Ajou University repository

Large scale text classification with efficient word embedding
Citations

SCOPUS

0

Citation Export

Publication Year
2018-01-01
Journal
Lecture Notes in Electrical Engineering
Publisher
Springer Verlag
Citation
Lecture Notes in Electrical Engineering, Vol.425, pp.465-469
Mesh Keyword
CNN modelsConvolutional neural networkDe noiseLarge-scale datasetsText classificationWord level
All Science Classification Codes (ASJC)
Industrial and Manufacturing Engineering
Abstract
This article offers an empirical exploration on the efficient use of word-level convolutional neural networks (word-CNN) for large-scale text classification. Generally, the word-CNNs are difficult to train on large-scale datasets as the size of word embedding dramatically increases as the size of vocabulary increases. In order to handle this issue, this paper presents a de-noise approach to word embedding. We compare our model with several recently proposed CNN models on publicly available dataset. The experimental results show that proposed method improves the usefulness of word-CNN and increases the accuracy of text classification.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36343
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85022219023&origin=inward
DOI
https://doi.org/2-s2.0-85022219023
Journal URL
http://www.springer.com/series/7818
Type
Conference
Funding
This research was supported by the MISP(Ministry of Science, ICT & Future Planning), Korea, under the National Program for Excellence in SW) supervised by the IITP(Institute for Information & communications Technology Promotion).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Chung, Tae-Sun Image
Chung, Tae-Sun정태선
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.