Zobrazeno 1 - 10
of 546
pro vyhledávání: '"Feng, Zijian"'
Controllable text generation (CTG) seeks to craft texts adhering to specific attributes, traditionally employing learning-based techniques such as training, fine-tuning, or prefix-tuning with attribute-specific datasets. These approaches, while effec
Externí odkaz:
http://arxiv.org/abs/2406.09688
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e., sensitivity
Externí odkaz:
http://arxiv.org/abs/2405.20612
Prompts play a crucial role in guiding the responses of Large Language Models (LLMs). However, the intricate role of individual tokens in prompts, known as input saliency, in shaping the responses remains largely underexplored. Existing saliency meth
Externí odkaz:
http://arxiv.org/abs/2405.11891
In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting to a
Externí odkaz:
http://arxiv.org/abs/2311.06555
Category text generation receives considerable attentions since it is beneficial for various natural language processing tasks. Recently, the generative adversarial network (GAN) has attained promising performance in text generation, attributed to it
Externí odkaz:
http://arxiv.org/abs/2308.00939
Accurate online transient stability prediction is critical for ensuring power system stability when facing disturbances. While traditional transient stablity analysis replies on the time domain simulations can not be quickly adapted to the power grid
Externí odkaz:
http://arxiv.org/abs/2308.00537
Deep learning (DL) algorithms have been widely applied to short-term voltage stability (STVS) assessment in power systems. However, transferring the knowledge learned in one power grid to other power grids with topology changes is still a challenging
Externí odkaz:
http://arxiv.org/abs/2303.07138
Autor:
Zheng Hui, Wang Yu, Wang Fuzhen, Shen Liping, Zhang Guomin, Liu Jianhua, Wang Feng, Miao Ning, Li Jian, Ding Guowei, Meng Tongtong, Tang Lin, Zhang Shuang, Li Mingshuang, Li Yuan, Wang Xiaoqi, Liu Qianqian, Zhang Qian, Wu Dan, Yan Tingting, Su Qiudong, Wang Miao, Li Li, Hou Qian, Li Yixing, Liu Yi, Ye Shaodong, An Zhijie, Lance E. Rodewald, Jia Jidong, Wang Huaqing, Yu Wenzhou, Liu Zhongfu, Li Qun, Feng Zijian, Yin Zundong
Publikováno v:
The Lancet Regional Health. Western Pacific, Vol 51, Iss , Pp 101193- (2024)
Summary: Background: Since 1992, when recombinant hepatitis B vaccine was introduced in China, government health officials have used nationally representative serological surveys to monitor progress in prevention and control of hepatitis B. In 2020,
Externí odkaz:
https://doaj.org/article/3d8f8d5d61f4459895427fb0d3d8cb7b
While COVID-19 has impacted humans for a long time, people search the web for pandemic-related information, causing anxiety. From a theoretic perspective, previous studies have confirmed that the number of COVID-19 cases can cause negative emotions,
Externí odkaz:
http://arxiv.org/abs/2211.08644
Autor:
ZHENG Wenjun, SUN Xin, LEI Qiyun, GONG Zhikang, WANG Yin, LIU Xingwang, LI Chuanyou, FENG Zijian
Publikováno v:
Dizhi lixue xuebao, Vol 30, Iss 2, Pp 206-224 (2024)
Objective The Ordos block, with typical boundary zone activity, is located in the center of mainland China. Influenced by the remote action of the Tibetan Plateau in the southwest and the Pacific Plate in the east, each boundary zone of the Ordos Blo
Externí odkaz:
https://doaj.org/article/25e0e51fc8724bfa8a247a4e02d2a03f