Large-Scale Text Classification with Deep Neural Networks

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long- Short Term Memory...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:KIISE Transactions on Computing Practices Ročník 23; číslo 5; s. 322 - 327
Hlavní autoři: Jo, Hwiyeol, Kim, Jin-Hwa, Kim, Kyung-Min, Chang, Jeong-Ho, Eom, Jae-Hong, Zhang, Byoung-Tak
Médium: Journal Article
Jazyk:angličtina
Vydáno: Korean Institute of Information Scientists and Engineers 15.05.2017
한국정보과학회
Témata:
컴퓨터학
deep learning
artificial neural networks
자연어 처리
인공신경망
대용량 문서 분류
natural language processing
large-scale text classification
딥러닝
ISSN:2383-6318, 2383-6326
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long- Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment’s result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers. KCI Citation Count: 4
ISSN:2383-6318
2383-6326
DOI:10.5626/KTCP.2017.23.5.322