Text classification using capsules

Kim, Jae‐Young; Jang, Sion; Choi, Sungchul; Park, Eunjeong

doi:10.1016/j.neucom.2019.10.033

Cited by 151 publications

(69 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The theoretical time and space complexities of the SVM model defined here based on various sources [34] [35]. The complexity of SVM mainly depends on the amounts of sampling data.…”

Section: Time Complexitymentioning

confidence: 99%

WITHDRAWN: Exploring the Effectiveness of Convolutional Neural Network with Ensemble Technique

Ghosh¹,

Sanyal²

2020

Preprint

View full text Add to dashboard Cite

Sentiment Analysis has recently been considered as the most active research field in the natural language processing (NLP) domain. Deep Learning is a subset of the large family of Machine Learning and becoming a growing trend due to its automatic learning capability with impressive consequences across different NLP tasks. Hence, a fusion-based Machine Learning framework has been attempted by merging the Traditional Machine Learning method with Deep Learning techniques to tackle the challenge of sentiment prediction for a massive amount of unstructured review dataset. The proposed architecture aims to utilize the Convolutional Neural Network (CNN) with a backpropagation algorithm to extract embedded feature vectors from the top hidden layer. Thereafter, these vectors augmented to an optimized feature set generated from binary particle swarm optimization (BPSO) method. Finally, a traditional SVM classifier is trained with these extended features set to determine the optimal hyper-plane for separating two classes of review datasets. The evaluation of this research work has been carried out on two benchmark movie review datasets IMDB, SST2. Experimental results with comparative studies based on performance accuracy and F-score value are reported to highlight the benefits of the developed frameworks.

show abstract

“…The theoretical time and space complexities of the SVM model defined here based on various sources [34] [35]. The complexity of SVM mainly depends on the amounts of sampling data.…”

Section: Time Complexitymentioning

confidence: 99%

WITHDRAWN: Exploring the Effectiveness of Convolutional Neural Network with Ensemble Technique

Ghosh¹,

Sanyal²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…CapsNet-static-routing [29]: A capsule network model, which uses static routing algorithm for text categorization tasks.…”

Section: Comparison With Baseline Methods On Imdb Datasetmentioning

confidence: 99%

“…The experimental results demonstrate that capsule network outperforms baseline methods in text classification. Kim et al [29] proposed a static routing algorithm for sentiment classification tasks, which effectively reduced the complexity of routing computation and achieved good results on multiple datasets. Du et al [30] proposed a capsule model based on BGRU for sentiment analysis, which utilizes BGRU and capsule code semantic information together to raise the classification results.…”

Section: Related Workmentioning

confidence: 99%

SC-BiCapsNet: A Sentiment Classification Model Based on Bi-Channel Capsule Network

et al. 2019

View full text Add to dashboard Cite

Most text sentiment classification methods have the shortcomings of insufficient semantic understanding and low classification accuracy. To solve these problems, a sentiment classification model based on capsule network (SC-BiCapsNet) was proposed in this paper. In the stage of word vectorization, the G-Word model is presented to improve the ability of text information representation. In the stage of text semantic representation, the COL-Att model is presented to optimize the semantic coding structure and enhance the effect of text semantic expression. In the stage of text classification, the capsule network is devised, and its core dynamic routing algorithm can increase the weight value of important features, thus improving the accuracy of classification results. This paper evaluates the performance of SC-BiCapsNet model on two text datasets, IMDB and NLPCC 2014 dataset. The experimental results demonstrate that our method outperforms the results of other related models on IMDB dataset and gets the highest accuracy of 0.9238. Meanwhile, comparing with the best system in NLPCC2014-Task II, the F1-scsore of SC-BiCapsNet has increased by at least 1.5%, which proves the validity of SC-BiCapsNet. In the future work, we will try to reduce the time consumption and improve the generalization ability of the model. INDEX TERMS Text sentiment classification, capsule network, dynamic routing algorithm, deep learning.

show abstract

“…To address above problems, the capsule network methods have been proposed [16][17][18], which encapsulate multiple attributes into groups of neurons and replaces the scalar-output feature detectors with vector-output capsules to preserve additional information such as position and correlation [19]. Recently, capsule networks have achieved competitive results in classification tasks [18,20,21], relation extraction [22], especially for those structural information learning tasks [19,23]. In RP task, the entity relationship is usually correlate with their multiple attributes information.…”

Section: Introductionmentioning

confidence: 99%

Attribute-Driven Capsule Network for Entity Relation Prediction

Chen

Gong

Chen

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Multi-attribute entity relation prediction is a novel data mining application about designing an intelligent system that supports inferencing across attributes information. However, most existing deep learning methods capture the inner structural information between different attributes are far more limited. In this paper, we propose an attributedriven approach for entity relation prediction task based on capsule networks that have been shown to demonstrate good performance on relation mining. We develop a self-attention routing method to encapsulate multiple attributes semantic representation into relational semantic capsules and using dynamic routing method to generate class capsules for predicting relations. Due to the lack of multi-attribute entity relation data is a major obstacle in this task, we construct a new real-world multi-attribute entity relation dataset in this work. Experimental results show significant superiority of our model, as compared with other baselines.

show abstract

Text classification using capsules

Cited by 151 publications

References 10 publications

WITHDRAWN: Exploring the Effectiveness of Convolutional Neural Network with Ensemble Technique

WITHDRAWN: Exploring the Effectiveness of Convolutional Neural Network with Ensemble Technique

SC-BiCapsNet: A Sentiment Classification Model Based on Bi-Channel Capsule Network

Attribute-Driven Capsule Network for Entity Relation Prediction

Contact Info

Product

Resources

About