SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis

TL;DR

SKEP introduces a sentiment knowledge-enhanced pre-training method that incorporates sentiment words and aspect-sentiment pairs into the model, significantly improving performance across multiple sentiment analysis tasks.

Contribution

This paper presents a novel pre-training approach that embeds sentiment knowledge, such as sentiment words and aspect-sentiment pairs, into unified representations for various sentiment analysis tasks.

Findings

SKEP outperforms strong baselines on multiple sentiment tasks.

Achieves new state-of-the-art results on most datasets.

Effectively captures sentiment dependencies at word, polarity, and aspect levels.

Abstract

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.