Work

Japanese Sentiment Classification with Stacked Denoising Auto-Encoder using Distributed Word Representation

Year: 2015
Type: conference-paper
Abstract: Traditional sentiment classification methods often require polarity dictionaries or crafted features to utilize machine learning.However, those approaches incur high costs in the making of dictionaries and/or features, which hinder generalization of tasks.Examples of these approaches include an approach that uses a polarity dictionary that cannot handle unknown or newly invented words and another approach that uses a complex model with 13 types of feature templates.We propose a novel high performance sentiment classification method with stacked denoising auto-encoders that uses distributed word representation instead of building dictionaries or utilizing engineering features.The results of experiments conducted indicate that our model achieves state-of-the-art performance in Japanese sentiment classification tasks.
Language: English
Open Access status: green
OpenAlex ID: W2402082582
FWCI: 0.916
Cites: 28
Cited by: 11
Related to: 10