151 citations · 157 across the 7 of their papers we have counts for
7 papers
Tunable Soft Prompts are Messengers in Federated Learning
Chenhe Dong, Yuexiang Xie, Bolin Ding +2
Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources, alleviating privacy concerns that arise fro…
Counterfactual Debiasing for Generating Factually Consistent Text Summaries
Chenhe Dong, Yuexiang Xie, Yaliang Li +1
Despite substantial progress in abstractive text summarization to generate fluent and informative texts, the factual inconsistency in the generated summaries remains an important y…
Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning
Chenhe Dong, Yuexiang Xie, Bolin Ding +2
The increasing privacy concerns on personal private text data promote the development of federated learning (FL) in recent years. However, the existing studies on applying FL in NL…
A Benchmark for Federated Hetero-Task Learning
Liuyi Yao, Dawei Gao, Zhen Wang +7
To investigate the heterogeneity in federated learning in real-world scenarios, we generalize the classic federated learning to federated hetero-task learning, which emphasizes the…
A Survey of Natural Language Generation
Chenhe Dong, Yinghui Li, Haifan Gong +4
This paper offers a comprehensive review of the research on Natural Language Generation (NLG) over the past two decades, especially in relation to data-to-text generation and text-…
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression
Chenhe Dong, Yaliang Li, Ying Shen +1
On many natural language processing tasks, large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. Neverthel…
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation
Chenhe Dong, Guangrun Wang, Hang Xu +3
Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge de…