Zobrazeno 1 - 10
of 216
pro vyhledávání: '"Jin, Hailong"'
Publikováno v:
Data Intelligence, Vol 1, Iss 1, Pp 77-98 (2019)
Knowledge bases (KBs) are often greatly incomplete, necessitating a demand for KB completion. Although XLORE is an English-Chinese bilingual knowledge graph, there are only 423,974 cross-lingual links between English instances and Chinese instances.
Externí odkaz:
https://doaj.org/article/6d75ab36f06e4cadaa29770d1d18521d
Autor:
Jin, Hailong, Li, Huiying
Semantic correspondence remains a challenging task for establishing correspondences between a pair of images with the same category or similar scenes due to the large intra-class appearance. In this paper, we introduce a novel problem called 'Small O
Externí odkaz:
http://arxiv.org/abs/2404.02678
Autor:
Yao, Zijun, Chen, Yuanyong, Lv, Xin, Cao, Shulin, Xin, Amy, Yu, Jifan, Jin, Hailong, Xu, Jianjun, Zhang, Peng, Hou, Lei, Li, Juanzi
We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. VisKoP not only provides a neural program ind
Externí odkaz:
http://arxiv.org/abs/2307.03130
Autor:
Yu, Jifan, Wang, Xiaozhi, Tu, Shangqing, Cao, Shulin, Zhang-Li, Daniel, Lv, Xin, Peng, Hao, Yao, Zijun, Zhang, Xiaohan, Li, Hanming, Li, Chunyang, Zhang, Zheyuan, Bai, Yushi, Liu, Yantao, Xin, Amy, Lin, Nianyi, Yun, Kaifeng, Gong, Linlu, Chen, Jianhui, Wu, Zhili, Qi, Yunjia, Li, Weikai, Guan, Yong, Zeng, Kaisheng, Qi, Ji, Jin, Hailong, Liu, Jinxin, Gu, Yu, Yao, Yuan, Ding, Ning, Hou, Lei, Liu, Zhiyuan, Xu, Bin, Tang, Jie, Li, Juanzi
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and a
Externí odkaz:
http://arxiv.org/abs/2306.09296
Entity linking models have achieved significant success via utilizing pretrained language models to capture semantic features. However, the NIL prediction problem, which aims to identify mentions without a corresponding entity in the knowledge base,
Externí odkaz:
http://arxiv.org/abs/2305.15725
Autor:
Peng, Hao, Wang, Xiaozhi, Hu, Shengding, Jin, Hailong, Hou, Lei, Li, Juanzi, Liu, Zhiyuan, Liu, Qun
Conceptual knowledge is fundamental to human cognition and knowledge bases. However, existing knowledge probing works only focus on evaluating factual knowledge of pre-trained language models (PLMs) and ignore conceptual knowledge. Since conceptual k
Externí odkaz:
http://arxiv.org/abs/2211.04079
Autor:
Jin, Hailong, Li, Huiying
Publikováno v:
In Expert Systems With Applications 1 February 2025 261
An enhanced approach for few-shot segmentation via smooth downsampling mask and label smoothing loss
Autor:
Jin, Hailong, Li, Huiying
Publikováno v:
In Image and Vision Computing August 2024 148
Publikováno v:
In Ore Geology Reviews January 2024 164
Autor:
Wang, Tong, Jin, Hailong, Sieverding, Heidi, Kumar, Sandeep, Miao, Yuxin, Rao, Xudong, Obembe, Oladipo, Mirzakhani Nafchi, Ali, Redfearn, Daren, Cheye, Stephen
Publikováno v:
In Ecological Economics November 2023 213