Text Understanding from Scratch
Text Understanding from Scratch
复制标题
DOI：
--
复制
发表时间：
2015-02
期刊：
影响因子：
--
通讯作者：
Xiang Zhang-;Yann LeCun
中科院分区：
文献类型：
--
作者：
Xiang Zhang-;Yann LeCun
本文展示了我们可以使用时间卷积网络（ConvNets）将深度学习应用于文本理解，从字符级输入一直到抽象文本概念。我们将ConvNets应用于各种大规模数据集，包括本体分类，情感分析和文本分类。我们表明，时间ConvNets可以在不了解单词，短语，句子和任何其他人类语言的句法或语义结构的情况下实现惊人的性能。证据表明，我们的模型可以工作的英语和汉语。
This article demontrates that we can apply deep learning to text understanding from character-level inputs all the way up to abstract text concepts, using temporal convolutional networks (ConvNets). We apply ConvNets to various large-scale datasets, including ontology classification, sentiment analysis, and text categorization. We show that temporal ConvNets can achieve astonishing performance without the knowledge of words, phrases, sentences and any other syntactic or semantic structures with regards to a human language. Evidence shows that our models can work for both English and Chinese.