Hierarchical Attention Generative Adversarial Networks for Cross-domain Sentiment Classification

Yuebing Zhang; Duoqian Miao; Jiaqi Wang

Hierarchical Attention Generative Adversarial Networks for Cross-domain Sentiment Classification

Machine Learning 2019-03-28 v1 Machine Learning

Authors: Yuebing Zhang , Duoqian Miao , Jiaqi Wang

Abstract

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for cross-domain sentiment classification task, many of which use Gradient Reversal Layer (GRL) to design an adversarial network structure to train a domain-shared sentiment classifier. Different from those methods, we proposed Hierarchical Attention Generative Adversarial Networks (HAGAN) which alternately trains a generator and a discriminator in order to produce a document representation which is sentiment-distinguishable but domain-indistinguishable. Besides, the HAGAN model applies Bidirectional Gated Recurrent Unit (Bi-GRU) to encode the contextual information of a word and a sentence into the document representation. In addition, the HAGAN model use hierarchical attention mechanism to optimize the document representation and automatically capture the pivots and non-pivots. The experiments on Amazon review dataset show the effectiveness of HAGAN.

Keywords

generative adversarial network heterogeneous graph learning hierarchical classification

Cite

@article{arxiv.1903.11334,
  title  = {Hierarchical Attention Generative Adversarial Networks for Cross-domain Sentiment Classification},
  author = {Yuebing Zhang and Duoqian Miao and Jiaqi Wang},
  journal= {arXiv preprint arXiv:1903.11334},
  year   = {2019}
}

Hierarchical Attention Generative Adversarial Networks for Cross-domain Sentiment Classification

Abstract

Keywords

Cite

Related papers