A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis
The aspect-based sentiment analysis (ABSA) consists of two subtasks'aspect term extraction and aspect sentiment prediction. Existing methods deal with both subtasks one by one in a pipeline manner, in which there lies some problems in performance and real application. This study investigates th...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2021-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2021.9020003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572965283168256 |
|---|---|
| author | Yong Bie Yan Yang |
| author_facet | Yong Bie Yan Yang |
| author_sort | Yong Bie |
| collection | DOAJ |
| description | The aspect-based sentiment analysis (ABSA) consists of two subtasks'aspect term extraction and aspect sentiment prediction. Existing methods deal with both subtasks one by one in a pipeline manner, in which there lies some problems in performance and real application. This study investigates the end-to-end ABSA and proposes a novel multitask multiview network (MTMVN) architecture. Specifically, the architecture takes the unified ABSA as the main task with the two subtasks as auxiliary tasks. Meanwhile, the representation obtained from the branch network of the main task is regarded as the global view, whereas the representations of the two subtasks are considered two local views with different emphases. Through multitask learning, the main task can be facilitated by additional accurate aspect boundary information and sentiment polarity information. By enhancing the correlations between the views under the idea of multiview learning, the representation of the global view can be optimized to improve the overall performance of the model. The experimental results on three benchmark datasets show that the proposed method exceeds the existing pipeline methods and end-to-end methods, proving the superiority of our MTMVN architecture. |
| format | Article |
| id | doaj-art-b1b407e20a5b46b098bcd0c352a7836e |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2021-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-b1b407e20a5b46b098bcd0c352a7836e2025-02-02T05:59:19ZengTsinghua University PressBig Data Mining and Analytics2096-06542021-09-014319520710.26599/BDMA.2021.9020003A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment AnalysisYong Bie0Yan Yang1<institution>School of Computing and Artificial Intelligence, Southwest Jiaotong University</institution>, <city>Chengdu</city> <postal-code>611756</postal-code>, <country>China</country><institution>School of Computing and Artificial Intelligence, Southwest Jiaotong University</institution>, <city>Chengdu</city> <postal-code>611756</postal-code>, <country>China</country>The aspect-based sentiment analysis (ABSA) consists of two subtasks'aspect term extraction and aspect sentiment prediction. Existing methods deal with both subtasks one by one in a pipeline manner, in which there lies some problems in performance and real application. This study investigates the end-to-end ABSA and proposes a novel multitask multiview network (MTMVN) architecture. Specifically, the architecture takes the unified ABSA as the main task with the two subtasks as auxiliary tasks. Meanwhile, the representation obtained from the branch network of the main task is regarded as the global view, whereas the representations of the two subtasks are considered two local views with different emphases. Through multitask learning, the main task can be facilitated by additional accurate aspect boundary information and sentiment polarity information. By enhancing the correlations between the views under the idea of multiview learning, the representation of the global view can be optimized to improve the overall performance of the model. The experimental results on three benchmark datasets show that the proposed method exceeds the existing pipeline methods and end-to-end methods, proving the superiority of our MTMVN architecture.https://www.sciopen.com/article/10.26599/BDMA.2021.9020003deep learningmultitask learningmultiview learningnatural language processingaspect-based sentiment analysis |
| spellingShingle | Yong Bie Yan Yang A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis Big Data Mining and Analytics deep learning multitask learning multiview learning natural language processing aspect-based sentiment analysis |
| title | A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis |
| title_full | A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis |
| title_fullStr | A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis |
| title_full_unstemmed | A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis |
| title_short | A Multitask Multiview Neural Network for End-to-End Aspect-Based Sentiment Analysis |
| title_sort | multitask multiview neural network for end to end aspect based sentiment analysis |
| topic | deep learning multitask learning multiview learning natural language processing aspect-based sentiment analysis |
| url | https://www.sciopen.com/article/10.26599/BDMA.2021.9020003 |
| work_keys_str_mv | AT yongbie amultitaskmultiviewneuralnetworkforendtoendaspectbasedsentimentanalysis AT yanyang amultitaskmultiviewneuralnetworkforendtoendaspectbasedsentimentanalysis AT yongbie multitaskmultiviewneuralnetworkforendtoendaspectbasedsentimentanalysis AT yanyang multitaskmultiviewneuralnetworkforendtoendaspectbasedsentimentanalysis |