Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Entity Linking is crucial for numerous downstream tasks, such as question answering, knowledge graph population, and general knowledge extraction. A frequently overlooked aspect of entity linking is the potential encounter with entities not yet present in a target knowledge graph. Although some recent studies have addressed this issue, they primarily utilize full-text knowledge bases or depend on external information such as crawled webpages. Full-text knowledge bases are not available in all domains and using external information is connected to increased effort. However, these resources are not available in most use cases. In this work, we solely rely on the information within a knowledge graph and assume no external information is accessible.

To investigate the challenge of identifying and disambiguating entities absent from the knowledge graph, we introduce a comprehensive silver-standard benchmark dataset that covers texts from 1999 to 2022. Based on our novel dataset, we develop an approach using pre-trained language models and knowledge graph embeddings without the need for a parallel full-text corpus. Moreover, by assessing the influence of knowledge graph embeddings on the given task, we show that implementing a sequential entity linking approach, which considers the whole sentence, can outperform clustering techniques that handle each mention separately in specific instances.
Original languageEnglish
Title of host publicationKnowledge Graphs in the Age of Language Models and Neuro-Symbolic AI- : Proceedings of the 20th International Conference on Semantic Systems, 17-19 September 2024, Amsterdam, The Netherlands
EditorsAngelo A. Salatino, Mehwish Alam, Femke Ongenae, Sahar Vahdati, Anna Lisa Gentile, Tassilo Pellegrini, Shufan Jiang
Number of pages18
Place of PublicationAmsterdam
PublisherIOS Press BV
Publication date11.09.2024
Pages88-105
ISBN (electronic)978-1-64368-537-3
DOIs
Publication statusPublished - 11.09.2024
Event20th International Conference on Semantic Systems - SEMANTiCS 2024: Knowledge Graphs in the Age of Language Models and Neuro-Symbolic AI - Universität Amsterdam, Amsterdam, Netherlands
Duration: 17.09.202419.09.2024
Conference number: 20
https://2024-eu.semantics.cc/

Bibliographical note

© 2024 The Authors

DOI

Recently viewed

Publications

  1. Proceedings of the SeMantic Answer Type and Relation Prediction Task at ISWC 2021 Semantic Web Challenge (SMART2021)
  2. Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model
  3. Exact and approximate inference for annotating graphs with structural SVMs
  4. Finding Creativity in Predictability: Seizing Kairos in Chronos Through Temporal Work in Complex Innovation Processes
  5. Commitment to grand challenges in fluid forms of organizing
  6. The Replication Database: Documenting the Replicability of Psychological Science
  7. Study of fuzzy controllers performance
  8. Modernizing persistence–bioaccumulation–toxicity (PBT) assessment with high throughput animal-free methods
  9. Special Issue The Discourse of Redundancy Introduction
  10. Exploiting ConvNet diversity for flooding identification
  11. Modelling, explaining, enacting and getting feedback: How can the acquisition of core practices in teacher education be optimally fostered?
  12. Development of Early Spatial Perspective-Taking - Toward a Three-Level Model
  13. Introduction
  14. Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities
  15. Who can nudge for sustainable development? How nudge source renders dynamic norms (in-)effective in eliciting sustainable behavior
  16. Biodegradability and genotoxicity of surface functionalized colloidal silica (SiO2) particles in the aquatic environment
  17. Towards a caring transdisciplinary research practice
  18. A slow-fast trait continuum at the whole community level in relation to land-use intensification
  19. Measurement in Machine Vision Editorial Paper
  20. Hedge Detection Using the RelHunter Approach
  21. Chronic effects of a static stretching intervention program on range of motion and tissue hardness in older adults
  22. How to support students-learning in mathematical bridging-courses using ITS? Remedial Scenarios in the EU-Project Math-Bridge
  23. Study of non-linear systems
  24. Using latent class analysis to produce a typology of environmental concern in the UK
  25. Ablation Study of a Multimodal Gat Network on Perfect Synthetic and Real-world Data to Investigate the Influence of Language Models in Invoice Recognition
  26. Implementation of Chemometric Tools to Improve Data Mining and Prioritization in LC-HRMS for Nontarget Screening of Organic Micropollutants in Complex Water Matrixes
  27. The language of situated joint activity: Social virtual reality and language learning in virtual exchange
  28. Anonymized firm data under test: evidence from a replication study
  29. How development leads to democracy
  30. Predicting recurrent chat contact in a psychological intervention for the youth using natural language processing