Text Understanding from Scratch
Xiang Zhang Yann LeCun Computer Science Department, Courant Institute of Mathematical Sciences, New York University
Abstract
This article demonstrates 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(LeCun et al., 1998) (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.
中文速览
用卷积神经网络（ConvNet）直接从字符级别理解文本，过去普遍认为这类任务离不开分词、句法分析等语言学预处理，而这篇论文偏偏要绕开这些"人类知识"，让模型从原始字符序列出发自己学。研究者设计了一个9层的时序卷积网络（temporal ConvNet），把每个字符编码成固定维度的向量后直接输入模型，在本体分类、情感分析、文本分类等多个百万级大规模数据集上展开实验。结果表明，这种"从零学起"的字符级卷积网络不仅能媲美甚至超越依赖词向量（word2vec）或词袋特征的传统方法，还同时适用于英文和中文。这项工作的意义在于，它证明了深度学习可以在不依赖任何语言学结构先验知识的情况下完成复杂的文本理解任务，为构建跨语言、低工程量的文本处理系统提供了新的可能。
原文 arXiv:1502.01710;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1502.01710v5