A Contrastive Cross-Channel Data Augmentation Framework for Aspect-Based Sentiment Analysis

Proceedings of the 29th International Conference on Computational Linguistics, pages 6691–6704 October 12–17, 2022. 6691 A Contrastive Cross-Channel Data Augmentation Framework for Aspect-Based Sentiment Analysis Bing Wang1∗, Liang Ding2†, Qihuang Zhong4, Ximing Li1, Dacheng Tao2,3 1College of Computer Science and Technology, Jilin University 2JD Explore Academy 3The University of Sydney 4Wuhan University dingliang1@jd.com, liximing86@gmail.com Abstract Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which fo- cuses on detecting the sentiment polarity to- wards 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 (C3DA), which leverages an in-domain genera- tor 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 ap- proaches 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 as- pect and polarity respectively. Specifically, our C3DA 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. Exten- sive experiments show that our C3DA can out- perform those baselines without any augmen- tations by about 1% on accuracy and Macro- F1. Code and data are released in https: //github.com/wangbing1416/C3DA. 1 Introduction Sentiment Analysis (SA) is a typical Natural Lan- guage Understanding (NLU) task to predict the sentence-level sentiment polarities (Pang and Lee, 2007; Liu, 2012). However, since a single review sentence always exists multiple polarities, Aspect- based Sentiment Analysis (ABSA), a fine-grained ∗Work was done when Bing and Qihuang were interning at JD Explore Academy. †Liang Ding is the corresponding author. sentiment analysis task (Ma et al., 2017; Fan et al., 2018; Sun et al., 2019; Wang et al., 2020; Li et al., 2021b; Zhang et al., 2022a), is further introduced to detect the sentiment polarities towards given as- pects (entities) in a review sentence. Gathering a review "while the ambiance and atmosphere were great, the food and service could have been a lot better.", the sentiment polarities of "ambiance" and "atmosphere" are Positive and we get Negative po- larity for aspects "food" and "service". It is crucial to capture the aspect-specific contex- tual features for an ABSA model. Unfortunately, as shown in the aforementioned example, the multi- aspect challenge that there are multiple aspects in a sentence always deteriorates the model’s gener- alization, especially when the expressed polarities of multiple aspect words in a sentence are opposite. Meanwhile, since ABSA is a low-resource task, it is hard to train a robust model under fewer samples. Some existing works focused on the multi-aspect challenge, such as Lu et al. (2011); Hu et al. (2019) in which novel …

Content truncated to 500 words