ACL Findings2023
Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clustering
Abstract
The nodes in the commonsense knowledge graph (CSKG) are normally represented by free-form short text (e.g., word or phrase). Different nodes may represent the same concept. This leads to the problems of edge sparsity and node redundancy, which challenges CSKG representation and completion. On the one hand, edge sparsity limits the performance of graph representation learning; On the other hand, node redundancy makes different nodes corresponding to the same concept have inconsistent relations with other nodes. To address the two problems, we propose a new CSKG completion framework based on Contrastive Pretraining and Node Clustering (CPNC). Contrastive Pretraining constructs positive and negative head-tail node pairs on CSKG and utilizes contrastive learning to obtain better semantic node representation. Node Clustering aggregates nodes with the same concept into a latent concept, assisting the task of CSKG completion. We evaluate our CPNC approach on two CSKG completion benchmarks (CN-100K and ATOMIC), where CPNC outperforms the stateof-the-art methods. Extensive experiments demonstrate that both Contrastive Pretraining and Node Clustering can significantly improve the performance of CSKG completion. The source code of CPNC is publicly available on https://github.com/NUSTM/CPNC.
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.
4 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
- Knowledge Graph Compression Enhances Diverse Commonsense Generation cites MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation
- Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision cites Commonsense Knowledge Base Completion with Structural and Semantic Context
- ATAP: Automatic Template-Augmented Commonsense Knowledge Graph Completion via Pre-Trained Language Models cites Commonsense Knowledge Base Completion with Structural and Semantic Context
- Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
- Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs cites Commonsense Knowledge Base Completion with Structural and Semantic Context
Cited by top-tier papers4
- Complex Reasoning over Logical Queries on Commonsense Knowledge GraphsTianqing Fang, Zeming Chen, Yangqiu Song, Antoine BosselutACL 2024 · 5 citations
- Knowledge Graph Compression Enhances Diverse Commonsense GenerationEunjeong Hwang, Veronika Thost, Vered Shwartz, Tengfei MaEMNLP 2023 · 3 citations
- ATAP: Automatic Template-Augmented Commonsense Knowledge Graph Completion via Pre-Trained Language ModelsFu Zhang, Yifan Ding, Jingwei ChengEMNLP 2024 · 2 citations
- Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model SupervisionYudai Pan, Jiajie Hong, Tianzhe Zhao, Lingyun Song et al.WWW 2025 · 1 citation
Builds on8
- On the Sentence Embeddings from Pre-trained Language ModelsBohan Li, Hao Zhou, Junxian He, Mingxuan Wang et al.EMNLP 2020 · 538 citations
- Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsHongyu Ren, Weihua Hu, Jure LeskovecICLR 2020 · 355 citations
- Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question AnsweringShangwen Lv, Daya Guo, Jingjing Xu, Duyu Tang et al.AAAI 2020 · 224 citations
- Commonsense Knowledge Base Completion with Structural and Semantic ContextChaitanya Malaviya, Chandra Bhagavatula, Antoine Bosselut, Yejin ChoiAAAI 2020 · 155 citations
- MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support ConversationQuan Tu, Yanran Li, Jianwei Cui, Bin Wang et al.ACL 2022 · 141 citations
Related papers
- Improving Knowledge Graph Completion with Structure-Aware Supervised Contrastive LearningJiashi Lin, Lifang Wang, Xinyu Lu, Zhongtian Hu et al.EMNLP 2024 · 5 citations
- MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge RepresentationYing Su, Zihao Wang, Tianqing Fang, Hongming Zhang et al.EMNLP Findings 2022 · 13 citations
- Improving Knowledge Graph Completion with Generative Hard Negative MiningZile Qiao, Wei Ye, Dingyao Yu, Tong Mo et al.ACL Findings 2023 · 18 citations
- Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop PathsXiangqing Shen, Siwei Wu, Rui XiaACL 2023 · 3 citations
- GCC: Graph Contrastive Coding for Graph Neural Network Pre-TrainingJiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang et al.KDD 2020 · 755 citations
