Zobrazeno 1 - 10
of 202
pro vyhledávání: '"E Haihong"'
Autor:
Luo, Haoran, E, Haihong, Tang, Zichen, Peng, Shiyao, Guo, Yikai, Zhang, Wentai, Ma, Chenghao, Dong, Guanting, Song, Meina, Lin, Wei, Zhu, Yifan, Tuan, Luu Anh
Publikováno v:
ACL 2024
Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing. However, three core challenges remain
Externí odkaz:
http://arxiv.org/abs/2310.08975
Autor:
Luo, Haoran, E, Haihong, Yang, Yuhao, Yao, Tianyu, Guo, Yikai, Tang, Zichen, Zhang, Wentai, Wan, Kaiyang, Peng, Shiyao, Song, Meina, Lin, Wei, Zhu, Yifan, Tuan, Luu Anh
Publikováno v:
NeurIPS 2024
Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction
Externí odkaz:
http://arxiv.org/abs/2310.05185
Autor:
Luo, Haoran, E, Haihong, Yang, Yuhao, Guo, Yikai, Sun, Mingzhi, Yao, Tianyu, Tang, Zichen, Wan, Kaiyang, Song, Meina, Lin, Wei
Publikováno v:
ACL 2023
Link Prediction on Hyper-relational Knowledge Graphs (HKG) is a worthwhile endeavor. HKG consists of hyper-relational facts (H-Facts), composed of a main triple and several auxiliary attribute-value qualifiers, which can effectively represent factual
Externí odkaz:
http://arxiv.org/abs/2305.06588
Autor:
Luo, Haoran, E, Haihong, Yang, Yuhao, Zhou, Gengxian, Guo, Yikai, Yao, Tianyu, Tang, Zichen, Lin, Xueyuan, Wan, Kaiyang
Publikováno v:
AAAI 2023
Complex query answering (CQA) is an essential task for multi-hop and logical reasoning on knowledge graphs (KGs). Currently, most approaches are limited to queries among binary relational facts and pay less attention to n-ary facts (n>=2) containing
Externí odkaz:
http://arxiv.org/abs/2211.13469
Publikováno v:
AAAI 2023
In the field of representation learning on knowledge graphs (KGs), a hyper-relational fact consists of a main triple and several auxiliary attribute-value descriptions, which is considered more comprehensive and specific than a triple-based fact. How
Externí odkaz:
http://arxiv.org/abs/2207.08562
Autor:
Lin, Xueyuan, Xu, Chengjin, E, Haihong, Su, Fenglong, Zhou, Gengxian, Hu, Tianyi, Li, Ningyuan, Sun, Mingzhi, Luo, Haoran
Multi-hop logical reasoning over knowledge graph (KG) plays a fundamental role in many artificial intelligence tasks. Recent complex query embedding (CQE) methods for reasoning focus on static KGs, while temporal knowledge graphs (TKGs) have not been
Externí odkaz:
http://arxiv.org/abs/2205.14307
Autor:
Lin, Xueyuan, E, Haihong, Zhou, Gengxian, Hu, Tianyi, Ningyuan, Li, Sun, Mingzhi, Luo, Haoran
Current best performing models for knowledge graph reasoning (KGR) introduce geometry objects or probabilistic distributions to embed entities and first-order logical (FOL) queries into low-dimensional vector spaces. They can be summarized as a cente
Externí odkaz:
http://arxiv.org/abs/2205.11039
Automated diagnosis using deep neural networks can help ophthalmologists detect the blinding eye disease wet Age-related Macular Degeneration (AMD). Wet-AMD has two similar subtypes, Neovascular AMD and Polypoidal Choroidal Vessels (PCV). However, du
Externí odkaz:
http://arxiv.org/abs/2112.12386
Entity alignment (EA) plays an important role in automatically integrating knowledge graphs (KGs) from multiple sources. Recent approaches based on Graph Neural Network (GNN) obtain entity representation from relation information and have achieved pr
Externí odkaz:
http://arxiv.org/abs/2107.03054
A spoken language understanding (SLU) system includes two main tasks, slot filling (SF) and intent detection (ID). The joint model for the two tasks is becoming a tendency in SLU. But the bi-directional interrelated connections between the intent and
Externí odkaz:
http://arxiv.org/abs/1907.00390