arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.11857cs.CL
收藏

基于混合分块卷积神经网络的文本情感分类

Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification

Bucharest University of Economic Studies(布加勒斯特经济研究大学);Maastricht University(马斯特里赫特大学)

Maria Mihaela Trusca, Gerasimos Spanakis

摘要:

平铺卷积神经网络(平铺CNN)仅应用于计算机视觉以学习不变性。我们将其架构调整为NLP,以提高情感分析中最显著特征的提取。知道在NLP领域的平铺CNN的主要缺点是其不灵活的过滤器结构,我们提出了一种称为混合平铺CNN的新架构,该架构仅对出现在相似上下文中的单词及其相邻单词应用过滤器(这是防止丢失一些n-gram的必要步骤)。在IMDB电影评论和SemEval 2017数据集上的实验证明了混合平铺CNN的效率,其性能优于CNN和平铺CNN。

英文摘要:

The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the tiled CNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled CNN that applies a filter only on the words that appear in the similar contexts and on their neighbor words (a necessary step for preventing the loss of some n-grams). The experiments on the datasets of IMDB movie reviews and SemEval 2017 demonstrate the efficiency of the hybrid tiled CNN that performs better than both CNN and tiled CNN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑