A Novel BGCapsule Network for Text Classification

نویسندگان

چکیده

Several text classification tasks such as sentiment analysis, news categorization, multi-label and opinion are challenging problems even for modern deep learning networks. Recently, Capsule Networks (CapsNets) proposed image classification. It has been shown that CapsNets have several advantages over Convolutional Neural (CNNs), while their validity in the domain of was less explored. In this paper, we propose a novel hybrid architecture viz., BGCapsule, which is model preceded by an ensemble Bidirectional Gated Recurrent Units (BiGRU) tasks. We employed GRUs feature extraction layer preceding primary capsule layer. The architecture, after performing basic pre-processing steps, consists five layers: embedding based on GloVe, BiGRU-based layer, flatten fully connected ReLU followed softmax To evaluate effectiveness conducted extensive experiments benchmark datasets (ranging from 10,000 records to 700,000 records) including Movie Review (MR Imdb 2005), AG’s News dataset, Dbpedia ontology Yelp Full dataset review polarity dataset. These benchmarks cover multiclass classification, found our (BGCapsule) achieves better accuracy compared existing methods without help any external linguistic knowledge positive keywords negative keywords. Further, BGCapsule converged faster other extant techniques.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Novel One Sided Feature Selection Method for Imbalanced Text Classification

The imbalance data can be seen in various areas such as text classification, credit card fraud detection, risk management, web page classification, image classification, medical diagnosis/monitoring, and biological data analysis. The classification algorithms have more tendencies to the large class and might even deal with the minority class data as the outlier data. The text data is one of t...

متن کامل

Bayesian network models for hierarchical text classification from a thesaurus

We propose a method which, given a document to be classified, automatically generates an ordered set of appropriate descriptors extracted from a thesaurus. The method creates a Bayesian network to model the thesaurus and uses probabilistic inference to select the set of descriptors having high posterior probability of being relevant given the available evidence (the document to be classified). ...

متن کامل

A C-LSTM Neural Network for Text Classification

Neural network models have been demonstrated to be capable of achieving remarkable performance in sentence and document modeling. Convolutional neural network (CNN) and recurrent neural network (RNN) are two mainstream architectures for such modeling tasks, which adopt totally different ways of understanding natural languages. In this work, we combine the strengths of both architectures and pro...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: SN computer science

سال: 2021

ISSN: ['2661-8907', '2662-995X']

DOI: https://doi.org/10.1007/s42979-021-00963-4