SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis

Code

• github.com/baidu/Senta
  OfficialIn paperpytorch★ 2,007
• github.com/livingbody/paddlenlp_sentiment
  paddle★ 5
• github.com/aaronvvv/sentiment_analysis
  paddle★ 2
• github.com/Mind23-2/MindCode-96
  mindspore★ 0
• github.com/MindSpore-paper-code-3/code9/tree/main/senta
  mindspore★ 0
• github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/sentiment_analysis/skep
  paddle★ 0
• github.com/mindspore-ai/models/blob/master/research/nlp/senta/
  mindspore★ 0

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.

Tasks

Benchmark Results

Reproductions