[4G2] 自然言語処理-対話システム(2)

[4G2-04] Semi-supervised Sentiment Classification with Dialog Data

〇Toru Shimizu¹, Hayato Kobayashi^1,2, Nobuyuki Shimizu¹ (1. Yahoo Japan Corporation, 2. RIKEN AIP)

キーワード：Sentiment Analysis, Semi-supervised Learning, Dialog

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.