Adversarial Domain Adaptation Network for Semantic Role Classification

Haitong YANG  Guangyou ZHOU  Tingting HE  Maoxi LI  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.12   pp.2587-2594
Publication Date: 2019/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDP7087
Type of Manuscript: PAPER
Category: Natural Language Processing
argument classification,  domain adaption,  adversarial domain adaptation,  supervised learning,  

Full Text: PDF(873.9KB)>>
Buy this Article

In this paper, we study domain adaptation of semantic role classification. Most systems utilize the supervised method for semantic role classification. But, these methods often suffer severe performance drops on out-of-domain test data. The reason for the performance drops is that there are giant feature differences between source and target domain. This paper proposes a framework called Adversarial Domain Adaption Network (ADAN) to relieve domain adaption of semantic role classification. The idea behind our method is that the proposed framework can derive domain-invariant features via adversarial learning and narrow down the gap between source and target feature space. To evaluate our method, we conduct experiments on English portion in the CoNLL 2009 shared task. Experimental results show that our method can largely reduce the performance drop on out-of-domain test data.