Marie and BERT-A knowledge graph embedding based question answering system for chemistry
This paper presents a novel knowledge graph question answering (KGQA) system for chemistry, which is implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171565 |
| _version_ | 1811695274228187136 |
|---|---|
| author | Zhou, Xiaochi Zhang, Shaocong Agarwal, Mehal Akroyd, Jethro Mosbach, Sebastian Kraft, Markus |
| author2 | School of Chemistry, Chemical Engineering and Biotechnology |
| author_facet | School of Chemistry, Chemical Engineering and Biotechnology Zhou, Xiaochi Zhang, Shaocong Agarwal, Mehal Akroyd, Jethro Mosbach, Sebastian Kraft, Markus |
| author_sort | Zhou, Xiaochi |
| collection | NTU |
| description | This paper presents a novel knowledge graph question answering (KGQA) system for chemistry, which is implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the system operates on multiple embedding spaces, which use various embedding methods and queries the embedding spaces in parallel. With the answers returned from multiple embedding spaces, the system leverages a score alignment model to adjust the answer scores and rerank the answers. Further, the system implements an algorithm to derive implicit multihop relations to handle the complexities of deep ontologies and improve multihop question answering. The system also implements a BERT-based bidirectional entity-linking model to enhance the robustness and accuracy of the entity-linking module. The system uses a joint numerical embedding model to efficiently handle numerical filtering questions. Further, it can invoke semantic agents to perform dynamic calculations autonomously. Finally, the KGQA system handles numerous chemical reaction mechanisms using semantic parsing supported by a Linked Data Fragment server. This paper evaluates the accuracy of each module within the KGQA system with a chemistry question data set. |
| first_indexed | 2024-10-01T07:20:52Z |
| format | Journal Article |
| id | ntu-10356/171565 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:20:52Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1715652023-11-03T15:31:49Z Marie and BERT-A knowledge graph embedding based question answering system for chemistry Zhou, Xiaochi Zhang, Shaocong Agarwal, Mehal Akroyd, Jethro Mosbach, Sebastian Kraft, Markus School of Chemistry, Chemical Engineering and Biotechnology Cambridge Centre for Advanced Research and Education in Singapore Engineering::Chemical engineering Knowledge Graph Question Answering Information Retrieval This paper presents a novel knowledge graph question answering (KGQA) system for chemistry, which is implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the system operates on multiple embedding spaces, which use various embedding methods and queries the embedding spaces in parallel. With the answers returned from multiple embedding spaces, the system leverages a score alignment model to adjust the answer scores and rerank the answers. Further, the system implements an algorithm to derive implicit multihop relations to handle the complexities of deep ontologies and improve multihop question answering. The system also implements a BERT-based bidirectional entity-linking model to enhance the robustness and accuracy of the entity-linking module. The system uses a joint numerical embedding model to efficiently handle numerical filtering questions. Further, it can invoke semantic agents to perform dynamic calculations autonomously. Finally, the KGQA system handles numerous chemical reaction mechanisms using semantic parsing supported by a Linked Data Fragment server. This paper evaluates the accuracy of each module within the KGQA system with a chemistry question data set. National Research Foundation (NRF) Published version This project was supported by CMCL Innovations and 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 also supported by Towards Turing 2.0 under EPSRC Grant EP/W037211/1. M.K. gratefully acknowledges the support of the Alexander von Humboldt Foundation. 2023-10-31T01:51:24Z 2023-10-31T01:51:24Z 2023 Journal Article Zhou, X., Zhang, S., Agarwal, M., Akroyd, J., Mosbach, S. & Kraft, M. (2023). Marie and BERT-A knowledge graph embedding based question answering system for chemistry. ACS Omega, 8(36), 33039-33057. https://dx.doi.org/10.1021/acsomega.3c05114 2470-1343 https://hdl.handle.net/10356/171565 10.1021/acsomega.3c05114 37720754 2-s2.0-85170262741 36 8 33039 33057 en ACS Omega © 2023 The Authors. Published by American Chemical Society. This is an open-access article distributed under the terms of the Creative Commons License. application/pdf |
| spellingShingle | Engineering::Chemical engineering Knowledge Graph Question Answering Information Retrieval Zhou, Xiaochi Zhang, Shaocong Agarwal, Mehal Akroyd, Jethro Mosbach, Sebastian Kraft, Markus Marie and BERT-A knowledge graph embedding based question answering system for chemistry |
| title | Marie and BERT-A knowledge graph embedding based question answering system for chemistry |
| title_full | Marie and BERT-A knowledge graph embedding based question answering system for chemistry |
| title_fullStr | Marie and BERT-A knowledge graph embedding based question answering system for chemistry |
| title_full_unstemmed | Marie and BERT-A knowledge graph embedding based question answering system for chemistry |
| title_short | Marie and BERT-A knowledge graph embedding based question answering system for chemistry |
| title_sort | marie and bert a knowledge graph embedding based question answering system for chemistry |
| topic | Engineering::Chemical engineering Knowledge Graph Question Answering Information Retrieval |
| url | https://hdl.handle.net/10356/171565 |
| work_keys_str_mv | AT zhouxiaochi marieandbertaknowledgegraphembeddingbasedquestionansweringsystemforchemistry AT zhangshaocong marieandbertaknowledgegraphembeddingbasedquestionansweringsystemforchemistry AT agarwalmehal marieandbertaknowledgegraphembeddingbasedquestionansweringsystemforchemistry AT akroydjethro marieandbertaknowledgegraphembeddingbasedquestionansweringsystemforchemistry AT mosbachsebastian marieandbertaknowledgegraphembeddingbasedquestionansweringsystemforchemistry AT kraftmarkus marieandbertaknowledgegraphembeddingbasedquestionansweringsystemforchemistry |