Who Wrote When? Author Diarization in Social Media Discussions
Boenninghoff, Benedikt; Hosseini, Henry; Nickel, Robert M.; Kolossa, Dorothea
Research article in edited proceedings (conference) | Peer reviewedAbstract
We are proposing a novel framework for author diarization, i.e. attributing comments in online discussions to individual authors. We consider an innovative approach that merges pre-trained neural representations of writing style with author-conditional encoder-decoder diarization, enhanced by a Conditional Random Field with Viterbi decoding for alignment refinement. Additionally, we introduce two new large-scale German language datasets, one for authorship verification and the other for author diarization. We evaluate the performance of our diarization framework on these datasets, offering insights into the strengths and limitations of this approach.
Details about the publication
Editors: Al-Onaizan, Yaser; Bansal, Mohit; Chen, Yun-Nung
Book title: Findings of the Association for Computational Linguistics: EMNLP 2024
Page range: 15721-15734
Publisher: Selbstverlag / Eigenverlag
Published by: Association for Computational Linguistics
Place of publication: Miami, Florida, USA
Status: Published
Release year: 2024
Language in which the publication is written: English
Conference: Empirical Methods in Natural Language Processing (EMNLP), Miami, Florida, United States
Link to the full text: https://aclanthology.org/2024.findings-emnlp.922
Keywords: NLP; Deep Learning; Author Diarization; Social Media
Authors from the University of Münster
| Hosseini, Henry | Department of Information Systems (WI) |
Projects the publication originates from
Duration: 01/01/2023 - 31/12/2026 | 1st Funding period Funded by: DFG - Research Unit Type of project: Subproject in DFG-joint project hosted at University of Münster |