Pretraining Sentiment Classifiers with Unlabeled Dialog Data

Toru Shimizu, Nobuyuki Shimizu, Hayato Kobayashi
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
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
more » ... 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-theart strategies including language model pretraining.
doi:10.18653/v1/p18-2121 dblp:conf/acl/ShimizuSK18 fatcat:ylqmofwkl5cetlesfbqv3psxx4