A Neural Network Model for Hierarchical Multilingual Text Categorization

Chau, Rowena; Yeh, Chung‐Hsing; Smith, Kate

doi:10.1007/11427445_38

Cited by 14 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Li et al [19] proposed a hybrid classification model based on sentiment dictionary, support vector machine (SVM) and k-nearest neighbor (KNN) for sentiment classification of Chinese micro-blogs. Chau et al [4] improved neural network algorithm to achieve multilingual text classification task. Sabbah et al [27] proposed four modified frequency-based term weighting schemes, which is combined with common text classifiers such as SVM, KNN, naive Bayes (NB) and extreme learning machine, and tested in the text classification corpora.…”

Section: Related Workmentioning

confidence: 99%

Text Classification of Public Feedbacks using Convolutional Neural Network Based on Differential Evolution Algorithm

Zhang

Chen

Huang

et al. 2019

INT J COMPUT COMMUN

View full text Add to dashboard Cite

Online feedback is an effective way of communication between government departments and citizens. However, the daily high number of public feedbacks has increased the burden on government administrators. The deep learning method is good at automatically analyzing and extracting deep features of data, and then improving the accuracy of classification prediction. In this study, we aim to use the text classification model to achieve the automatic classification of public feedbacks to reduce the work pressure of administrator. In particular, a convolutional neural network model combined with word embedding and optimized by differential evolution algorithm is adopted. At the same time, we compared it with seven common text classification models, and the results show that the model we explored has good classification performance under different evaluation metrics, including accuracy, precision, recall, and F1-score.

show abstract

Section: Related Workmentioning

confidence: 99%

Text Classification of Public Feedbacks using Convolutional Neural Network Based on Differential Evolution Algorithm

Zhang

Chen

Huang

et al. 2019

INT J COMPUT COMMUN

View full text Add to dashboard Cite

show abstract

“…Neural network have also been widely used in text categorization. Chau et al [5] proposed an intelligent method for enabling concept-based hierarchical multilingual text categorization. Through their method, a universal concept space was constructed and a set of concept-based multilingual document categories were generated.…”

Section: Related Workmentioning

confidence: 99%

A Text Categorization Method Based on Improved k-means and BP Neural Network

Xia

Jia

2013

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

K-means is a widely used cluster algorithm. It is widely used in text categorization as an unsupervised method. However, it could be easily affected by some isolated observations. BP neural network is usually used for text categorization because it's superiority in handling non-linear problem. However, sometimes it could not achieve high performance. Based on the combination of these two algorithms, we propose a new text categorization algorithm. We first improve k-means clustering algorithm. After that, we use it to cluster vectors in our vector space model. And then, BP neural network is used to categorize the preprocessed vectors. The experiments show that our algorithm could achieve a high performance than the traditional BP neural network text categorization method.

show abstract

“…On the other hand, parallel corpora were used as language resources in Chau et al [19] and Wei et al [20]. Chau et al [19] developed a technique of supervised text categorization enabling unsupervised document clustering to be executed in a multilingual setting, in which language-independent concept-based vectors representing multilingual documents were generated by applying an SOM algorithm to a parallel corpus, and as a result, a hierarchy of document categories was constructed based on the vectors. In Wei et al [20], a latent semantic indexing (LSI) technique was applied to MLDC.…”

Section: Literature On Multilingual Document Clusteringmentioning

confidence: 99%

Double-pass clustering technique for multilingual document collections

Kishida

2011

Journal of Information Science

View full text Add to dashboard Cite

It is often necessary to categorize automatically multilingual document sets, in which documents written in a variety of languages are included, into topically homogeneous subsets, such as when applying an automatic summarization system for multilingual news articles. However, there have been few studies on multilingual document clustering to date. In particular, it is not known whether clustering techniques are effective in medium- or large-scale multilingual document sets. For scalability, techniques should be based on dictionary-based translation and a single- or double-pass clustering algorithm. This article reports on experiments of applying multilingual document clustering to medium-scale sets of English, French, German and Italian documents (Reuters news articles). The results show that the double-pass algorithm has a positive effect in the case that each document is translated. On the other hand, the cluster translation strategy in which clusters obtained by applying a clustering algorithm to each language document set are translated has almost no effect. Also, translation disambiguation techniques can improve, but only slightly, the effectiveness of clustering.

show abstract

A Neural Network Model for Hierarchical Multilingual Text Categorization

Cited by 14 publications

References 7 publications

Text Classification of Public Feedbacks using Convolutional Neural Network Based on Differential Evolution Algorithm

Text Classification of Public Feedbacks using Convolutional Neural Network Based on Differential Evolution Algorithm

A Text Categorization Method Based on Improved k-means and BP Neural Network

Double-pass clustering technique for multilingual document collections

Contact Info

Product

Resources

About