A5101494431- Topic Modeling
- Speech and dialogue systems
- Advanced battery technologies research
- Advanced Battery Technologies Research
- Natural Language Processing Techniques
- Energy Load and Power Forecasting
- Geochemistry and Geologic Mapping
- Superconducting Materials and Applications
- Fuel Cells and Related Materials
- Evaluation Methods in Various Fields
- Advanced Decision-Making Techniques
- Supercapacitor Materials and Fabrication
- Hydrocarbon exploration and reservoir analysis
- Geological and Geochemical Analysis
- Smart Grid Energy Management
- Geoscience and Mining Technology
- Evaluation and Optimization Models
- Electric Power System Optimization
- Smart Grid and Power Systems
- Magnetic confinement fusion research
- Grey System Theory Applications
- Environmental Impact and Sustainability
- earthquake and tectonic studies
- Multimodal Machine Learning Applications
- Advanced Battery Materials and Technologies
Southwest University of Science and Technology
2013-2025
North China Electric Power University
2016-2025
Hubei University of Medicine
2025
Zhejiang Sci-Tech University
2024
Henan University of Engineering
2012-2024
Harbin Engineering University
2023-2024
Bellevue Hospital Center
2024
Ministry of Natural Resources
2024
Snap (United States)
2024
Cangzhou Central Hospital
2024
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts act represented semantic form into response natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it pivotal an NLG system to generalize well with limited labelled data real applications. To this end, we present FewshotWOZ, first benchmark simulate few-shot learning...
This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). edition of DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in systems, namely, 1. Task-oriented Modeling with unstructured knowledge access, 2. Multi-domain task-oriented dialog, 3. Interactive evaluation and 4. Situated interactive multi-modal dialog. describes task definition, provided datasets, baselines set-up each track. We also summarize results submitted systems to highlight...
We present a new method SOLOIST that uses transfer learning and machine teaching to build task bots at scale. parameterize classical modular task-oriented dialog systems using Transformer-based auto-regressive language model, which subsumes different modules into single neural model. pre-train, on heterogeneous corpora, task-grounded response generation can generate responses grounded in user goals real-world knowledge for completion. The pre-trained model be efficiently adapted accomplish...
A novel side-chain-type fluorinated sulfonated polyimide (s-FSPI) membrane is synthesized for vanadium redox batteries (VRBs) by high-temperature polycondensation and grafting reactions. The s-FSPI has a ion permeability that over an order of magnitude lower proton selectivity 6.8 times higher compared to those the Nafion 115 membrane. possesses superior chemical stability most linear aromatic polymer membranes reported VRBs. Also, flow/static (VRFB/VRSB) assembled with exhibit stable...
Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Xiang Li, Jinchao Baolin Peng, Xiujun Minlie Huang, Jianfeng Gao. Proceedings of the 57th Annual Meeting Association for Computational Linguistics: System Demonstrations. 2019.
Abstract We present a new method, Soloist,1 that uses transfer learning and machine teaching to build task bots at scale. parameterize classical modular task-oriented dialog systems using Transformer-based auto-regressive language model, which subsumes different modules into single neural model. pre-train, on heterogeneous corpora, task-grounded response generation can generate responses grounded in user goals real-world knowledge for completion. The pre-trained model be efficiently adapted...
Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Baolin Peng, Jianfeng Gao, Xiaoyan Minlie Huang. Proceedings of the 58th Annual Meeting Association for Computational Linguistics: System Demonstrations. 2020.
This paper introduces the Eighth Dialog System Technology Challenge. In line with recent challenges, eighth edition focuses on applying end-to-end dialog technologies in a pragmatic way for multi-domain task-completion, noetic response selection, audio visual scene-aware dialog, and schema-guided state tracking tasks. describes task definition, provided datasets, evaluation set-up each track. We also summarize results of submitted systems to highlight overall trends state-of-the-art