Zobrazeno 1 - 10
of 1 562
pro vyhledávání: '"Qu, Hong"'
While Transformer-based pre-trained language models and their variants exhibit strong semantic representation capabilities, the question of comprehending the information gain derived from the additional components of PLMs remains an open question in
Externí odkaz:
http://arxiv.org/abs/2401.01667
Document-level event argument extraction poses new challenges of long input and cross-sentence inference compared to its sentence-level counterpart. However, most prior works focus on capturing the relations between candidate arguments and the event
Externí odkaz:
http://arxiv.org/abs/2310.05991
Autor:
Li Shufang, Feng Yuping, Huang Yuxia, Liu Yu, Wang Yanxi, Liang Yan, Zeng Hui, Qu Hong, Wei Ling
Publikováno v:
Open Life Sciences, Vol 19, Iss 1 (2024)
Externí odkaz:
https://doaj.org/article/105e6869301840969c6a4382a27175f2
Autor:
Zhu, Zhangzi, Qu, Hong
In the dataset of image captioning, each image is aligned with several descriptions. Despite the fact that the quality of these descriptions varies, existing captioning models treat them equally in the training process. In this paper, we propose a ne
Externí odkaz:
http://arxiv.org/abs/2206.03196
We consider the trade-off problem between exploration and exploitation under finite discounted Markov Decision Process, where the state transition matrix of the underlying environment stays unknown. We propose a double Thompson sampling reinforcement
Externí odkaz:
http://arxiv.org/abs/2202.10008
Publikováno v:
In Knowledge-Based Systems 27 September 2024 300
Autor:
Fang, Laiping, Meng, Qi, Wang, Jizhuang, Tu, Yike, Qu, Hong, Diao, Yanzhao, Li, Wuming, Wen, Hua, Fang, Jin, Hang, Lifeng, Ma, Ping'an, Jiang, Guihua
Publikováno v:
In Acta Biomaterialia 15 September 2024 186:383-395
Publikováno v:
Hangkong gongcheng jinzhan, Vol 14, Iss 6, Pp 63-72 (2023)
At present,the research on UAV air combat mainly considers the fully autonomous decision-making maneuver algorithm of UAV,and the research on the air combat maneuver decision-making under the limited supervision decision of UAV is rare,let alone the
Externí odkaz:
https://doaj.org/article/55e22e0d37ba4602bc14e3cd38f610e0
The Controllable Image Captioning (CIC) task aims to generate captions conditioned on designated control signals. Several structure-related control signals are proposed to control the semantic structure of sentences, such as sentence length and Part-
Externí odkaz:
http://arxiv.org/abs/2110.08446