arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07267cs.CLcs.LG
收藏

基于深度神经网络的文本分类主动学习研究综述

A Survey of Active Learning for Text Classification using Deep Neural Networks

University of Leipzig(莱比锡大学)

Christopher Schröder, Andreas Niekler

摘要:

近年来,自然语言处理(NLP)和神经网络(NN)都发生了重大变化。然而,对于主动学习(AL)目的,NN不太常用-尽管它们目前很受欢迎。通过将NN的卓越文本分类性能用于AL,我们可以使用相同的数据量来提高模型的性能,或者减少数据,从而减少所需的注释工作,同时保持相同的性能。我们回顾了使用深度神经网络(DNN)进行文本分类的AL,并详细说明了过去阻碍采用的两个主要原因:(a)NN无法提供可靠的不确定性估计,最常用的查询策略依赖于此,以及(b)在小数据上训练DNN的挑战。为了调查前者,我们构建了一个分类的查询策略,区分基于数据的,基于模型的,基于预测的实例选择,并调查这些类在最近的研究中的流行程度。此外,我们回顾了(D)NN背景下基于NN的NLP最新进展,如词嵌入或语言模型,调查了AL,文本分类和DNN交叉点的当前最新技术水平,并将NLP的最新进展与AL联系起来。最后,我们分析了AL文本分类的最新工作,将各自的查询策略与分类法联系起来,并概述了共性和缺点。因此,我们强调了当前研究的差距,并提出了开放的研究问题。

英文摘要:

Natural language processing (NLP) and neural networks (NNs) have both undergone significant changes in recent years. For active learning (AL) purposes, NNs are, however, less commonly used -- despite their current popularity. By using the superior text classification performance of NNs for AL, we can either increase a model's performance using the same amount of data or reduce the data and therefore the required annotation efforts while keeping the same performance. We review AL for text classification using deep neural networks (DNNs) and elaborate on two main causes which used to hinder the adoption: (a) the inability of NNs to provide reliable uncertainty estimates, on which the most commonly used query strategies rely, and (b) the challenge of training DNNs on small data. To investigate the former, we construct a taxonomy of query strategies, which distinguishes between data-based, model-based, and prediction-based instance selection, and investigate the prevalence of these classes in recent research. Moreover, we review recent NN-based advances in NLP like word embeddings or language models in the context of (D)NNs, survey the current state-of-the-art at the intersection of AL, text classification, and DNNs and relate recent advances in NLP to AL. Finally, we analyze recent work in AL for text classification, connect the respective query strategies to the taxonomy, and outline commonalities and shortcomings. As a result, we highlight gaps in current research and present open research questions.

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。

↑