loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Chukwuka Victor Obionwu 1 ; Bhavya Valappil 1 ; Minu Genty 1 ; Maria Jomy 1 ; Visakh Padmanabhan 1 ; Aishwarya Suresh 1 ; Sumat Bedi 1 ; David Broneske 2 and Gunter Saake 1

Affiliations: 1 University of Magdeburg, Magdeburg, Germany ; 2 German Centre for Higher Education Research and Science Studies, Hannover, Germany

Keyword(s): Information Retrieval, Generative AI, Knowledge Graphs, Intent Classification, Conversational Agents, Instructional Feedback.

Abstract: The interaction between students and instructors can be likened to an interaction with a conversational agent model that understands the context of the interaction and the questions the student poses. Large language models have exhibited remarkable aptitude for facilitating learning and educational procedures. However, they occasionally exhibit hallucinations, which can result in the spread of inaccurate or false information. This issue is problematic and requires attention in order to ensure the general reliability of the information system. Knowledge graphs provide a methodical technique for describing entities and their interconnections. This facilitates a comprehensive and interconnected understanding of the knowledge in a specific field. Therefore, in order to make the interactions with our conversational agent more human-like and to deal with hallucinations, we employ a retrieval-focused generation strategy that utilizes existing knowledge and creates responses based on context ually relevant information. Our system relies on a knowledge graph, an intent classifier, and a response generator that compares and evaluates question embeddings to ensure accurate and contextually appropriate replies. We further evaluate our implementation based on relevant metrics and compare it to state-of-the-art task-specific retrieve-and-extract architectures. For language generation tasks, we find that the RCG models generate more specific, diverse, and factual information than state-of-the-art baseline models. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.116.52.43

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Victor Obionwu, C.; Valappil, B.; Genty, M.; Jomy, M.; Padmanabhan, V.; Suresh, A.; Bedi, S.; Broneske, D. and Saake, G. (2024). Expert Agent Guided Learning with Transformers and Knowledge Graphs. In Proceedings of the 13th International Conference on Data Science, Technology and Applications - DATA; ISBN 978-989-758-707-8; ISSN 2184-285X, SciTePress, pages 180-189. DOI: 10.5220/0012860700003756

@conference{data24,
author={Chukwuka {Victor Obionwu}. and Bhavya Valappil. and Minu Genty. and Maria Jomy. and Visakh Padmanabhan. and Aishwarya Suresh. and Sumat Bedi. and David Broneske. and Gunter Saake.},
title={Expert Agent Guided Learning with Transformers and Knowledge Graphs},
booktitle={Proceedings of the 13th International Conference on Data Science, Technology and Applications - DATA},
year={2024},
pages={180-189},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012860700003756},
isbn={978-989-758-707-8},
issn={2184-285X},
}

TY - CONF

JO - Proceedings of the 13th International Conference on Data Science, Technology and Applications - DATA
TI - Expert Agent Guided Learning with Transformers and Knowledge Graphs
SN - 978-989-758-707-8
IS - 2184-285X
AU - Victor Obionwu, C.
AU - Valappil, B.
AU - Genty, M.
AU - Jomy, M.
AU - Padmanabhan, V.
AU - Suresh, A.
AU - Bedi, S.
AU - Broneske, D.
AU - Saake, G.
PY - 2024
SP - 180
EP - 189
DO - 10.5220/0012860700003756
PB - SciTePress