Design and Investigation of Capsule Networks for Sentence Classification
In recent years, convolutional neural networks (CNNs) have been used as an alternative to recurrent neural networks (RNNs) in text processing with promising results. In this paper, we investigated the newly introduced capsule networks (CapsNets), which are getting a lot of attention due to their gre...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/11/2200 |
| _version_ | 1819078769148690432 |
|---|---|
| author | Haftu Wedajo Fentaw Tae-Hyong Kim |
| author_facet | Haftu Wedajo Fentaw Tae-Hyong Kim |
| author_sort | Haftu Wedajo Fentaw |
| collection | DOAJ |
| description | In recent years, convolutional neural networks (CNNs) have been used as an alternative to recurrent neural networks (RNNs) in text processing with promising results. In this paper, we investigated the newly introduced capsule networks (CapsNets), which are getting a lot of attention due to their great performance gains on image analysis more than CNNs, for sentence classification or sentiment analysis in some cases. The results of our experiment show that the proposed well-tuned CapsNet model can be a good, sometimes better and cheaper, substitute of models based on CNNs and RNNs used in sentence classification. In order to investigate whether CapsNets can learn the sequential order of words or not, we performed a number of experiments by reshuffling the test data. Our CapsNet model shows an overall better classification performance and better resistance to adversarial attacks than CNN and RNN models. |
| first_indexed | 2024-12-21T19:18:21Z |
| format | Article |
| id | doaj.art-36f31236c0be4fd9bf30f10949ea4cb5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T19:18:21Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-36f31236c0be4fd9bf30f10949ea4cb52022-12-21T18:53:00ZengMDPI AGApplied Sciences2076-34172019-05-01911220010.3390/app9112200app9112200Design and Investigation of Capsule Networks for Sentence ClassificationHaftu Wedajo Fentaw0Tae-Hyong Kim1Department of Computer Engineering, Kumoh National Institute of Technology, 61 Daehak-ro, Gumi, Gyeongbuk 39177, KoreaDepartment of Computer Engineering, Kumoh National Institute of Technology, 61 Daehak-ro, Gumi, Gyeongbuk 39177, KoreaIn recent years, convolutional neural networks (CNNs) have been used as an alternative to recurrent neural networks (RNNs) in text processing with promising results. In this paper, we investigated the newly introduced capsule networks (CapsNets), which are getting a lot of attention due to their great performance gains on image analysis more than CNNs, for sentence classification or sentiment analysis in some cases. The results of our experiment show that the proposed well-tuned CapsNet model can be a good, sometimes better and cheaper, substitute of models based on CNNs and RNNs used in sentence classification. In order to investigate whether CapsNets can learn the sequential order of words or not, we performed a number of experiments by reshuffling the test data. Our CapsNet model shows an overall better classification performance and better resistance to adversarial attacks than CNN and RNN models.https://www.mdpi.com/2076-3417/9/11/2200deep learningcapsule networkssentence classificationsentiment analysis |
| spellingShingle | Haftu Wedajo Fentaw Tae-Hyong Kim Design and Investigation of Capsule Networks for Sentence Classification Applied Sciences deep learning capsule networks sentence classification sentiment analysis |
| title | Design and Investigation of Capsule Networks for Sentence Classification |
| title_full | Design and Investigation of Capsule Networks for Sentence Classification |
| title_fullStr | Design and Investigation of Capsule Networks for Sentence Classification |
| title_full_unstemmed | Design and Investigation of Capsule Networks for Sentence Classification |
| title_short | Design and Investigation of Capsule Networks for Sentence Classification |
| title_sort | design and investigation of capsule networks for sentence classification |
| topic | deep learning capsule networks sentence classification sentiment analysis |
| url | https://www.mdpi.com/2076-3417/9/11/2200 |
| work_keys_str_mv | AT haftuwedajofentaw designandinvestigationofcapsulenetworksforsentenceclassification AT taehyongkim designandinvestigationofcapsulenetworksforsentenceclassification |