Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information
Abstract We propose a deep graph learning approach for computing semantic textual similarity (STS) by using semantic role labels generated by a Semantic Role Labeling (SRL) system. SRL system output has significant challenges in dealing with graph-neural networks because it doesn't have a graph...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-19259-5 |
| _version_ | 1798004296137048064 |
|---|---|
| author | Majid Mohebbi Seyed Naser Razavi Mohammad Ali Balafar |
| author_facet | Majid Mohebbi Seyed Naser Razavi Mohammad Ali Balafar |
| author_sort | Majid Mohebbi |
| collection | DOAJ |
| description | Abstract We propose a deep graph learning approach for computing semantic textual similarity (STS) by using semantic role labels generated by a Semantic Role Labeling (SRL) system. SRL system output has significant challenges in dealing with graph-neural networks because it doesn't have a graph structure. To address these challenges, we propose a novel SRL graph by using semantic role labels and dependency grammar. For processing the SRL graph, we proposed a Deep Graph Neural Network (DGNN) based graph-U-Net model that is placed on top of the transformers to use a variety of transformers to process representations obtained from them. We investigate the effect of using the proposed DGNN and SRL graph on the performance of some transformers in computing STS. For the evaluation of our approach, we use STS2017 and SICK datasets. Experimental evaluations show that using the SRL graph accompanied by applying the proposed DGNN increases the performance of the transformers used in the DGNN. |
| first_indexed | 2024-04-11T12:21:17Z |
| format | Article |
| id | doaj.art-41adfb8686ca4f3d9989b10c29b4349b |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T12:21:17Z |
| publishDate | 2022-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-41adfb8686ca4f3d9989b10c29b4349b2022-12-22T04:24:05ZengNature PortfolioScientific Reports2045-23222022-08-0112111110.1038/s41598-022-19259-5Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label informationMajid Mohebbi0Seyed Naser Razavi1Mohammad Ali Balafar2Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of TabrizDepartment of Computer Engineering, Faculty of Electrical and Computer Engineering, University of TabrizDepartment of Computer Engineering, Faculty of Electrical and Computer Engineering, University of TabrizAbstract We propose a deep graph learning approach for computing semantic textual similarity (STS) by using semantic role labels generated by a Semantic Role Labeling (SRL) system. SRL system output has significant challenges in dealing with graph-neural networks because it doesn't have a graph structure. To address these challenges, we propose a novel SRL graph by using semantic role labels and dependency grammar. For processing the SRL graph, we proposed a Deep Graph Neural Network (DGNN) based graph-U-Net model that is placed on top of the transformers to use a variety of transformers to process representations obtained from them. We investigate the effect of using the proposed DGNN and SRL graph on the performance of some transformers in computing STS. For the evaluation of our approach, we use STS2017 and SICK datasets. Experimental evaluations show that using the SRL graph accompanied by applying the proposed DGNN increases the performance of the transformers used in the DGNN.https://doi.org/10.1038/s41598-022-19259-5 |
| spellingShingle | Majid Mohebbi Seyed Naser Razavi Mohammad Ali Balafar Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information Scientific Reports |
| title | Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information |
| title_full | Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information |
| title_fullStr | Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information |
| title_full_unstemmed | Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information |
| title_short | Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information |
| title_sort | computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information |
| url | https://doi.org/10.1038/s41598-022-19259-5 |
| work_keys_str_mv | AT majidmohebbi computingsemanticsimilarityoftextsbasedondeepgraphlearningwithabilitytousesemanticrolelabelinformation AT seyednaserrazavi computingsemanticsimilarityoftextsbasedondeepgraphlearningwithabilitytousesemanticrolelabelinformation AT mohammadalibalafar computingsemanticsimilarityoftextsbasedondeepgraphlearningwithabilitytousesemanticrolelabelinformation |