arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.05694cs.CLcs.LGstat.ML
收藏

基于多项对抗网络的多领域文本分类

Multinomial Adversarial Networks for Multi-Domain Text Classification

Xilun Chen, Claire Cardie

摘要:

许多文本分类任务都是高度依赖于领域的。不幸的是,训练数据的可用性在不同的域之间可能会有很大的差异。更糟糕的是,对于某些领域,可能根本没有任何注释数据。在这项工作中,我们提出了一个多项对抗网络(MAN)来解决这个现实世界的多域设置(MDTC)中的文本分类问题。我们为MAN框架提供了理论依据,证明了MAN的不同实例本质上是多个概率分布中各种f-散度度量(Ali和Silvey,1966)的最小化者。因此,MAN在理论上是对传统对抗网络的合理概括,它可以区分两种分布。更具体地说,对于MDTC任务,MAN通过利用其减少每个域的特征分布之间的分歧的能力来学习跨多个域不变的特征。我们目前的实验结果表明,MAN显着优于现有技术的MDTC任务。我们还表明,MAN实现国家的最先进的性能域没有标记的数据。

英文摘要:

Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains. Worse still, for some domains there may not be any annotated data at all. In this work, we propose a multinomial adversarial network (MAN) to tackle the text classification problem in this real-world multidomain setting (MDTC). We provide theoretical justifications for the MAN framework, proving that different instances of MANs are essentially minimizers of various f-divergence metrics (Ali and Silvey, 1966) among multiple probability distributions. MANs are thus a theoretically sound generalization of traditional adversarial networks that discriminate over two distributions. More specifically, for the MDTC task, MAN learns features that are invariant across multiple domains by resorting to its ability to reduce the divergence among the feature distributions of each domain. We present experimental results showing that MANs significantly outperform the prior art on the MDTC task. We also show that MANs achieve state-of-the-art performance for domains with no labeled data.

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。

↑