@InProceedings{Ranzenberger2024_1226,
<br/>   author = {Thomas Ranzenberger and Tobias Bocklet and Steffen Freisinger and Munir Georges and Kevin Glocker and Aaricia Herygers and Korbinian Riedhammer and Fabian Schneider and Christopher Simic and Khabbab Zakaria},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2024},
<br/>   title = {Extending HAnS: Large Language Models for Question Answering, Summarization, and Topic Segmentation in an ML-based Learning Experience Platform},
<br/>   year = {2024},
<br/>   editor = {Timo Baumann},
<br/>   month = mar,
<br/>   pages = {219--224},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {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.},
<br/>   isbn = {978-3-95908-325-6},
<br/>   issn = {0940-6832},
<br/>   keywords = {Poster},
<br/>   url = {https://www.essv.de/pdf/2024_219_224.pdf},
<br/>   doi = {10.35096/othr/pub-7103},
<br/>}