Question answering system for chemistry—a semantic agent extension
This paper introduces an extension of a previously developed question answering (QA) system for chemistry, operating on a knowledge graph (KG) called Marie. This extension enables the automatic invocation of semantic agents to answer questions when static data is absent from the KG. The agents are s...
Saved in:
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/173757 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-173757 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1737572024-02-26T07:34:34Z Question answering system for chemistry—a semantic agent extension Zhou, Xiaochi Nurkowski, Daniel Menon, Angiras Akroyd, Jethro Mosbach, Sebastian Kraft, Markus School of Chemical and Biomedical Engineering Cambridge Centre for Advanced Research and Education in Singapore (CARES) Engineering Semantic agent Knowledge graph This paper introduces an extension of a previously developed question answering (QA) system for chemistry, operating on a knowledge graph (KG) called Marie. This extension enables the automatic invocation of semantic agents to answer questions when static data is absent from the KG. The agents are semantically described using the agent ontology, OntoAgent, to enable automated agent discovery and invocation. The natural language processing (NLP) models of the QA system need to be trained in order to interpret questions to be answered by new agents. For this purpose, we extend OntoAgent so that it becomes possible to automatically create training material for the NLP models. We evaluate the extended QA system with two example chemistry-related agents and an evaluation question set. The evaluation result shows that the extension allows the QA system to discover the suitable agent and to invoke the agent by automatically constructing requests from the semantic agent description, thereby increasing the range of questions the QA system can answer. National Research Foundation (NRF) Published version This project is funded by the National Research Foundation (NRF), Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme. Part of this work was supported by Towards Turing 2.0 under the EPSRC Grant EP/W037211/1 and The Alan Turing Institute. M.K. gratefully acknowledges the support of the Alexander von Humboldt Foundation. X. Zhou acknowledges financial support provided CMCL Innovations. 2024-02-26T07:34:34Z 2024-02-26T07:34:34Z 2022 Journal Article Zhou, X., Nurkowski, D., Menon, A., Akroyd, J., Mosbach, S. & Kraft, M. (2022). Question answering system for chemistry—a semantic agent extension. Digital Chemical Engineering, 3, 100032-. https://dx.doi.org/10.1016/j.dche.2022.100032 2772-5081 https://hdl.handle.net/10356/173757 10.1016/j.dche.2022.100032 2-s2.0-85146546671 3 100032 en Digital Chemical Engineering © 2022 The Authors. Published by Elsevier Ltd on behalf of Institution of Chemical Engineers (IChemE). This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Semantic agent Knowledge graph |
spellingShingle |
Engineering Semantic agent Knowledge graph Zhou, Xiaochi Nurkowski, Daniel Menon, Angiras Akroyd, Jethro Mosbach, Sebastian Kraft, Markus Question answering system for chemistry—a semantic agent extension |
description |
This paper introduces an extension of a previously developed question answering (QA) system for chemistry, operating on a knowledge graph (KG) called Marie. This extension enables the automatic invocation of semantic agents to answer questions when static data is absent from the KG. The agents are semantically described using the agent ontology, OntoAgent, to enable automated agent discovery and invocation. The natural language processing (NLP) models of the QA system need to be trained in order to interpret questions to be answered by new agents. For this purpose, we extend OntoAgent so that it becomes possible to automatically create training material for the NLP models. We evaluate the extended QA system with two example chemistry-related agents and an evaluation question set. The evaluation result shows that the extension allows the QA system to discover the suitable agent and to invoke the agent by automatically constructing requests from the semantic agent description, thereby increasing the range of questions the QA system can answer. |
author2 |
School of Chemical and Biomedical Engineering |
author_facet |
School of Chemical and Biomedical Engineering Zhou, Xiaochi Nurkowski, Daniel Menon, Angiras Akroyd, Jethro Mosbach, Sebastian Kraft, Markus |
format |
Article |
author |
Zhou, Xiaochi Nurkowski, Daniel Menon, Angiras Akroyd, Jethro Mosbach, Sebastian Kraft, Markus |
author_sort |
Zhou, Xiaochi |
title |
Question answering system for chemistry—a semantic agent extension |
title_short |
Question answering system for chemistry—a semantic agent extension |
title_full |
Question answering system for chemistry—a semantic agent extension |
title_fullStr |
Question answering system for chemistry—a semantic agent extension |
title_full_unstemmed |
Question answering system for chemistry—a semantic agent extension |
title_sort |
question answering system for chemistry—a semantic agent extension |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/173757 |
_version_ |
1794549400815534080 |