@inproceedings{zhou-etal-2020-sentix,
    title = "{S}enti{X}: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis",
    author = "Zhou, Jie  and
      Tian, Junfeng  and
      Wang, Rui  and
      Wu, Yuanbin  and
      Xiao, Wenming  and
      He, Liang",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.coling-main.49/",
    doi = "10.18653/v1/2020.coling-main.49",
    pages = "568--579",
    abstract = "Pre-trained language models have been widely applied to cross-domain NLP tasks like sentiment analysis, achieving state-of-the-art performance. However, due to the variety of users' emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain. In this paper, we pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets, and utilize it for cross-domain sentiment analysis task without fine-tuning. We propose several pre-training tasks based on existing lexicons and annotations at both token and sentence levels, such as emoticons, sentiment words, and ratings, without human interference. A series of experiments are conducted and the results indicate the great advantages of our model. We obtain new state-of-the-art results in all the cross-domain sentiment analysis tasks, and our proposed SentiX can be trained with only 1{\%} samples (18 samples) and it achieves better performance than BERT with 90{\%} samples."
}