arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.04513cs.CL
收藏

用于句子分类的多通道变尺度卷积

Multichannel Variable-Size Convolution for Sentence Classification

Center for Information and Language Processing(信息与语言处理中心);University of Munich(慕尼黑大学)

Wenpeng Yin, Hinrich Schütze

摘要:

我们提出了MVCNN,一个卷积神经网络(CNN)结构的句子分类。它(i)结合了不同版本的预训练词嵌入,(ii)用可变大小的卷积滤波器提取多粒度短语的特征。我们还表明,预训练MVCNN对于良好的性能至关重要。MVCNN在四个任务上实现了最先进的性能:小规模二进制,小规模多类和大规模Twitter情感预测以及主观分类。

英文摘要:

We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification. It (i) combines diverse versions of pretrained word embeddings and (ii) extracts features of multigranular phrases with variable-size convolution filters. We also show that pretraining MVCNN is critical for good performance. MVCNN achieves state-of-the-art performance on four tasks: on small-scale binary, small-scale multi-class and largescale Twitter sentiment prediction and on subjectivity classification.

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。

↑