...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >AELA-DLSTMs: Attention-Enabled and Location-Aware Double LSTMs for aspect-level sentiment classification
【24h】

AELA-DLSTMs: Attention-Enabled and Location-Aware Double LSTMs for aspect-level sentiment classification

机译：AELA-DLSTM：用于方面级别情感分类的启用注意和位置感知的双重LSTM

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Aspect-level sentiment classification, as a fine-grained task in sentiment classification, aiming to extract sentiment polarity from opinions towards a specific aspect word, has been made tremendous improvements in recent years. There are three key factors for aspect-level sentiment classification: contextual semantic information towards aspect words, correlations between aspect words and their context words, and location information of context words with regard to aspect words. In this paper, two models named AE-DLSTMs (Attention-Enabled Double LSTMs) and AELA-DLSTMs (Attention-Enabled and Location-Aware Double LSTMs) are proposed for aspect-level sentiment classification. AE-DLSTMs takes full advantage of the DLSTMs (Double LSTMs) which can capture the contextual semantic information in both forward and backward directions towards aspect words. Meanwhile, a novel attention weights generating method that combines aspect words with their contextual semantic information is designed so that those weights can make better use of the correlations between aspect words and their context words. Besides, we observe that context words with different distances or different directions towards aspect words have different contributions in sentiment polarity. Based on AE-DLSTMs, the location information of context words by assigning different weights is incorporated in AELA-DLSTMs to improve the accuracy. Experiments are conducted on two English datasets and one Chinese dataset. The experimental results have confirmed that our models can make remarkable improvements and outperform all the baseline models in all datasets, improving the accuracy of 1.67 percent to 4.77 percent in different datasets compared with baseline models. (C) 2018 Published by Elsevier B.V.
机译：方面级别的情感分类是情感分类中的一项细粒度任务，旨在从观点到特定方面单词中提取情感极性，近年来已取得了巨大的进步。方面级别的情感分类有三个关键因素：针对方面单词的上下文语义信息，方面单词与其上下文单词之间的相关性以及上下文单词相对于方面单词的位置信息。在本文中，提出了两个模型，分别称为AE-DLSTM（启用了注意的Double LSTM）和AELA-DLSTM（启用了注意和位置感知的Double LSTM）用于方面级别的情感分类。 AE-DLSTM充分利用了DLSTM（双LSTM）的优势，该DLSTM可以捕获朝向方面词的正反两个方向的上下文语义信息。同时，设计了一种新的注意权重生成方法，该方法将方面词与其上下文语义信息相结合，从而可以更好地利用方面词与其上下文词之间的相关性。此外，我们观察到，朝向方面词的距离或方向不同的上下文词对情感极性的贡献也不同。基于AE-DLSTM，通过分配不同的权重将上下文词的位置信息合并到AELA-DLSTM中，以提高准确性。实验在两个英文数据集和一个中文数据集上进行。实验结果证实，我们的模型可以对所有数据集进行显着改进，并且性能优于所有基线模型，与基线模型相比，不同数据集中的准确性提高了1.67％至4.77％。 （C）2018由Elsevier B.V.发布

著录项

  • 来源
    《Neurocomputing》 |2019年第21期|25-34|共10页
  • 作者

    Shuang Kai; Ren Xintao; Yang Qianqian; Li Rui; Loo Jonathan;

  • 作者单位

    Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing, Peoples R China;

    Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing, Peoples R China;

    Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing, Peoples R China;

    Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing, Peoples R China;

    Univ West London, Sch Comp & Engn, London, England;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Neural network; Long short-term memory; Attention mechanism; Aspect-level sentiment classification;

    机译：神经网络;长时短时记忆;注意机制;层面情感分类;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号