Multi-Domain Sentiment Classification Based on Domain-Aware Embedding and
Attention
Abstract
Sentiment classification is a fundamental task in
NLP. However, as revealed by many researches,
sentiment classification models are highly domaindependent. It is worth investigating to leverage
data from different domains to improve the classification performance in each domain. In this
work, we propose a novel completely-shared multidomain neural sentiment classification model to
learn domain-aware word embeddings and make
use of domain-aware attention mechanism. Our
model first utilizes BiLSTM for domain classi-
fication and extracts domain-specific features for
words, which are then combined with general word
embeddings to form domain-aware word embeddings. Domain-aware word embeddings are fed
into another BiLSTM to extract sentence features.
The domain-aware attention mechanism is used for
selecting significant features, by using the domainaware sentence representation as the query vector. Evaluation results on public datasets with 16
different domains demonstrate the efficacy of our
proposed model. Further experiments show the
generalization ability and the transferability of our
model