当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
A Label Proportions Estimation Technique for Adversarial Domain Adaptation in Text Classification
arXiv - CS - Machine Learning Pub Date : 2020-03-16 , DOI: arxiv-2003.07444 Zhuohao Chen, Singla Karan, David C. Atkins, Zac E Imel, Shrikanth Narayanan
arXiv - CS - Machine Learning Pub Date : 2020-03-16 , DOI: arxiv-2003.07444 Zhuohao Chen, Singla Karan, David C. Atkins, Zac E Imel, Shrikanth Narayanan
Many text classification tasks are domain-dependent, and various domain
adaptation approaches have been proposed to predict unlabeled data in a new
domain. Domain-adversarial neural networks (DANN) and their variants have been
used widely recently and have achieved promising results for this problem.
However, most of these approaches assume that the label proportions of the
source and target domains are similar, which rarely holds in most real-world
scenarios. Sometimes the label shift can be large and the DANN fails to learn
domain-invariant features. In this study, we focus on unsupervised domain
adaptation of text classification with label shift and introduce a domain
adversarial network with label proportions estimation (DAN-LPE) framework. The
DAN-LPE simultaneously trains a domain adversarial net and processes label
proportions estimation by the confusion of the source domain and the
predictions of the target domain. Experiments show the DAN-LPE achieves a good
estimate of the target label distributions and reduces the label shift to
improve the classification performance.
中文翻译:
文本分类中对抗域自适应的标签比例估计技术
许多文本分类任务都依赖于域,并且已经提出了各种域适应方法来预测新域中的未标记数据。领域对抗神经网络 (DANN) 及其变体最近已被广泛使用,并在此问题上取得了可喜的成果。然而,这些方法中的大多数都假设源域和目标域的标签比例相似,这在大多数现实世界场景中很少适用。有时标签偏移可能很大并且 DANN 无法学习域不变特征。在这项研究中,我们专注于具有标签移位的文本分类的无监督域适应,并引入了具有标签比例估计(DAN-LPE)框架的域对抗网络。DAN-LPE 同时训练域对抗网络并通过源域和目标域的预测的混淆处理标签比例估计。实验表明,DAN-LPE 实现了对目标标签分布的良好估计,并减少了标签偏移以提高分类性能。
更新日期:2020-03-27
中文翻译:
文本分类中对抗域自适应的标签比例估计技术
许多文本分类任务都依赖于域,并且已经提出了各种域适应方法来预测新域中的未标记数据。领域对抗神经网络 (DANN) 及其变体最近已被广泛使用,并在此问题上取得了可喜的成果。然而,这些方法中的大多数都假设源域和目标域的标签比例相似,这在大多数现实世界场景中很少适用。有时标签偏移可能很大并且 DANN 无法学习域不变特征。在这项研究中,我们专注于具有标签移位的文本分类的无监督域适应,并引入了具有标签比例估计(DAN-LPE)框架的域对抗网络。DAN-LPE 同时训练域对抗网络并通过源域和目标域的预测的混淆处理标签比例估计。实验表明,DAN-LPE 实现了对目标标签分布的良好估计,并减少了标签偏移以提高分类性能。