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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Digital Chemical Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772508122000230 |
| _version_ | 1818230178729426944 |
|---|---|
| author | Xiaochi Zhou Daniel Nurkowski Angiras Menon Jethro Akroyd Sebastian Mosbach Markus Kraft |
| author_facet | Xiaochi Zhou Daniel Nurkowski Angiras Menon Jethro Akroyd Sebastian Mosbach Markus Kraft |
| author_sort | Xiaochi Zhou |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-12-12T10:30:22Z |
| format | Article |
| id | doaj.art-c866dfda1efc4a5b9427181212ce4657 |
| institution | Directory Open Access Journal |
| issn | 2772-5081 |
| language | English |
| last_indexed | 2024-12-12T10:30:22Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Digital Chemical Engineering |
| spelling | doaj.art-c866dfda1efc4a5b9427181212ce46572022-12-22T00:27:22ZengElsevierDigital Chemical Engineering2772-50812022-06-013100032Question answering system for chemistry—A semantic agent extensionXiaochi Zhou0Daniel Nurkowski1Angiras Menon2Jethro Akroyd3Sebastian Mosbach4Markus Kraft5Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, West Site, Cambridge CB3 0AS, UKCMCL Innovations, Sheraton House, Cambridge CB3 0AX, UKDepartment of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, West Site, Cambridge CB3 0AS, UKCambridge Centre for Advanced Research and Education in Singapore (CARES), CREATE Tower, 1 Create Way, 138602, Singapore; Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, West Site, Cambridge CB3 0AS, UKCambridge Centre for Advanced Research and Education in Singapore (CARES), CREATE Tower, 1 Create Way, 138602, Singapore; Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, West Site, Cambridge CB3 0AS, UKCorresponding author at: Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, West Site, Cambridge CB3 0AS, UK.; Cambridge Centre for Advanced Research and Education in Singapore (CARES), CREATE Tower, 1 Create Way, 138602, Singapore; Department of Chemical Engineering and Biotechnology, University of Cambridge, Philippa Fawcett Drive, West Site, Cambridge CB3 0AS, UK; Nanyang Technological University, School of Chemical and Biomedical Engineering, 62 Nanyang Drive, 637459, SingaporeThis 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.http://www.sciencedirect.com/science/article/pii/S2772508122000230Question answeringSemantic agentKnowledge graph |
| spellingShingle | Xiaochi Zhou Daniel Nurkowski Angiras Menon Jethro Akroyd Sebastian Mosbach Markus Kraft Question answering system for chemistry—A semantic agent extension Digital Chemical Engineering Question answering Semantic agent Knowledge graph |
| title | 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_short | Question answering system for chemistry—A semantic agent extension |
| title_sort | question answering system for chemistry a semantic agent extension |
| topic | Question answering Semantic agent Knowledge graph |
| url | http://www.sciencedirect.com/science/article/pii/S2772508122000230 |
| work_keys_str_mv | AT xiaochizhou questionansweringsystemforchemistryasemanticagentextension AT danielnurkowski questionansweringsystemforchemistryasemanticagentextension AT angirasmenon questionansweringsystemforchemistryasemanticagentextension AT jethroakroyd questionansweringsystemforchemistryasemanticagentextension AT sebastianmosbach questionansweringsystemforchemistryasemanticagentextension AT markuskraft questionansweringsystemforchemistryasemanticagentextension |