• search hit 15 of 2803
Back to Result List

Extending HAnS: Large Language Models For Question Answering, Summarization, And Topic Segmentation In An ML-based Learning Experience Platform

  • The use of chatbots based on large language models (LLMs) and their impact on society are influencing our learning experience platform Hochschul-Assistenz-System (HAnS). HAnS uses machine learning (ML) methods to support students and lecturers in the online learning and teaching processes [1]. This paper introduces LLM-based features available in HAnS which are using the transcript of our improved Automatic Speech Recognition (ASR) pipeline with an average transcription duration of 45 seconds and an average word error rate (WER) of 6.66% on over 8 hours of audio data of 7 lecture videos. A LLM-based chatbot could be used to answer questions on the lecture content as the ASR transcript is provided as context. The summarization and topic segmentation uses the LLM to improve our learning experience platform. We generate multiple choice questions using the LLM and the ASR transcript as context during playback in a period of 3 minutes and display them in the HAnS frontend.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Thomas Ranzenberger, Tobias Bocklet, Steffen Freisinger, Munir Georges, Kevin Glocker, Aaricia Herygers, Korbinian Riedhammer, Fabian Schneider, Christopher Simic, Khabbab Zakaria
URN:urn:nbn:de:bvb:898-opus4-71032
DOI:https://doi.org/10.35096/othr/pub-7103
ISBN:978-3-95908-325-6
Parent Title (German):Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024
Publisher:TUDpress
Place of publication:Dresden
Editor:Timo Baumann
Document Type:conference proceeding (article)
Language:English
Year of first Publication:2024
Publishing Institution:Ostbayerische Technische Hochschule Regensburg
Release Date:2024/03/08
First Page:219
Last Page:224
Andere Schriftenreihe:Studientexte zur Sprachkommunikation ; 107
Institutes:Fakultät Informatik und Mathematik
research focus:Information und Kommunikation
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG