Transformer-based approach to variable typing
The upsurge of multifarious endeavors across scientific fields propelled Big Data in the scientific domain. Despite the advancements in management systems, researchers find that mathematical knowledge remains one of the most challenging to manage due to the latter's inherent heterogeneity. One...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023077137 |
| _version_ | 1797646523957248000 |
|---|---|
| author | Charles Arthel Rey Jose Lorenzo Danguilan Karl Patrick Mendoza Miguel Francisco Remolona |
| author_facet | Charles Arthel Rey Jose Lorenzo Danguilan Karl Patrick Mendoza Miguel Francisco Remolona |
| author_sort | Charles Arthel Rey |
| collection | DOAJ |
| description | The upsurge of multifarious endeavors across scientific fields propelled Big Data in the scientific domain. Despite the advancements in management systems, researchers find that mathematical knowledge remains one of the most challenging to manage due to the latter's inherent heterogeneity. One novel recourse being explored is variable typing where current works remain preliminary and, thus, provide a wide room for contribution. In this study, a primordial attempt to implement the end-to-end Entity Recognition (ER) and Relation Extraction (RE) approach to variable typing was made using the BERT (Bidirectional Encoder Representations from Transformers) model. A micro-dataset was developed for this process. According to our findings, the ER model and RE model, respectively, have Precision of 0.8142 and 0.4919, Recall of 0.7816 and 0.6030, and F1-Scores of 0.7975 and 0.5418. Despite the limited dataset, the models performed at par with values in the literature. This work also discusses the factors affecting this BERT-based approach, giving rise to suggestions for future implementations. |
| first_indexed | 2024-03-11T15:03:55Z |
| format | Article |
| id | doaj.art-7ed1d61911724571be0b87892b07456c |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-11T15:03:55Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-7ed1d61911724571be0b87892b07456c2023-10-30T06:06:23ZengElsevierHeliyon2405-84402023-10-01910e20505Transformer-based approach to variable typingCharles Arthel Rey0Jose Lorenzo Danguilan1Karl Patrick Mendoza2Miguel Francisco Remolona3Chemical Engineering Intelligence Learning Laboratory, Department of Chemical Engineering, University of the Philippines Diliman, Quezon City, 1101 PhilippinesChemical Engineering Intelligence Learning Laboratory, Department of Chemical Engineering, University of the Philippines Diliman, Quezon City, 1101 PhilippinesChemical Engineering Intelligence Learning Laboratory, Department of Chemical Engineering, University of the Philippines Diliman, Quezon City, 1101 PhilippinesCorresponding author.; Chemical Engineering Intelligence Learning Laboratory, Department of Chemical Engineering, University of the Philippines Diliman, Quezon City, 1101 PhilippinesThe upsurge of multifarious endeavors across scientific fields propelled Big Data in the scientific domain. Despite the advancements in management systems, researchers find that mathematical knowledge remains one of the most challenging to manage due to the latter's inherent heterogeneity. One novel recourse being explored is variable typing where current works remain preliminary and, thus, provide a wide room for contribution. In this study, a primordial attempt to implement the end-to-end Entity Recognition (ER) and Relation Extraction (RE) approach to variable typing was made using the BERT (Bidirectional Encoder Representations from Transformers) model. A micro-dataset was developed for this process. According to our findings, the ER model and RE model, respectively, have Precision of 0.8142 and 0.4919, Recall of 0.7816 and 0.6030, and F1-Scores of 0.7975 and 0.5418. Despite the limited dataset, the models performed at par with values in the literature. This work also discusses the factors affecting this BERT-based approach, giving rise to suggestions for future implementations.http://www.sciencedirect.com/science/article/pii/S2405844023077137Natural language processingTransformersEntity recognitionRelation extractionVariable typingMachine learning |
| spellingShingle | Charles Arthel Rey Jose Lorenzo Danguilan Karl Patrick Mendoza Miguel Francisco Remolona Transformer-based approach to variable typing Heliyon Natural language processing Transformers Entity recognition Relation extraction Variable typing Machine learning |
| title | Transformer-based approach to variable typing |
| title_full | Transformer-based approach to variable typing |
| title_fullStr | Transformer-based approach to variable typing |
| title_full_unstemmed | Transformer-based approach to variable typing |
| title_short | Transformer-based approach to variable typing |
| title_sort | transformer based approach to variable typing |
| topic | Natural language processing Transformers Entity recognition Relation extraction Variable typing Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023077137 |
| work_keys_str_mv | AT charlesarthelrey transformerbasedapproachtovariabletyping AT joselorenzodanguilan transformerbasedapproachtovariabletyping AT karlpatrickmendoza transformerbasedapproachtovariabletyping AT miguelfranciscoremolona transformerbasedapproachtovariabletyping |