Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings
Albert Sawczyn, Jakub Binkowski, Piotr Bielak, Tomasz Kajdanowicz
Abstract
Knowledge-intensive tasks pose a significant challenge for Machine Learning (ML) techniques. Commonly adopted methods, such as Large Language Models (LLMs), often exhibit limitations when applied to such tasks. Nevertheless, there have been notable endeavours to mitigate these challenges, with a significant emphasis on augmenting LLMs through Knowledge Graphs (KGs). While KGs provide many advantages for representing knowledge, their development costs can deter extensive research and applications. Addressing this limitation, we introduce a framework for enriching embeddings of small-scale domain-specific Knowledge Graphs with well-established general-purpose KGs. Adopting our method, a modest domain-specific KG can benefit from a performance boost in downstream tasks when linked to a substantial general-purpose KG. Experimental evaluations demonstrate a notable enhancement, with up to a 44% increase observed in the Hits@10 metric. This relatively unexplored research direction can catalyze more frequent incorporation of KGs in knowledge-intensive tasks, resulting in more robust, reliable ML implementations, which hallucinates less than prevalent LLM solutions.- Anthology ID:
- 2024.lrec-main.512
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 5768–5782
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.512
- DOI:
- Cite (ACL):
- Albert Sawczyn, Jakub Binkowski, Piotr Bielak, and Tomasz Kajdanowicz. 2024. Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5768–5782, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings (Sawczyn et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.512.pdf