Zobrazeno 1 - 10
of 390
pro vyhledávání: '"An, Saiping"'
Sparse Knowledge Graphs (KGs), frequently encountered in real-world applications, contain fewer facts in the form of (head entity, relation, tail entity) compared to more populated KGs. The sparse KG completion task, which reasons answers for given q
Externí odkaz:
http://arxiv.org/abs/2407.18556
Autor:
Liu, Yantao, Li, Zixuan, Jin, Xiaolong, Guo, Yucan, Bai, Long, Guan, Saiping, Guo, Jiafeng, Cheng, Xueqi
The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base. Recently, Large Language Models (LLMs) have shown strong capabilities in language understanding and can be used to solve this
Externí odkaz:
http://arxiv.org/abs/2310.14174
Publikováno v:
BMC Cancer, Vol 24, Iss 1, Pp 1-11 (2024)
Abstract Background Primary screening for high-risk human papillomavirus (hrHPV) with cytological triage for women with non-16/18 hrHPV-positive status has become popular in China. However, cytology relies on the subjective judgment of pathologists,
Externí odkaz:
https://doaj.org/article/9b1d51a883034c7ab1e506309155e762
Autor:
Ren, Weicheng, Li, Zixuan, Jin, Xiaolong, Bai, Long, Su, Miao, Liu, Yantao, Guan, Saiping, Guo, Jiafeng, Cheng, Xueqi
Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively. Nested events involve a kind of Pivot Elements (PEs) that simultaneously act as arguments of outer-nest events a
Externí odkaz:
http://arxiv.org/abs/2309.12960
Event Causality Identification (ECI) aims to identify causal relations between events in unstructured texts. This is a very challenging task, because causal relations are usually expressed by implicit associations between events. Existing methods usu
Externí odkaz:
http://arxiv.org/abs/2305.12792
Hyper-relational facts, which consist of a primary triple (head entity, relation, tail entity) and auxiliary attribute-value pairs, are widely present in real-world Knowledge Graphs (KGs). Link Prediction on Hyper-relational Facts (LPHFs) is to predi
Externí odkaz:
http://arxiv.org/abs/2305.06104
Script is a kind of structured knowledge extracted from texts, which contains a sequence of events. Based on such knowledge, script event prediction aims to predict the subsequent event. To do so, two aspects should be considered for events, namely,
Externí odkaz:
http://arxiv.org/abs/2212.08287
Autor:
Li, Zixuan, Hou, Zhongni, Guan, Saiping, Jin, Xiaolong, Peng, Weihua, Bai, Long, Lyu, Yajuan, Li, Wei, Guo, Jiafeng, Cheng, Xueqi
A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (\emph{subject}, \emph{relation}, \emph{object}, \emph{timestamp}) to describe dynamic facts. TKG reasoning has facilitated many
Externí odkaz:
http://arxiv.org/abs/2210.09708
In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos. Our framework includes attention and adaptation to different quantization parameters (QPs) in a single model. The attent
Externí odkaz:
http://arxiv.org/abs/2206.07893
Autor:
Liu, Zhaocheng, Herranz, Luis, Yang, Fei, Zhang, Saiping, Wan, Shuai, Mrak, Marta, Blanch, Marc Górriz
Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures,
Externí odkaz:
http://arxiv.org/abs/2205.06754