EMNLP Findings2021
Context-aware Entity Typing in Knowledge Graphs
Weiran Pan, Wei Wei, Xian-Ling Mao
Abstract
Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this task by utilizing entities' contextual information. Specifically, we design two inference mechanisms: i) N2T: independently use each neighbor of an entity to infer its type; ii) Agg2T: aggregate the neighbors of an entity to infer its type. Those mechanisms will produce multiple inference results, and an exponentially weighted pooling method is used to generate the final inference result. Furthermore, we propose a novel loss function to alleviate the false-negative problem during training. Experiments on two real-world KGs demonstrate the effectiveness of our method.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Multi-level Matching Network for Multimodal Entity Linking cites Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs
- A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing cites Connecting Embeddings for Knowledge Graph Entity Typing
- A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing cites Composition-based Multi-Relational Graph Convolutional Networks
- Transformer-based Entity Typing in Knowledge Graphs cites Refining activation downsampling with SoftPool
- Transformer-based Entity Typing in Knowledge Graphs cites Connecting Embeddings for Knowledge Graph Entity Typing
- Transformer-based Entity Typing in Knowledge Graphs cites Composition-based Multi-Relational Graph Convolutional Networks
- Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs cites Connecting Embeddings for Knowledge Graph Entity Typing
- Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs cites Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
- Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs cites Composition-based Multi-Relational Graph Convolutional Networks
Cited by top-tier papers5
- Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender SystemDing Zou, Wei Wei, Xian-Ling Mao, Ziyang Wang et al.SIGIR 2022 · 226 citations
- Transformer-based Entity Typing in Knowledge GraphsZhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li et al.EMNLP 2022 · 16 citations
- A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity TypingZhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu et al.EMNLP 2022 · 6 citations
- Multi-view Contrastive Learning for Entity Typing over Knowledge GraphsZhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li et al.EMNLP 2023 · 2 citations
- Multi-level Matching Network for Multimodal Entity LinkingZhiwei Hu, Víctor Gutiérrez-Basulto, Ru Li, Jeff Z. PanKDD 2025 · 1 citation
Builds on4
- Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 citations
- Refining activation downsampling with SoftPoolAlexandros Stergiou, Ronald Poppe, Grigorios KalliatakisICCV 2021 · 195 citations
- DGL-KE: Training Knowledge Graph Embeddings at ScaleDa Zheng, Xiang Song, Chao Ma, Zeyuan Tan et al.SIGIR 2020 · 132 citations
- Connecting Embeddings for Knowledge Graph Entity TypingYu Zhao, Anxiang Zhang, Ruobing Xie, Kang Liu et al.ACL 2020 · 62 citations
Related papers
- InGram: Inductive Knowledge Graph Embedding via Relation GraphsJaejun Lee, Chanyoung Chung, Joyce Jiyoung WhangICML 2023 · 83 citations
- AsyncET: Asynchronous Representation Learning for Knowledge Graph Entity TypingYun-Cheng Wang, Xiou Ge, Bin Wang, C.-C. Jay KuoKDD 2024 · 4 citations
- AutoETER: Automated Entity Type Representation with Relation-Aware Attention for Knowledge Graph EmbeddingGuanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu et al.EMNLP Findings 2020 · 38 citations
- NeuInfer: Knowledge Inference on N-ary FactsSaiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang et al.ACL 2020 · 66 citations
- Inductive Relation Inference of Knowledge Graph Enhanced by Ontology InformationWentao Zhou, Jun Zhao, Tao Gui, Qi Zhang et al.EMNLP Findings 2023 · 6 citations
