一种基于联合深度学习模型的情感分类方法
发布时间：2018-07-22 11:38
【摘要】：针对情感分类问题中长句和短句具有不同的建模特点,提出了一种基于联合深度学习模型的情感分类方法。该方法融合长短期记忆(long-short term memory,LSTM)模型与卷积神经网络(convolutional neural network,CNN)对影视评论数据进行情感极性判别;采用LSTM对上下文进行建模,通过逐词迭代得到上下文的特征向量;采用CNN模型从词向量序列中自动发现特征,抽取局部特征并整合成全局特征来提高分类效果。所提出的方法在COAE2016评测的任务2的情感极性分类任务中,取得最高的系统准确率。
[Abstract]:Aiming at the different modeling characteristics of long sentence and short sentence in affective classification, a method of emotion classification based on joint deep learning model is proposed. This method combines long-short term memory LSTM model with convolutional neural network (convolutional neural network to judge the emotional polarity of video review data, uses LSTM to model the context, and obtains the feature vector of the context by word iteration. The CNN model is used to automatically discover features from word vector sequences, extract local features and integrate them into global features to improve the classification effect. The proposed method achieves the highest system accuracy in the classification of emotional polarity of task 2 evaluated by COAE2016.
【作者单位】： 哈尔滨工业大学计算机科学与技术学院机器智能与翻译实验室;
【基金】：国家自然科学基金资助项目(61402134)
【分类号】：TP391.1
本文编号：2137326
[Abstract]:Aiming at the different modeling characteristics of long sentence and short sentence in affective classification, a method of emotion classification based on joint deep learning model is proposed. This method combines long-short term memory LSTM model with convolutional neural network (convolutional neural network to judge the emotional polarity of video review data, uses LSTM to model the context, and obtains the feature vector of the context by word iteration. The CNN model is used to automatically discover features from word vector sequences, extract local features and integrate them into global features to improve the classification effect. The proposed method achieves the highest system accuracy in the classification of emotional polarity of task 2 evaluated by COAE2016.
【作者单位】： 哈尔滨工业大学计算机科学与技术学院机器智能与翻译实验室;
【基金】：国家自然科学基金资助项目(61402134)
【分类号】：TP391.1
【相似文献】
相关硕士学位论文 前1条
1 陈浩;基于中层语义特征表达的物体检测方法研究[D];北京工业大学;2016年
，本文编号：2137326
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2137326.html
