Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification
Hsin-Ping Huang | Junyi Jessy Li
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
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.