Investigating Capsule Networks with Dynamic Routing for Text Classification

Zhao, Wei; Ye, Jianbo; Yang, Min; Lei, Zhijun; Zhang, Suofei; Zhao, Zhou

doi:10.18653/v1/d18-1350

Cited by 178 publications

(93 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jaiswal et al reported a capsule-based GAN [70]. Yang et al applied a capsule network to the text domain [71]. Nguyen et al were pioneers in applying capsule networks to the digital media forensics problem [28].…”

Section: Capsule Networkmentioning

confidence: 99%

Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos

Nguyen

Yamagishi

Echizen

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

510

224

View full text Add to dashboard Cite

The revolution in computer hardware, especially in graphics processing units and tensor processing units, has enabled significant advances in computer graphics and artificial intelligence algorithms. In addition to their many beneficial applications in daily life and business, computergenerated/manipulated images and videos can be used for malicious purposes that violate security systems, privacy, and social trust. The deepfake phenomenon and its variations enable a normal user to use his or her personal computer to easily create fake videos of anybody from a short real online video. Several countermeasures have been introduced to deal with attacks using such videos. However, most of them are targeted at certain domains and are ineffective when applied to other domains or new attacks. In this paper, we introduce a capsule network that can detect various kinds of attacks, from presentation attacks using printed images and replayed videos to attacks using fake videos created using deep learning. It uses many fewer parameters than traditional convolutional neural networks with similar performance. Moreover, we explain, for the first time ever in the literature, the theory behind the application of capsule networks to the forensics problem through detailed analysis and visualization.

show abstract

Section: Capsule Networkmentioning

confidence: 99%

Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos

Nguyen

Yamagishi

Echizen

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

510

224

View full text Add to dashboard Cite

show abstract

“…A significant advantage of capsule network is that it performs much better in the transferring single-label to multilabel classification task [13]. Different from traditional deep learning classification models that are based on fully connected network, capsule networks use activity vectors of each capsule in DigitCaps layer to indicate the presence of an instance of each class.…”

Section: Performance Evaluation On Reuters-21578mentioning

confidence: 99%

“…[49], [30], [31] as a kind of supervised representation learning methods, in which groups of neurons are called capsules. Capsule network has been proved effective in learning the intrinsic spatial relationship between features [13], [29], [50]. [13] showed that Capsule networks can help to improve low-data and label transfer learning.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

Peng

Wang

et al. 2021

IEEE Trans. Knowl. Data Eng.

140

View full text Add to dashboard Cite

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics, but how to consider them both coherently is less studied. In addition, most existing methods treat output labels as independent medoids, but ignore the hierarchical relations among them, leading to useful semantic information loss. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding words-matrix representation which preserves both the non-consecutive, long-distance and local sequential semantics. Then the words-matrix is input to the proposed attentional graph capsule recurrent CNNs for more effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.

show abstract

“…Recently, CapsNet has been applied to several NLP tasks like text classification and relation extraction (Yang et al, 2018b;Gong et al, 2018;Xiao et al, 2018;Wang et al, 2018b). CapsNet is able to adaptively decide the information transferred between layers by using dynamic routing.…”

Section: Definitions and Preliminarymentioning

confidence: 99%

Transfer Capsule Network for Aspect Level Sentiment Classification

Chen

Qian

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

182

View full text Add to dashboard Cite

Aspect-level sentiment classification aims to determine the sentiment polarity of a sentence towards an aspect. Due to the high cost in annotation, the lack of aspect-level labeled data becomes a major obstacle in this area. On the other hand, document-level labeled data like reviews are easily accessible from online websites. These reviews encode sentiment knowledge in abundant contexts. In this paper, we propose a Transfer Capsule Network (Tran-sCap) model for transferring document-level knowledge to aspect-level sentiment classification. To this end, we first develop an aspect routing approach to encapsulate the sentence-level semantic representations into semantic capsules from both aspect-level and document-level data. We then extend the dynamic routing approach to adaptively couple the semantic capsules with the class capsules under the transfer learning framework. Experiments on SemEval datasets demonstrate the effectiveness of TransCap.

show abstract

Investigating Capsule Networks with Dynamic Routing for Text Classification

Cited by 178 publications

References 22 publications

Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos

Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

Transfer Capsule Network for Aspect Level Sentiment Classification

Contact Info

Product

Resources

About