arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1702.01923cs.CL
收藏

自然语言处理中CNN和RNN的比较研究

Comparative Study of CNN and RNN for Natural Language Processing

LMU Munich(慕尼黑大学);IBM Research(IBM研究院)

Wenpeng Yin, Katharina Kann, Mo Yu, Hinrich Schütze

摘要:

深度神经网络(DNN)彻底改变了自然语言处理(NLP)领域。卷积神经网络(CNN)和递归神经网络(RNN)是DNN架构的两种主要类型,被广泛探索以处理各种NLP任务。CNN被认为擅长于提取位置不变的特征,而RNN则擅长于按顺序提取建模单元。由于CNN和RNN之间的斗争,许多NLP任务的最新技术经常发生变化。这项工作是CNN和RNN在广泛的代表性NLP任务上的首次系统比较,旨在为DNN的选择提供基本指导。

英文摘要:

Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP). Convolutional neural network (CNN) and recurrent neural network (RNN), the two main types of DNN architectures, are widely explored to handle various NLP tasks. CNN is supposed to be good at extracting position-invariant features and RNN at modeling units in sequence. The state of the art on many NLP tasks often switches due to the battle between CNNs and RNNs. This work is the first systematic comparison of CNN and RNN on a wide range of representative NLP tasks, aiming to give basic guidance for DNN selection.

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。

↑