论文标题
无监督的对抗领域适应隐式话语关系分类
Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification
论文作者
论文摘要
隐含的话语关系不仅比明确的对应物更具挑战性，而且要注释。我们解决缺乏隐式关系数据的培训数据，并利用明确关系的域适应性（Ji等，2015）。我们提出了一个配备了重建组件的无监督对抗域自适应网络。我们的系统的表现优于先前的工作和其他对抗性基准，用于无监督的域适应。此外，如果有些可用，我们将扩展系统以利用标记的数据。
Implicit discourse relations are not only more challenging to classify, but also to annotate, than their explicit counterparts. We tackle situations where training data for implicit relations are lacking, and exploit domain adaptation from explicit relations (Ji et al., 2015). We present an unsupervised adversarial domain adaptive network equipped with a reconstruction component. Our system outperforms prior works and other adversarial benchmarks for unsupervised domain adaptation. Additionally, we extend our system to take advantage of labeled data if some are available.
