Large-Scale Text Classification Using Scope-Based Convolutional Neural Network: A Deep Learning Approach

Abstract

Text classification is one of the most important and typical tasks in Natural Language Processing (NLP) which can be applied for many applications. Recently, deep learning approaches has shown their advantages in solving text classification problem, in which Convolutional Neural Network (CNN) is one of the most successful model in the field. In this paper, we propose a novel deep learning approach for categorizing text documents by using scope-based convolutional neural network. Different from windowbased CNN, scope does not require the words that construct a local feature have to be contiguous. It can represent deeper local information of text data. We propose a large-scale scope-based convolutional neural network (LSS-CNN), which is based on scope convolution, aggregation optimization, and max pooling operation. Based on these techniques, we can gradually extract the most valuable local information of the text document. This paper also discusses how to effectively calculate the scope-based information and parallel training for large-scale datasets. Extensive experiments have been conducted on real datasets to compare our model with several state-of-the-art approaches. The experimental results show that LSS-CNN can achieve both effectiveness and good scalability on big text data.

WITHDRAWN: Rider Weed Deep Residual Network-Based Incremental Model for Text Classification Using Multidimensional Features and MapReduce Framework

“…The goal of classifying text is to categorize data into different parts. Here, the goal is to allocate pertinent labels based on the content [3].…”

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

“…Conventionally, these inputs are the stemmed tweets. The CNN model has frequently been used to perform text classification [95]- [100], as well as sentiment analysis task [101]- [105].…”

ATTRACTIVE – An Auto-Updating Database for Experimental Protocols in Regenerative Medicine

“…Next, the algorithm checked whether the assigned category was the same as the label (each article from the training dataset was initially labeled). If the assignment was not consistent with the label, the wrongly assigned article vector would be subtracted from the wrong organ/tissue model vector and the correctly assigned article vector would be added to the correct organ/tissue model, as shown in ( 7) and (8).…”

“…Some previous research used cosine similarity algorithms to cluster similar documents or text into the same category [5]- [7]. Although these cosine similarity algorithms showed good performance in clustering similar text, this method could be improved by adding efficient learning rules to train the classification model using deep learning algorithms [8]- [10], such as convolutional neural networks (CNN) or longshort term memory (LSTM). However, deep learning algorithms require a great deal of labeled data to train the clas- sification model [11]- [13], because they take all the training patterns into consideration and modify the hyperplanes when separating different classes progressively.…”