Speaker Attribution in German Parliamentary Debates with QLoRA-adapted Large Language Models
- The growing body of political texts opens up new opportunities for rich insights into political dynamics and ideologies but also increases the workload for manual analysis. Automated speaker attribution, which detects who said what to whom in a speech event and is closely related to semantic role labeling, is an important processing step for computational text analysis. We study the potential of the large language model family Llama 2 to automate speaker attribution in German parliamentary debates from 2017-2021. We fine-tune Llama 2 with QLoRA, an efficient training strategy, and observe our approach to achieve competitive performance in the GermEval 2023 Shared Task On Speaker Attribution in German News Articles and Parliamentary Debates. Our results shed light on the capabilities of large language models in automating speaker attribution, revealing a promising avenue for computational analysis of political discourse and the development of semantic role labeling systems.
Verfasserangaben: | Tobias Bornheim, Niklas Grieger, Patrick Gustav Blaneck, Stephan BialonskiORCiD |
---|---|
DOI: | https://doi.org/10.21248/jlcl.37.2024.244 |
ISSN: | 2190-6858 |
Titel des übergeordneten Werkes (Englisch): | Journal for language technology and computational linguistics : JLCL |
Verlag: | Gesellschaft für Sprachtechnologie und Computerlinguistik |
Verlagsort: | Regensburg |
Dokumentart: | Wissenschaftlicher Artikel |
Sprache: | Englisch |
Erscheinungsjahr: | 2024 |
Datum der Publikation (Server): | 05.03.2024 |
Freies Schlagwort / Tag: | German; large language models; semantic role labeling; speaker attribution |
Jahrgang: | 37 |
Ausgabe / Heft: | 1 |
Umfang: | 13 Seiten |
Link: | https://doi.org/10.21248/jlcl.37.2024.244 |
Zugriffsart: | weltweit |
Fachbereiche und Einrichtungen: | FH Aachen / Fachbereich Medizintechnik und Technomathematik |
open_access (DINI-Set): | open_access |
Lizenz (Deutsch): | Creative Commons - Namensnennung-Weitergabe unter gleichen Bedingungen |