The many faces of GESIS
Vita
Kanishka Silva is a research associate at the Department of Knowledge Technologies for the Social Sciences (KTS) team FAIR Data. Kanishka joined GESIS in 2025 after her PhD defense on "Self-Attentive Generative Adversarial Network-based Authorship Attribution in Historical Texts" at the University of Wolverhampton, UK, in 2025. During her doctoral studies, she was a member of the Data Science and AI group (DAIREL) and contributed to the EU MSCA Staff Exchange Project OMINO. She has taught several BSc and MSc courses as a Visiting Lecturer at the Faculty of Science, University of Wolverhampton. Before her PhD, she worked as an Associate Technical Lead at 99x, Sri Lanka. She holds an MSc in Artificial Intelligence (2022) and a BSc (Hons.) in Information Technology (2017) from the University of Moratuwa, Sri Lanka.Service
Contributes to the projects NFDI4DS and BERD@NFDI at GESIS.Research
Knowledge Graphs, Authorship Attribution, Information Retrieval, Natural Language Processing, Deep Learning and Machine LearningPublications
Journal article
Ranasinghe, Tharindu, Isuri Anuradha, Damith Premasiri, Kanishka Silva, Hansi Hettiarachchi, Lasitha Uyangodage, and Marcos Zampieri. 2024. "Sold: Sinhala offensive language dataset." Language Resources and Evaluation: 1-41. doi: https://doi.org/10.1007/s10579-024-09723-1.
Silva, Kanishka, Burcu Can, Raheem Sarwar, Fred Blain, and Ruslan Mitkov. 2023. "Text data augmentation using generative adversarial networks–a systematic review." Journal of Computational and Applied Linguistics 1: 6-38. doi: https://doi.org/10.33919/JCAL.23.1.1.
Chapter in an edited book
Silva, Kanishka, Ingo Frommholz, Burcu Can, Fred Blain, Raheem Sarwar, and Laura Ugolini. 2024. "Forged-GAN-BERT: Authorship attribution for LLM-generated forged novels." In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, edited by Neele Falk, Sara Papi, and Mike Zhang, 325--337. Association for Computational Linguistics. https://aclanthology.org/2024.eacl-srw.26/.
Silva, Kanishka, Burcu Can, Fred Blain, Raheem Sarwar, Laura Ugolini, and Ruslan Mitkov. 2023. "Authorship attribution of late 19th century novels using GAN-BERT." In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), edited by Vishakh Padmakumar, Gisela Vallejo, and Yao Fu, 310-320. Association for Computational Linguistics. doi: https://doi.org/10.18653/v1/2023.acl-srw.44.
Silva, Kanishka, Thushari Silva, and Gayani Nanayakkara. 2023. "microConceptBERT: Concept-Relation Based Document Information Extraction Framework." In 2023 7th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI), 1-6. IEEE. doi: https://doi.org/10.1109/SLAAI-ICAI59257.2023.10365022.
Silva, Kanishka, and Ingo Frommholz. 2023. "What if ChatGPT wrote the Abstract?-Explainable Multi-Authorship Attribution with a Data Augmentation Strategy." In Proceedings of the IACT’23 Workshop, 38-48. CEUR Workshop Proceedings. https://ceur-ws.org/Vol-3477/paper6.pdf.
Silva, Kanishka, and Thushari Silva. 2021. "A Review on Document Information Extraction Approaches." In Proceedings of the Student Research Workshop Associated with RANLP 2021, edited by Souhila Djabri, 174-179. INCOMA Ltd.. https://aclanthology.org/2021.ranlp-srw.24/.
Presentation not at a conference
Silva, Kanishka. 2025. "Forged-GAN-BERT: Authorship attribution for LLM-generated forged novels." Guest Lecture: AI for the Arts and Humanities, School of Humanities, College of Arts, University of Glasgow, Glasgow, 2025-03-11.