Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Li, Feng-Lin"'
While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal Policy Op
Externí odkaz:
http://arxiv.org/abs/2402.16030
Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher single-student
Externí odkaz:
http://arxiv.org/abs/2305.07928
Although pre-trained language models (PLMs) have achieved state-of-the-art performance on various natural language processing (NLP) tasks, they are shown to be lacking in knowledge when dealing with knowledge driven tasks. Despite the many efforts ma
Externí odkaz:
http://arxiv.org/abs/2208.00635
Publikováno v:
He huaxue yu fangshe huaxue, Vol 45, Iss 6, Pp 524-531 (2023)
The design and application of carborane polypeptide derivatives have attracted more and more attention, especially as boron carrier in the treatment of malignant tumors(BNCT). BNCT uses 10B to react with neutron capture, releasing alpha particles tha
Externí odkaz:
https://doaj.org/article/52774a5dc23b470e8ba55356190963a1
Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach tha
Externí odkaz:
http://arxiv.org/abs/2109.10547
Autor:
Xu, Guohai, Chen, Hehong, Li, Feng-Lin, Sun, Fu, Shi, Yunzhou, Zeng, Zhixiong, Zhou, Wei, Zhao, Zhongzhou, Zhang, Ji
Live streaming is becoming an increasingly popular trend of sales in E-commerce. The core of live-streaming sales is to encourage customers to purchase in an online broadcasting room. To enable customers to better understand a product without jumping
Externí odkaz:
http://arxiv.org/abs/2109.07411
Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support in evidenc
Externí odkaz:
http://arxiv.org/abs/2105.04201
Pre-sales customer service is of importance to E-commerce platforms as it contributes to optimizing customers' buying process. To better serve users, we propose AliMe KG, a domain knowledge graph in E-commerce that captures user problems, points of i
Externí odkaz:
http://arxiv.org/abs/2009.11684
With the rise of knowledge graph (KG), question answering over knowledge base (KBQA) has attracted increasing attention in recent years. Despite much research has been conducted on this topic, it is still challenging to apply KBQA technology in indus
Externí odkaz:
http://arxiv.org/abs/1912.05728
Autor:
Xue-yan Zheng, Si-li Tang, Tao Liu, Ye Wang, Xiao-jun Xu, Ni Xiao, Chuan Li, Yan-jun Xu, Zhao-xuan He, Shu-li Ma, Yu-liang Chen, Rui-lin Meng, Li-feng Lin
Publikováno v:
Environmental Health, Vol 21, Iss 1, Pp 1-11 (2022)
Abstract Background We aimed to explore the association between long-term exposure to particulate matter ≤ 2.5 µm (PM2.5) and metabolic syndrome (MetS) and its components including fasting blood glucose (FBG), blood pressure, triglyceride (TG), hi
Externí odkaz:
https://doaj.org/article/b2cad73d483148e2aef35f6a10eaa55a