@InProceedings{shimizu-shimizu-kobayashi:2018:Short,
  author    = {Shimizu, Toru  and  Shimizu, Nobuyuki  and  Kobayashi, Hayato},
  title     = {Pretraining Sentiment Classifiers with Unlabeled Dialog Data},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {764--770},
  abstract  = {The huge cost of creating labeled training data is a common problem for supervised learning tasks such as sentiment classification. Recent studies showed that pretraining with unlabeled data via a language model can improve the performance of classification models. In this paper, we take the concept a step further by using a conditional language model, instead of a language model. Specifically, we address a sentiment classification task for a tweet analysis service as a case study and propose a pretraining strategy with unlabeled dialog data (tweet-reply pairs) via an encoder-decoder model. Experimental results show that our strategy can improve the performance of sentiment classifiers and outperform several state-of-the-art strategies including language model pretraining.},
  url       = {http://www.aclweb.org/anthology/P18-2121}
}