Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models (2403.01972v1)

Published 4 Mar 2024 in cs.CL

Abstract: Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained LLMs to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a general framework to compensate for the deficiency of contextualized knowledge and improve KGC by querying LLMs from various perspectives, which involves leveraging the reasoning, explanation, and summarization capabilities of LLMs to expand entity descriptions, understand relations, and extract structures, respectively. We conducted extensive evaluation of the effectiveness and improvement of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding. arXiv preprint arXiv:2308.14508.
  2. Freebase: A Collaboratively Created Graph Database for Structuring Human Knowledge. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, page 1247–1250. Association for Computing Machinery.
  3. Translating Embeddings for Modeling Multi-relational Data. In Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc.
  4. Low-Dimensional Hyperbolic Knowledge Graph Embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6901–6914. Association for Computational Linguistics.
  5. Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11489–11503. Association for Computational Linguistics.
  6. Convolutional 2D Knowledge Graph Embeddings. In Proceedings of the 32th AAAI Conference on Artificial Intelligence, pages 1811–1818.
  7. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  8. Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models. arXiv preprint arXiv:2305.15597.
  9. DBpedia–A Large-scale, Multilingual Knowledge Base Extracted from Wikipedia. Semantic Web, 6(2).
  10. Prompt ChatGPT In MNER: Improved multimodal named entity recognition method based on auxiliary refining knowledge from ChatGPT. arXiv preprint arXiv:2305.12212.
  11. Learning inter-entity-interaction for few-shot knowledge graph completion. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7691–7700. Association for Computational Linguistics.
  12. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110.
  13. YAGO3: A Knowledge Base from Multilingual Wikipedias. In CIDR 2015, Seventh Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, January 4-7, 2015, Online Proceedings.
  14. George A Miller. 1995. WordNet: a lexical database for English. Communications of the ACM, 38(11):39–41.
  15. Rethinking Language Models as Symbolic Knowledge Graphs. arXiv preprint arXiv:2308.13676.
  16. A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 327–333.
  17. OpenAI. 2023. GPT-4 Technical Report. ArXiv, abs/2303.08774.
  18. Large Language Models and Knowledge Graphs: Opportunities and Challenges. arXiv preprint arXiv:2308.06374.
  19. Unifying Large Language Models and Knowledge Graphs: A Roadmap. arXiv preprint arXiv:2306.08302.
  20. Large language model based long-tail query rewriting in taobao search. arXiv preprint arXiv:2311.03758.
  21. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4498–4507.
  22. Reasoning with neural tensor networks for knowledge base completion. Advances in neural information processing systems, 26.
  23. Multi-modal knowledge graphs for recommender systems. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 1405–1414.
  24. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In International Conference on Learning Representations.
  25. Kristina Toutanova and Danqi Chen. 2015. Observed Versus Latent Features for Knowledge Base and Text Inference. In Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pages 57–66, Beijing, China. Association for Computational Linguistics.
  26. SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4281–4294. Association for Computational Linguistics.
  27. KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation. Transactions of the Association for Computational Linguistics, 9:176–194.
  28. Language Models as Knowledge Embeddings. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 2291–2297. International Joint Conferences on Artificial Intelligence Organization. Main Track.
  29. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837.
  30. Representation Learning of Knowledge Graphs with Entity Descriptions. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1).
  31. Large language models for generative information extraction: A survey. arXiv preprint arXiv:2312.17617.
  32. Relation-enhanced Negative Sampling for Multimodal Knowledge Graph Completion. MM ’22, page 3857–3866, New York, NY, USA. Association for Computing Machinery.
  33. Multimodal Biological Knowledge Graph Completion via Triple Co-attention Mechanism. In 2023 IEEE 39th International Conference on Data Engineering (ICDE), pages 3928–3941. IEEE.
  34. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. arXiv preprint arXiv:1412.6575.
  35. KG-BERT: BERT for Knowledge Graph Completion. arXiv preprint arXiv:1909.03193.
  36. Relation-aware Ensemble Learning for Knowledge Graph Embedding. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16620–16631, Singapore. Association for Computational Linguistics.
  37. GLM-130B: An Open Bilingual Pre-trained Model. In The Eleventh International Conference on Learning Representations.
  38. Multi-modal knowledge graph construction and application: A survey. IEEE Transactions on Knowledge and Data Engineering.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Derong Xu (26 papers)
  2. Ziheng Zhang (43 papers)
  3. Zhenxi Lin (11 papers)
  4. Xian Wu (139 papers)
  5. Zhihong Zhu (45 papers)
  6. Tong Xu (113 papers)
  7. Xiangyu Zhao (192 papers)
  8. Yefeng Zheng (197 papers)
  9. Enhong Chen (242 papers)
Citations (4)
View on Semantic Scholar