Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence. However, it is always sensitive to the multi-aspect challenge, where features of multiple aspects in a sentence will affect each other. To mitigate this issue, we design a novel training framework, called Contrastive Cross-Channel Data Augmentation (C3 DA), which leverages an in-domain generator to construct more multi-aspect samples and then boosts the robustness of ABSA models via contrastive learning on these generated data. In practice, given a generative pretrained language model and some limited ABSA labeled data, we first employ some parameter-efficient approaches to perform the in-domain fine-tuning. Then, the obtained in-domain generator is used to generate the synthetic sentences from two channels, i.e., Aspect Augmentation Channel and Polarity Augmentation Channel, which generate the sentence condition on a given aspect and polarity respectively. Specifically, our C3 DA performs the sentence generation in a cross-channel manner to obtain more sentences, and proposes an Entropy-Minimization Filter to filter low-quality generated samples. Extensive experiments show that our C3 DA can outperform those baselines without any augmentations by about 1% on accuracy and Macro- F1. Code and data are released in https://github.com/wangbing1416/C3DA.
翻译:以外观为基础的情绪分析(ABSA) 是一种精细的情感分析任务, 重点是检测对句子中部分的情绪极极极性。 但是, 它总是敏感地关注多方形的挑战, 句子中多个方面的特点会相互影响 。 为了缓解这一问题, 我们设计了一个新型的培训框架, 名为“ 相交跨通道数据增强( C3 DA ) ”, 它利用一个在部内生成的生成器来构建更多的多层样本, 然后通过在这些生成的数据上进行对比性学习来提升ABSA模型的稳健性。 在实践中, 由于具有基因化的预先培训语言模型和一些有限的ABSA标签数据, 我们首先使用一些具有参数效率的方法来进行内部微调。 然后, 我们从部内获取的生成的生成器用于生成两个渠道的合成句, 即“ 外观增强频度频道和极度增强频道” 。 具体地说, 我们的C3 DA 以跨通道过滤器3 的方式进行生成的句子生成, 以不具有跨层级级的版本级的版本的版本 3, 显示任何磁基级的磁标 。