SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis
This work addresses the need for better sentiment analysis models by integrating sentiment knowledge into pre-training, though it is incremental as it builds on existing pre-training approaches.
The paper tackles the problem of incorporating sentiment knowledge into pre-training for sentiment analysis by introducing SKEP, which uses sentiment masking and prediction objectives to embed sentiment information at multiple levels, resulting in new state-of-the-art performance on most test datasets.
Recently, sentiment analysis has seen remarkable advance with the help of pre-training approaches. However, sentiment knowledge, such as sentiment words and aspect-sentiment pairs, is ignored in the process of pre-training, despite the fact that they are widely used in traditional sentiment analysis approaches. In this paper, we introduce Sentiment Knowledge Enhanced Pre-training (SKEP) in order to learn a unified sentiment representation for multiple sentiment analysis tasks. With the help of automatically-mined knowledge, SKEP conducts sentiment masking and constructs three sentiment knowledge prediction objectives, so as to embed sentiment information at the word, polarity and aspect level into pre-trained sentiment representation. In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair. Experiments on three kinds of sentiment tasks show that SKEP significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets. We release our code at https://github.com/baidu/Senta.