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

Standard

Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs. / Möller, Cedric; Usbeck, Ricardo.
Knowledge 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. ed. / Angelo A. Salatino; Mehwish Alam; Femke Ongenae; Sahar Vahdati; Anna Lisa Gentile; Tassilo Pellegrini; Shufan Jiang. Amsterdam: IOS Press BV, 2024. p. 88-105 (Studies on the Semantic Web; Vol. 60).

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

Harvard

Möller, C & Usbeck, R 2024, Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs. in AA Salatino, M Alam, F Ongenae, S Vahdati, AL Gentile, T Pellegrini & S Jiang (eds), Knowledge 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. Studies on the Semantic Web, vol. 60, IOS Press BV, Amsterdam, pp. 88-105, 20th International Conference on Semantic Systems - SEMANTiCS 2024, Amsterdam, Netherlands, 17.09.24. https://doi.org/10.3233/SSW240009

APA

Möller, C., & Usbeck, R. (2024). Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs. In A. A. Salatino, M. Alam, F. Ongenae, S. Vahdati, A. L. Gentile, T. Pellegrini, & S. Jiang (Eds.), Knowledge 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 (pp. 88-105). (Studies on the Semantic Web; Vol. 60). IOS Press BV. https://doi.org/10.3233/SSW240009

Vancouver

Möller C, Usbeck R. Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs. In Salatino AA, Alam M, Ongenae F, Vahdati S, Gentile AL, Pellegrini T, Jiang S, editors, Knowledge 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. Amsterdam: IOS Press BV. 2024. p. 88-105. (Studies on the Semantic Web). doi: 10.3233/SSW240009

Bibtex

@inbook{0e3e0f1feb394832955e1c1aafac7b6d,
title = "Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs",
abstract = "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.",
keywords = "Business informatics, Entity Linking, Entity Disambiguation, Out-of-KG Entities",
author = "Cedric M{\"o}ller and Ricardo Usbeck",
note = "{\textcopyright} 2024 The Authors; 20th International Conference on Semantic Systems - SEMANTiCS 2024 : Knowledge Graphs in the Age of Language Models and Neuro-Symbolic AI, SEMANTiCS 2024 ; Conference date: 17-09-2024 Through 19-09-2024",
year = "2024",
month = sep,
day = "11",
doi = "10.3233/SSW240009",
language = "English",
series = "Studies on the Semantic Web",
publisher = "IOS Press BV",
pages = "88--105",
editor = "Salatino, {Angelo A.} and Mehwish Alam and Femke Ongenae and Sahar Vahdati and Gentile, {Anna Lisa} and Tassilo Pellegrini and Shufan Jiang",
booktitle = "Knowledge Graphs in the Age of Language Models and Neuro-Symbolic AI-",
address = "Netherlands",
url = "https://2024-eu.semantics.cc/ ",

}

RIS

TY - CHAP

T1 - Entity Linking with Out-of-Knowledge-Graph Entity Detection and Clustering Using Only Knowledge Graphs

AU - Möller, Cedric

AU - Usbeck, Ricardo

N1 - Conference code: 20

PY - 2024/9/11

Y1 - 2024/9/11

N2 - 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.

AB - 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.

KW - Business informatics

KW - Entity Linking

KW - Entity Disambiguation

KW - Out-of-KG Entities

U2 - 10.3233/SSW240009

DO - 10.3233/SSW240009

M3 - Article in conference proceedings

T3 - Studies on the Semantic Web

SP - 88

EP - 105

BT - Knowledge Graphs in the Age of Language Models and Neuro-Symbolic AI-

A2 - Salatino, Angelo A.

A2 - Alam, Mehwish

A2 - Ongenae, Femke

A2 - Vahdati, Sahar

A2 - Gentile, Anna Lisa

A2 - Pellegrini, Tassilo

A2 - Jiang, Shufan

PB - IOS Press BV

CY - Amsterdam

T2 - 20th International Conference on Semantic Systems - SEMANTiCS 2024

Y2 - 17 September 2024 through 19 September 2024

ER -

DOI

Recently viewed

Activities

  1. Trajectory-based computational analysis of coherent structures in flows
  2. International Conference on Applied Mathematics and Computational Methods in Engineering - AMCME 2013
  3. From Projects and Formats to Communities
  4. “Through the Threshold: responsive, performative, self-referential”
  5. Independent local lists and local parties - Challengers from Bottom Up? - 2009
  6. Towards a fully-automated adaptive e-learning environment: A predictive model for difficulty generating factors in gap-filling activities that target English tense-aspect-mood
  7. Digitalization and Organizational Learning: Use the Double-Loop
  8. Presentation: Nexus of Housing and Migration
  9. It's how, not what we use that matters - Communications Modes in the Internet
  10. Understanding Societal Development and Moral Progress: The Contribution of the World Values Surveys
  11. Knowledge Spaces
  12. Workshop „Meta-Image Day 2012”
  13. Liquidity, Flows, Circulation: The Cultural Logic of Environmentalization (2nd part) 2021
  14. Language Learning in Blended-Learning Projects: Moodle, Web 2.0, and Learner Agency
  15. Ars Electronica
  16. Blogs in the Foreign Language Classroom
  17. 9th International Multi-Conference on Systems, Signals and Devices - SSD 2012
  18. Are Self-Employed Time and Money Poor? Dynamics of Interpendent Multidimensional Poverty with German Time Use Diary Data
  19. Developing the ‘Benign by Design’ Approach for a Rational Design of Green Derivatives of b -Blockers: Propranolol as an Example
  20. From Christiane to Elisabeth. The 19th Century Genesis of the Intellectually Working Woman and the Epistemological Dependency on Structures of Desire in Hegel and Nietzsche
  21. Institutional dynamics of affecting and being affected: The emotionalization of injustice and the threat of withdrawing the organizational identification
  22. Scene as Ecosystem, Scenes as Parts of Ecosystems or Scene versus Ecosystem? Some considerations about the compability of two conceptional approaches
  23. 24th IEEE International Conference on Business Informatics
  24. 13th Trends in Enterprise Architecture Research Workshop - TEAR 2018
  25. Exploring Sustainability in Virtual Space
  26. Towards a sustainable Southern Transylvania: Recognizing existing contributions to reach sustainable visions and empowering stakeholders

Publications

  1. Modeling of Logistic Processes in Assembly Areas
  2. Factor structure and measurement invariance of the Students’ Self-report Checklist of Social and Learning Behaviour (SSL)
  3. Modern Baselines for SPARQL Semantic Parsing
  4. Inconsistent short-term effects of enhanced structural complexity on soil microbial properties across German forests
  5. Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge
  6. A blueprint for mapping and modelling ecosystem services
  7. Influence of initial severity of depression on effectiveness of low intensity interventions
  8. An Experimental Approach to the Optimization of Customer Information at the Point of Sale
  9. Model Based Logistic Monitoring of Assembly Areas
  10. Automated scoring in the era of artificial intelligence
  11. Handicaps in job assignment
  12. Adaptor device for transmitting e.g. blood pressure data of human body from blood pressure measuring device of data communication system to e.g. personal computer, has controller for controlling transmission of data to communication module
  13. A common European asylum system? How variation in Member States’ administrative capacity undermines EU asylum harmonisation
  14. Basic analysis of the incremental profile forming process
  15. HAWK@QALD5 - Trying to answer hybrid questions with various simple ranking techniques
  16. Models for integrated production-inventory systems
  17. Modeling of microstructural pattern formation in crystal plasticity
  18. Learning in Real-World Laboratories: A Systematic Impulse for Discussion
  19. Time for the Environment: The Tutzing Time Ecology Project
  20. Evidence for singlet state β cleavage in the photoreaction of α-(2,6-dimethoxyphenoxy)-acetophenone inferred from time-resolved CIDNP spectroscopy
  21. Distal and proximal predictors of snacking at work