@article{ma2018hierarchical,
title={A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification},
author={Ma, Shuming and Sun, Xu and Lin, Junyang and Ren, Xuancheng},
journal={arXiv preprint arXiv:1805.01089},
year={2018}
}
title
A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification
notes
首先使用双向LSTM编码输入的评论正文，然后使用attention得到每个位置的context向量，使用context向量去预测当前位置的摘要输出。然后再用相同的attention方法，不同的参数，再得到一组context向量，使用每个时刻的context和每个时刻的encoder的隐状态拼接起来，去预测评论情感分类。最终情感分类和评论摘要都得到了提升。
bibtex
@article{ma2018hierarchical, title={A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification}, author={Ma, Shuming and Sun, Xu and Lin, Junyang and Ren, Xuancheng}, journal={arXiv preprint arXiv:1805.01089}, year={2018} }
link
https://scholar.google.com/scholar_url?url=https://arxiv.org/pdf/1805.01089&hl=zh-CN&sa=T&oi=gsb-gga&ct=res&cd=0&ei=URn9Wr2wOce0yATE16Uo&scisig=AAGBfm0UHOpgTTwKsJ1Hwc5u6FNuiTenVw
publication
IJCAI 2018
open source
No
affiliated
Peking University