Contrasting Traditional Models and LLMs : An Evaluation Based on Text Segmentation
Jegan, Robin; Henrich, Andreas (2025): Contrasting Traditional Models and LLMs : An Evaluation Based on Text Segmentation, in: Christian Wartena, Ulrich Heid, und Christian Wartena (Hrsg.), Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025) : Workshops, Hannover: HsH Applied Academics, S. 274–281.
Details
- Fakultät/Lehrstuhl
- Autorin(nen)/Autor(en)
- Jegan, Robin
- Titel des Sammelwerks
- Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025) : Workshops
- Herausgeberin(nen)/Herausgeber des Sammelwerks
- Wartena, ChristianHeid, Ulrich
- Konferenz
- 21st Conference on Natural Language Processing (KONVENS 2025), Hannover
- Verlagsangabe
- HsH Applied Academics : Hannover
- Erscheinungsjahr
- 2025
- Sprache(n)
- Englisch
- URL
- Abstract
This paper presents a discussion of the relevancy of older natural language processing approaches compared to modern large language models (LLMs), with experimental results for a specific application: the segmentation of video transcripts. An analysis was conducted, if powerful modern LLMs are necessary for tasks such as text segmentation or if traditional and more efficient models – here TextTiling – suffice. In the end, LLMs provide comparable performance to the other models, but the results produced by TextTiling are promising and suggest a discussion about a trade-off regarding efficiency, performance, energy-consumption and other factors.
- Freie Schlagwort(e)
- -
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 12.11.2025