@inproceedings{chen-etal-2024-dynamic,
    title = "Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis",
    author = "Chen, Yanjiang  and
      Zhang, Kai  and
      Hu, Feng  and
      Wang, Xianquan  and
      Li, Ruikang  and
      Liu, Qi",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.emnlp-main.611/",
    doi = "10.18653/v1/2024.emnlp-main.611",
    pages = "10920--10931",
    abstract = "Aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity of a specific aspect within a given sentence. Most existing methods predominantly leverage semantic or syntactic information based on attention scores, which are susceptible to interference caused by irrelevant contexts and often lack sentiment knowledge at a data-specific level. In this paper, we propose a novel Dynamic Multi-granularity Attribution Network (DMAN) from the perspective of attribution. Initially, we leverage Integrated Gradients to dynamically extract attribution scores for each token, which contain underlying reasoning knowledge for sentiment analysis. Subsequently, we aggregate attribution representations from multiple semantic granularities in natural language, enhancing a profound understanding of the semantics. Finally, we integrate attribution scores with syntactic information to capture the relationships between aspects and their relevant contexts more accurately during the sentence understanding process. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our proposed method."
}