Sc-lstm: Learning task-specific representations in multi-task learning for sequence labeling P Lu, T Bai, P Langlais Proceedings of the 2019 Conference of the North American Chapter of the …, 2019 | 27 | 2019 |
RW-KD: Sample-wise loss terms re-weighting for knowledge distillation P Lu, A Ghaddar, A Rashid, M Rezagholizadeh, A Ghodsi, P Langlais Findings of the Association for Computational Linguistics: EMNLP 2021, 3145-3152, 2021 | 8 | 2021 |
Improving generalization of pre-trained language models via stochastic weight averaging P Lu, I Kobyzev, M Rezagholizadeh, A Rashid, A Ghodsi, P Langlais arXiv preprint arXiv:2212.05956, 2022 | 6 | 2022 |
Cnfrd: A few-shot rumor detection framework via capsule network for COVID-19 D Chen, X Chen, P Lu, X Wang, X Lan International Journal of Intelligent Systems 2023, 2023 | 5 | 2023 |
DNETC: dynamic network embedding preserving both triadic closure evolution and community structures M Yang, X Chen, B Chen, P Lu, Y Du Knowledge and Information Systems 65 (3), 1129-1157, 2023 | 4 | 2023 |
Evolutionary prediction of nonstationary event popularity dynamics of Weibo social network using time-series characteristics X Chen, X Lan, J Wan, P Lu, M Yang Discrete Dynamics in Nature and Society 2021, 1-19, 2021 | 3 | 2021 |
DialogueINAB: an interaction neural network based on attitudes and behaviors of interlocutors for dialogue emotion recognition J Ding, X Chen, P Lu, Z Yang, X Li, Y Du The Journal of Supercomputing 79 (18), 20481-20514, 2023 | 2 | 2023 |
Do we need Label Regularization to Fine-tune Pre-trained Language Models? I Kobyzev, A Jafari, M Rezagholizadeh, T Li, A Do-Omri, P Lu, P Poupart, ... arXiv preprint arXiv:2205.12428, 2022 | 2 | 2022 |
Resonance RoPE: Improving Context Length Generalization of Large Language Models S Wang, I Kobyzev, P Lu, M Rezagholizadeh, B Liu arXiv preprint arXiv:2403.00071, 2024 | 1 | 2024 |
SiMaLSTM-SNP: novel semantic relatedness learning model preserving both Siamese networks and membrane computing X Gu, X Chen, P Lu, X Lan, X Li, Y Du The Journal of Supercomputing 80 (3), 3382-3411, 2024 | 1 | 2024 |
Hyperparameter optimization for Large Language Model instruction-tuning C Tribes, S Benarroch-Lelong, P Lu, I Kobyzev arXiv preprint arXiv:2312.00949, 2023 | 1 | 2023 |
Influence maximization in social networks using role-based embedding. X Gu, Z Wang, X Chen, P Lu, Y Du, M Tang Networks & Heterogeneous Media 18 (4), 2023 | 1 | 2023 |
Towards understanding label regularization for fine-tuning pre-trained language models I Kobyzev, A Jafari, M Rezagholizadeh, T Li, A Do-Omri, P Lu, A Ghodsi, ... arXiv preprint arXiv:2205.12428, 2022 | 1 | 2022 |
CAREA: Cotraining Attribute and Relation Embeddings for Cross-Lingual Entity Alignment in Knowledge Graphs B Chen, X Chen, P Lu, Y Du Discrete Dynamics in Nature and Society 2020, 1-11, 2020 | 1 | 2020 |
Efficient Classification of Long Documents via State-Space Models P Lu, S Wang, M Rezagholizadeh, B Liu, I Kobyzev The 2023 Conference on Empirical Methods in Natural Language Processing, 2023 | | 2023 |
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization P Lu, A Rashid, I Kobyzev, M Rezagholizadeh, P Langlais arXiv preprint arXiv:2305.04971, 2023 | | 2023 |
Methods, devices and media for re-weighting to improve knowledge distillation P Lu, A Rashid, M Rezagholizadeh, A Ghaddar US Patent App. 17/231,514, 2022 | | 2022 |
Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization P Lu, A Rashid, I Kobyzev, M Rezagholizadeh, P Langlais | | 2021 |
Empirical study and multi-task learning exploration for neural sequence labeling models P Lu | | 2019 |