Cargando…
Multi-task learning approach for utilizing temporal relations in natural language understanding tasks
Various studies have been conducted on multi-task learning techniques in natural language understanding (NLU), which build a model capable of processing multiple tasks and providing generalized performance. Most documents written in natural languages contain time-related information. It is essential...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10219929/ https://www.ncbi.nlm.nih.gov/pubmed/37237035 http://dx.doi.org/10.1038/s41598-023-35009-7 |
_version_ | 1785049113780289536 |
---|---|
author | Lim, Chae-Gyun Jeong, Young-Seob Choi, Ho-Jin |
author_facet | Lim, Chae-Gyun Jeong, Young-Seob Choi, Ho-Jin |
author_sort | Lim, Chae-Gyun |
collection | PubMed |
description | Various studies have been conducted on multi-task learning techniques in natural language understanding (NLU), which build a model capable of processing multiple tasks and providing generalized performance. Most documents written in natural languages contain time-related information. It is essential to recognize such information accurately and utilize it to understand the context and overall content of a document while performing NLU tasks. In this study, we propose a multi-task learning technique that includes a temporal relation extraction task in the training process of NLU tasks such that the trained model can utilize temporal context information from the input sentences. To utilize the characteristics of multi-task learning, an additional task that extracts temporal relations from given sentences was designed, and the multi-task model was configured to learn in combination with the existing NLU tasks on Korean and English datasets. Performance differences were analyzed by combining NLU tasks to extract temporal relations. The accuracy of the single task for temporal relation extraction is 57.8 and 45.1 for Korean and English, respectively, and improves up to 64.2 and 48.7 when combined with other NLU tasks. The experimental results confirm that extracting temporal relations can improve its performance when combined with other NLU tasks in multi-task learning, compared to dealing with it individually. Also, because of the differences in linguistic characteristics between Korean and English, there are different task combinations that positively affect extracting the temporal relations. |
format | Online Article Text |
id | pubmed-10219929 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-102199292023-05-28 Multi-task learning approach for utilizing temporal relations in natural language understanding tasks Lim, Chae-Gyun Jeong, Young-Seob Choi, Ho-Jin Sci Rep Article Various studies have been conducted on multi-task learning techniques in natural language understanding (NLU), which build a model capable of processing multiple tasks and providing generalized performance. Most documents written in natural languages contain time-related information. It is essential to recognize such information accurately and utilize it to understand the context and overall content of a document while performing NLU tasks. In this study, we propose a multi-task learning technique that includes a temporal relation extraction task in the training process of NLU tasks such that the trained model can utilize temporal context information from the input sentences. To utilize the characteristics of multi-task learning, an additional task that extracts temporal relations from given sentences was designed, and the multi-task model was configured to learn in combination with the existing NLU tasks on Korean and English datasets. Performance differences were analyzed by combining NLU tasks to extract temporal relations. The accuracy of the single task for temporal relation extraction is 57.8 and 45.1 for Korean and English, respectively, and improves up to 64.2 and 48.7 when combined with other NLU tasks. The experimental results confirm that extracting temporal relations can improve its performance when combined with other NLU tasks in multi-task learning, compared to dealing with it individually. Also, because of the differences in linguistic characteristics between Korean and English, there are different task combinations that positively affect extracting the temporal relations. Nature Publishing Group UK 2023-05-26 /pmc/articles/PMC10219929/ /pubmed/37237035 http://dx.doi.org/10.1038/s41598-023-35009-7 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Lim, Chae-Gyun Jeong, Young-Seob Choi, Ho-Jin Multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
title | Multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
title_full | Multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
title_fullStr | Multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
title_full_unstemmed | Multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
title_short | Multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
title_sort | multi-task learning approach for utilizing temporal relations in natural language understanding tasks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10219929/ https://www.ncbi.nlm.nih.gov/pubmed/37237035 http://dx.doi.org/10.1038/s41598-023-35009-7 |
work_keys_str_mv | AT limchaegyun multitasklearningapproachforutilizingtemporalrelationsinnaturallanguageunderstandingtasks AT jeongyoungseob multitasklearningapproachforutilizingtemporalrelationsinnaturallanguageunderstandingtasks AT choihojin multitasklearningapproachforutilizingtemporalrelationsinnaturallanguageunderstandingtasks |