MaskAE:基于无监督的短文本情感迁移方法

基于无监督的文本情感迁移技术是通过迁移原句子情感并且保持句子内容不变,生成带有其他情感的新句子的技术。这项技术在两个方面富有挑战性:第一,没有平行语料;第二,文本属性纠缠问题,即当改变句子情感时,通常难以保证句子内容不变。该文提出了一个基于掩码自编码器(mask-autoEncoder,MaskAE)的文本情感迁移方法。首先,利用情感词典来匹配句子中的情感词并用"mask"符号标记它;之后,利用MaskAE模型生成被标记的情感词,保持其他词不变,从而缓解属性纠缠问题。在模型训练过程中,利用情感判别器去控制生成句子的情感,从而解决没有平行语料问题。实验结果表明,该文模型简单有效,与当前先进模型比较,在自动评价指标和人工评价指标上均有提升,生成的句子在语法和语义正确性上的表现也更好。

MaskAE: Unsupervised Short Text Sentiment Transfer Method

This paper proposed a unsupervised text sentiment transfer solution by MaskAE model. Firstly, the sentiment words in the sentence are detected by a dictionary and then replaced by "mask". The MaskAE model is used to generate the masked sentiment words, with the other words unchanged, to alleviate the text attribute entanglement problem. In model training, we use sentiment discriminator to control the sentiment of generated sentences, avoding the dependence on parallel corpus. The experimental results show that our model has improved in both automatic evaluation metrics and human evaluation metrics. And the generated sentences also perform better in grammar and semantic correctness.