meng, Fandong; Tong, Yunhai. - : arXiv, 2021 BASE Show details 10 MoEfication: Transformer Feed-forward Layers are Mixtures of Experts ... Zhang, Zhengyan; Lin, Yankai; Liu, Zhiyuan. - : arXiv, 2021 BASE Show details 11 Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation ... 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; ., Fandong; Lin, Zheng; Liu, Yuanxin; Wang, Weiping; Zhou, Jie. - : Underline Science Inc., 2021 Abstract: Read paper: https://www.aclanthology.org/2021.acl-long.228 Abstract: Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find that the rich information contained in the hidden layers of BERT is conducive to the student's performance. To better exploit the hidden knowledge, a common practice is to force the student to deeply mimic the teacher's hidden states of all the tokens in a layer-wise manner. In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled. To understand this effect, we conduct a series of analysis. Specifically, we divide the HSK of BERT into three dimensions, namely depth, length and width. We first investigate a variety of strategies to extract crucial knowledge for each single dimension and then jointly compress the three ... Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics URL: https://underline.io/lecture/25558-marginal-utility-diminishes-exploring-the-minimum-knowledge-for-bert-knowledge-distillation https://dx.doi.org/10.48448/t87s-3224 BASE Hide details 12 CLEVE: Contrastive Pre-training for Event Extraction ... 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; Han, Xu; Hou, Lei. - : Underline Science Inc., 2021 BASE Show details 13 Towards Making the Most of Dialogue Characteristics for Neural Chat Translation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; ., Fandong; Chen, Yufeng. - : Underline Science Inc., 2021 BASE Show details 14 Rethinking Stealthiness of Backdoor Attack against NLP 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; Li, Peng; Lin, Yankai. - : Underline Science Inc., 2021 BASE Show details 15 Prevent the Language Model from being Overconfident in Neural Machine Translation ... 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; ., Fandong; Liu, Yijin. - : Underline Science Inc., 2021 BASE Show details 16 KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion ... 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; Hu, Shengding; Liu, Zhiyuan. - : Underline Science Inc., 2021 BASE Show details 17 Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Li, Lei; Ren, Shuhuai. - : Underline Science Inc., 2021 BASE Show details 18 RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Li, Peng; Lin, Yankai. - : Underline Science Inc., 2021 BASE Show details 19 Modeling Bilingual Conversational Characteristics for Neural Chat Translation ... 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; ., Fandong; Chen, Yufeng. - : Underline Science Inc., 2021 BASE Show details 20 Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition ... 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; ., Fandong; Chen, Yufeng. - : Underline Science Inc., 2021 BASE Show details Page: 1 2

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 1 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 1 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 1 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 31 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0