An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning
Literal and metaphorical meanings can both be found in language as a system of communication. The literal sense is not difficult, but the figurative sense includes ideas like metaphors, similes, proverbs, and idioms to create a distinctive impact or imaginative description. Idioms are phrases whose...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Measurement: Sensors |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266591742200068X |
| _version_ | 1818065681390764032 |
|---|---|
| author | S. Abarna J.I. Sheeba S. Pradeep Devaneyan |
| author_facet | S. Abarna J.I. Sheeba S. Pradeep Devaneyan |
| author_sort | S. Abarna |
| collection | DOAJ |
| description | Literal and metaphorical meanings can both be found in language as a system of communication. The literal sense is not difficult, but the figurative sense includes ideas like metaphors, similes, proverbs, and idioms to create a distinctive impact or imaginative description. Idioms are phrases whose meaning differs from that of the words that make up the phrase. Due to its non-compositional character, idiom detection in NLP tasks like text categorization is a significant difficulty. Inaccurate idiom recognition has reduced the model's performance in one of the crucial text categorization tasks, such as cyberbullying and sentiment analysis. Using language representation models that have already been trained, such as BERT (Bidirectional Encoder Representation from Transformer) and RoBERTa, the current system categorises the phrases as literals or idioms (Robustly Optimised BERT Pretraining Approach). The current system performs more accurately than the baseline models. We propose a method for categorising idioms and literals is developed utilizing K-BERT (Knowledge-enabled BERT), a Deep Learning algorithm that injects knowledge-graphs (KGs) into the sentences as domain knowledge. Additionally, it will be ensembled utilizing the stacking ensemble approach with baseline models like BERT and RoBERTa. Trofi Metaphor dataset was utilised in this study for the model's training, while a brand-new internal dataset was used for testing. |
| first_indexed | 2024-12-10T14:55:45Z |
| format | Article |
| id | doaj.art-64691f608b3c46d79dace8f5b5c38d1b |
| institution | Directory Open Access Journal |
| issn | 2665-9174 |
| language | English |
| last_indexed | 2024-12-10T14:55:45Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Measurement: Sensors |
| spelling | doaj.art-64691f608b3c46d79dace8f5b5c38d1b2022-12-22T01:44:19ZengElsevierMeasurement: Sensors2665-91742022-12-0124100434An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learningS. Abarna0J.I. Sheeba1S. Pradeep Devaneyan2Department of Computer Science and Engineering, Puducherry Technological University, India; Corresponding author.Department of Computer Science and Engineering, Puducherry Technological University, IndiaDepartment of Mechanical Engineering, Sri Venkateshwaraa College of Engineering and Technology, Puducherry, IndiaLiteral and metaphorical meanings can both be found in language as a system of communication. The literal sense is not difficult, but the figurative sense includes ideas like metaphors, similes, proverbs, and idioms to create a distinctive impact or imaginative description. Idioms are phrases whose meaning differs from that of the words that make up the phrase. Due to its non-compositional character, idiom detection in NLP tasks like text categorization is a significant difficulty. Inaccurate idiom recognition has reduced the model's performance in one of the crucial text categorization tasks, such as cyberbullying and sentiment analysis. Using language representation models that have already been trained, such as BERT (Bidirectional Encoder Representation from Transformer) and RoBERTa, the current system categorises the phrases as literals or idioms (Robustly Optimised BERT Pretraining Approach). The current system performs more accurately than the baseline models. We propose a method for categorising idioms and literals is developed utilizing K-BERT (Knowledge-enabled BERT), a Deep Learning algorithm that injects knowledge-graphs (KGs) into the sentences as domain knowledge. Additionally, it will be ensembled utilizing the stacking ensemble approach with baseline models like BERT and RoBERTa. Trofi Metaphor dataset was utilised in this study for the model's training, while a brand-new internal dataset was used for testing.http://www.sciencedirect.com/science/article/pii/S266591742200068XBERTDeep learningNLPK-BERTRoBERTa |
| spellingShingle | S. Abarna J.I. Sheeba S. Pradeep Devaneyan An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning Measurement: Sensors BERT Deep learning NLP K-BERT RoBERTa |
| title | An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning |
| title_full | An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning |
| title_fullStr | An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning |
| title_full_unstemmed | An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning |
| title_short | An ensemble model for idioms and literal text classification using knowledge-enabled BERT in deep learning |
| title_sort | ensemble model for idioms and literal text classification using knowledge enabled bert in deep learning |
| topic | BERT Deep learning NLP K-BERT RoBERTa |
| url | http://www.sciencedirect.com/science/article/pii/S266591742200068X |
| work_keys_str_mv | AT sabarna anensemblemodelforidiomsandliteraltextclassificationusingknowledgeenabledbertindeeplearning AT jisheeba anensemblemodelforidiomsandliteraltextclassificationusingknowledgeenabledbertindeeplearning AT spradeepdevaneyan anensemblemodelforidiomsandliteraltextclassificationusingknowledgeenabledbertindeeplearning AT sabarna ensemblemodelforidiomsandliteraltextclassificationusingknowledgeenabledbertindeeplearning AT jisheeba ensemblemodelforidiomsandliteraltextclassificationusingknowledgeenabledbertindeeplearning AT spradeepdevaneyan ensemblemodelforidiomsandliteraltextclassificationusingknowledgeenabledbertindeeplearning |