Advanced search
1 file | 670.56 KB Add to list

KamerRaad : enhancing information retrieval in Belgian national politics through hierarchical summarization and conversational interfaces

Alexander Rogiers (UGent) , Maarten Buyl (UGent) , Bo Kang (UGent) and Tijl De Bie (UGent)
Author
Organization
Project
Abstract
KamerRaad is an AI tool that leverages large language models to help citizens interactively engage with Belgian political information. The tool extracts and concisely summarizes key excerpts from parliamentary proceedings, followed by the potential for interaction based on generative AI that allows users to steadily build up their understanding. KamerRaad's front-end, built with Streamlit, facilitates easy interaction, while the back-end employs open-source models for text embedding and generation to ensure accurate and relevant responses. By collecting feedback, we intend to enhance the relevancy of our source retrieval and the quality of our summarization, thereby enriching the user experience with a focus on source-driven dialogue.
Keywords
Information Retrieval, Retrieval-Augmented Generation, Large Language Models

Downloads

  • (...).pdf
    • full text (Accepted manuscript)
    • |
    • UGent only (changes to open access on 2025-08-22)
    • |
    • PDF
    • |
    • 670.56 KB

Citation

Please use this url to cite or link to this publication:

MLA
Rogiers, Alexander, et al. “KamerRaad : Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces.” MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024, edited by Albert Bifet et al., vol. 14948, Springer, 2024, pp. 409–12, doi:10.1007/978-3-031-70371-3_30.
APA
Rogiers, A., Buyl, M., Kang, B., & De Bie, T. (2024). KamerRaad : enhancing information retrieval in Belgian national politics through hierarchical summarization and conversational interfaces. In A. Bifet, P. Daniušis, J. Davis, T. Krilavičius, M. Kull, E. Ntoutsi, … I. Žliobaitė (Eds.), MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024 (Vol. 14948, pp. 409–412). https://doi.org/10.1007/978-3-031-70371-3_30
Chicago author-date
Rogiers, Alexander, Maarten Buyl, Bo Kang, and Tijl De Bie. 2024. “KamerRaad : Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces.” In MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024, edited by Albert Bifet, Povilas Daniušis, Jesse Davis, Tomas Krilavičius, Meelis Kull, Eirini Ntoutsi, Kai Puolamäki, and Indrė Žliobaitė, 14948:409–12. Springer. https://doi.org/10.1007/978-3-031-70371-3_30.
Chicago author-date (all authors)
Rogiers, Alexander, Maarten Buyl, Bo Kang, and Tijl De Bie. 2024. “KamerRaad : Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces.” In MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024, ed by. Albert Bifet, Povilas Daniušis, Jesse Davis, Tomas Krilavičius, Meelis Kull, Eirini Ntoutsi, Kai Puolamäki, and Indrė Žliobaitė, 14948:409–412. Springer. doi:10.1007/978-3-031-70371-3_30.
Vancouver
1.
Rogiers A, Buyl M, Kang B, De Bie T. KamerRaad : enhancing information retrieval in Belgian national politics through hierarchical summarization and conversational interfaces. In: Bifet A, Daniušis P, Davis J, Krilavičius T, Kull M, Ntoutsi E, et al., editors. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024. Springer; 2024. p. 409–12.
IEEE
[1]
A. Rogiers, M. Buyl, B. Kang, and T. De Bie, “KamerRaad : enhancing information retrieval in Belgian national politics through hierarchical summarization and conversational interfaces,” in MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024, Vilnius, Lithuania, 2024, vol. 14948, pp. 409–412.
@inproceedings{01HXRQS32BZR65SZ0NK9S0PYSK,
  abstract     = {{KamerRaad is an AI tool that leverages large language models to help citizens
interactively engage with Belgian political information. The tool extracts and
concisely summarizes key excerpts from parliamentary proceedings, followed by
the potential for interaction based on generative AI that allows users to
steadily build up their understanding. KamerRaad's front-end, built with
Streamlit, facilitates easy interaction, while the back-end employs open-source
models for text embedding and generation to ensure accurate and relevant
responses. By collecting feedback, we intend to enhance the relevancy of our
source retrieval and the quality of our summarization, thereby enriching the
user experience with a focus on source-driven dialogue.}},
  author       = {{Rogiers, Alexander and Buyl, Maarten and Kang, Bo and De Bie, Tijl}},
  booktitle    = {{MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES-RESEARCH TRACK AND DEMO TRACK, PT VIII, ECML PKDD 2024}},
  editor       = {{Bifet, Albert and Daniušis, Povilas and Davis, Jesse and Krilavičius, Tomas and Kull, Meelis and Ntoutsi, Eirini and Puolamäki, Kai and Žliobaitė, Indrė}},
  isbn         = {{9783031703706}},
  issn         = {{0302-9743}},
  keywords     = {{Information Retrieval,Retrieval-Augmented Generation,Large Language Models}},
  language     = {{eng}},
  location     = {{Vilnius, Lithuania}},
  pages        = {{409--412}},
  publisher    = {{Springer}},
  title        = {{KamerRaad : enhancing information retrieval in Belgian national politics through hierarchical summarization and conversational interfaces}},
  url          = {{http://doi.org/10.1007/978-3-031-70371-3_30}},
  volume       = {{14948}},
  year         = {{2024}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: