Back
  1. Home
  2. Profile of Keerthana MURUGARAJ (Unilu)
Profil

MURUGARAJ Keerthana

University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)

ORCID
0009-0008-5100-055X
Main Referenced Co-authors
LAMSIYAH, Salima  (4)
DURING, Marten  (2)
SCHOMMER, Christoph  (2)
THEOBALD, Martin  (2)
Main Referenced Keywords
Comparative Study (1); Extractive Text Summarization (1); HistBERT (1); Historical Domain (1); Historical Text Analysis (1);
Main Referenced Disciplines
Computer science (4)

Publications (total 4)

The most downloaded
141 downloads
K. MURUGARAJ, S. LAMSIYAH, M. DURING, and M. THEOBALD. "Mining the Past: A Comparative Study of Classical and Neural Topic Models on Historical Newspaper Archives." In Association for Computational Linguistics. Albuquerque, United States: Association for Computational Linguistics, 2025. https://hdl.handle.net/10993/64861

The most cited

5 citations (Scopus®)

K. MURUGARAJ, S. LAMSIYAH, and C. SCHOMMER. "Abstractive Summarization of Historical Documents: A New Dataset and Novel Method Using a Domain-Specific Pretrained Model." IEEE Access, 13 (2025): 10918-10932. doi:10.1109/access.2025.3528733 https://hdl.handle.net/10993/63750

Scientific outputs

Articles in scientific journals with peer reviewing verified by ORBi or included in HEC journal guide

K. MURUGARAJ, S. LAMSIYAH, M. DURING, and M. THEOBALD. "Topic-RAG for Historical Newspapers: Enhancing Information Retrieval in Humanities Research through Topic-Based Retrieval-Augmented Generation." Computational Humanities Research (2025): 1-21. doi:10.1017/chr.2025.10018
Peer reviewed

K. MURUGARAJ, S. LAMSIYAH, and C. SCHOMMER. "Abstractive Summarization of Historical Documents: A New Dataset and Novel Method Using a Domain-Specific Pretrained Model." IEEE Access, 13 (2025): 10918-10932. doi:10.1109/access.2025.3528733
Peer Reviewed verified by ORBi

Proceedings published in a book or a journal

K. MURUGARAJ, S. LAMSIYAH, M. DURING, and M. THEOBALD. "Mining the Past: A Comparative Study of Classical and Neural Topic Models on Historical Newspaper Archives." In Association for Computational Linguistics. Albuquerque, United States: Association for Computational Linguistics, 2025.
Peer reviewed

S. LAMSIYAH, K. MURUGARAJ, and C. SCHOMMER. "Historical-Domain Pre-trained Language Model for Historical Extractive Text Summarization." In Historical-Domain Pre-trained Language Model for Historical Extractive Text Summarization. London, United Kingdom: https://avestia.com/, 2023. doi:10.11159/cist23.152
Peer reviewed

Contact ORBilu