Abstract
This work leverages neural transformers to generate hierarchies in an existing knowledge graph. For small (\({<}\)10,000 node) domain-specific KGs, we find that a combination of few-shot prompting with one-shot generation works well, while larger KG may require cyclical generation. Hierarchy coverage increased by 98% for intents and 95% for colors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Carta, S., Giuliani, A., Piano, L., Podda, A.S., Pompianu, L., Tiddia, S.G.: Iterative zero-shot LLM prompting for knowledge graph construction (2023). http://arxiv.org/abs/2307.01128
Dong, X.L., et al.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014, New York, NY, USA, 24–27 August 2014, pp. 601–610 (2014). http://www.cs.cmu.edu/~nlao/publication/2014.kdd.pdf
Google: Google product type taxonomy. http://www.google.com/basepages/producttype/taxonomy.en-US.txt, 21 September 2021 version
Meyer, L.P., et al.: LLM-assisted knowledge graph engineering: experiments with ChatGPT (2023). http://arxiv.org/abs/2307.06917
OpenAI: GPT-4 technical report (2023). http://arxiv.org/abs/2303.08774
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: a roadmap (2023). http://arxiv.org/abs/2306.08302
Parnami, A., Lee, M.: Learning from few examples: a summary of approaches to few-shot learning (2022)
Song, Y., Wang, T., Mondal, S.K., Sahoo, J.P.: A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities (2022). http://arxiv.org/abs/2205.06743
Stokman, F., Vries, P.: Structuring knowledge in a graph. In: van der Veer, G.C., Mulder, G. (eds.) Human-Computer Interaction, pp. 186–206. Springer, Cham (1988). https://doi.org/10.1007/978-3-642-73402-1_12
Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023). http://arxiv.org/abs/2307.09288
Ugander, J., Karrer, B., Backstrom, L., Marlow, C.: The anatomy of the Facebook social graph. CoRR abs/1111.4503 (2011). http://arxiv.org/abs/1111.4503
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W.L., Leskovec, J.: Graph convolutional neural networks for web-scale recommender systems. CoRR abs/1806.01973 (2018). http://arxiv.org/abs/1806.01973
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sharma, S., Poddar, M., Kumar, J., Blank, K., King, T. (2024). Augmenting KG Hierarchies Using Neural Transformers. In: Goharian, N., et al. Advances in Information Retrieval. ECIR 2024. Lecture Notes in Computer Science, vol 14612. Springer, Cham. https://doi.org/10.1007/978-3-031-56069-9_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-56069-9_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56068-2
Online ISBN: 978-3-031-56069-9
eBook Packages: Computer ScienceComputer Science (R0)