Hierarchical Attention Generative Adversarial Networks for Cross-domain Sentiment Classification
This addresses the problem of domain adaptation in sentiment classification for applications like review analysis, but it is incremental as it builds on existing adversarial methods.
The paper tackles cross-domain sentiment classification by proposing Hierarchical Attention Generative Adversarial Networks (HAGAN) to generate document representations that are sentiment-distinguishable but domain-indistinguishable, achieving effectiveness as shown in experiments on the Amazon review dataset.
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.