Leveraging Large Language Models and Knowledge Graphs to Enhance Metadata Extraction for News Media Production

Metadata

Publisher: SMPTE — Hollywood, CA
Doc Type: Conference Paper
Content Type: Original Research
Volume: 00, pp. 1–15
Abstract: This paper introduces a novel procedure for leveraging Large Language Models (LLMs) to create Knowledge Graphs (KGs) from unstructured, multi-language news texts. The approach automates the extraction and disambiguation of entities, relations, and taxonomic hierarchies using iterative few-shot LLM prompting and unsupervised clustering techniques. These KGs are further enriched with additional nodes and edges from external sources like WikiData, enhancing the contextual understanding of the data. To make the KGs accessible to non-technical users, a conversational interface is developed, allowing journalists to interact with the KG via natural language queries, which are translated into database queries for information retrieval. This method shows significant potential for improving digital asset indexing, discovery, and content management in the media industry. Future work will focus on expanding the system's capabilities by incorporating metadata from other media types, integrating with external data sources such as DBpedia and social media, and refining the KG generation process to reduce inconsistencies. The ultimate goal is to create a unified, semantically rich environment for content discovery, enabling more sophisticated, context-aware information retrieval across various media platforms.
Publication Date: 2024-10-21
DOI: 10.5594/MOO/3042
ISBN: Electronic: 978-1-61482-965-2
Link: https://doi.org/10.5594/MOO/3042
Author(s): Caio Vinicius Dadauto
Daniel Pinheiro Franco
Roger Sacilotto
Rob Gonsalves
Shailendra Mathur
Keyword(s): Large Language Models (LLMs), Knowledge Graphs, Unstructured Text, Language Processing, News Media, Entity Extraction, Relation Extraction, Taxonomy Inference
Copyright: © 2024 SMPTE

Bibliographic Reference(s)

Ji, S., Pan, S., Cambria, E., Marttinen, P. and Philip, S.Y., 2021. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE transactions on neural networks and learning systems, 33(2), pp. 494–514. EXTERNAL
Ye, H., Zhang, N., Chen, H. and Chen, H., 2022. Generative knowledge graph construction: A review. arXiv preprint arXiv:2210.12714. EXTERNAL
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J. and Wu, X., 2024. Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering. EXTERNAL
Carta, S., Giuliani, A., Piano, L., Podda, A.S., Pompianu, L. and Tiddia, S.G., 2023. Iterative zero-shot llm prompting for knowledge graph construction. arXiv preprint arXiv:2307.01128. EXTERNAL
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J. and Wang, H., 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997. EXTERNAL
Wikidata. (n.d.). Available at: wikidata.org (Accessed: 12 August 2024). EXTERNAL
McInnes L, Healy J. Accelerated hierarchical density-based clustering. In 2017 IEEE International Conference on Data Mining Workshops (ICDMW) 2017 Nov 18 (pp. 33–42). IEEE. EXTERNAL
Song K, Tan X, Qin T, Lu J, Liu TY. Mpnet: Masked and permuted pre-training for language understanding. Advances in Neural Information Processing Systems. 2020; 33: 16857–67. EXTERNAL
APNews. (3 January 2024). Speaker Johnson demands hard-line policies during a border visit as Ukraine aid hangs in the balance. Available at: apnews.com/article/congress-border-security-ukraine-migrants-texas-mexico-909cfb700eafef95196f97906dc16ae1 (Accessed: 12 August 2024). EXTERNAL
U.S. Customs and Borders Protection. (31 November 2023). CBP officers seize fentanyl, cocaine and marijuana at the Port of EI Paso. Available at: cbp.gov/newsroom/local-media-release/cbp-officers-seize-fentanyl-cocaine-and-marijuana-port-el-paso (Accessed: 12 August 2024). EXTERNAL
Punchbowl News. (5 December 2023). House Speaker Johnson is insisting on sweeping border security changes in a deal for Ukraine aid. Available at: https://punchbowl.news/article/house/johnson-border-security-government-funding-negotiations-white-house/ (Accessed: 12 August 2024). EXTERNAL
Neo4j. Project NaLLM. Available at: https://github.com/neo4j/NaLLM. (Acessed: 20 August 2024). EXTERNAL
Wadhwa, S., Amir, S. and Wallace, B.C., 2023, July. Revisiting relation extraction in the era of large language models. In Proceedings of the conference. Association for Computational Linguistics. Meeting (Vol. 2023, p. 15566). NIH Public Access. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-MOO-3042.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Caio Vinicius Dadauto, Daniel Pinheiro Franco, Roger Sacilotto, Rob Gonsalves, and Shailendra Mathur; Leveraging Large Language Models and Knowledge Graphs to Enhance Metadata Extraction for News Media Production, MTS 2024, Article 31 (pp. 1 to 15); SMPTE, 2024, ISBN: 978-1-61482-965-2. Available at https://doi.org/10.5594/MOO/3042

Snippet:

Caio Vinicius Dadauto, Daniel Pinheiro Franco, Roger Sacilotto, Rob Gonsalves, and Shailendra Mathur; Leveraging Large Language Models and Knowledge Graphs to Enhance Metadata Extraction for News Media Production, MTS 2024, Article 31 (pp. 1 to 15); SMPTE, 2024, ISBN: 978-1-61482-965-2. Available at https://doi.org/10.5594/MOO/3042

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Caio Vinicius Dadauto, Daniel Pinheiro Franco, Roger Sacilotto, Rob Gonsalves, and Shailendra Mathur; <cite>Leveraging Large Language Models and Knowledge Graphs to Enhance Metadata Extraction for News Media Production</cite>, MTS 2024, Article 31 (pp. 1 to 15); SMPTE, 2024, ISBN: 978-1-61482-965-2. Available at <a href="https://doi.org/10.5594/MOO/3042" target="_blank" rel="noopener">https://doi.org/10.5594/MOO/3042</a></span>

SMPTE's HTML Pub

Preview:

Snippet:

<li>
Caio Vinicius Dadauto, Daniel Pinheiro Franco, Roger Sacilotto, Rob Gonsalves, and Shailendra Mathur; <cite id="bib-10-5594-moo-3042">Leveraging Large Language Models and Knowledge Graphs to Enhance Metadata Extraction for News Media Production</cite>, MTS 2024, Article 31 (pp. 1 to 15); SMPTE, 2024, ISBN: 978-1-61482-965-2
<span class="doi">10.5594/MOO/3042</span>
</li>