Aspect Sentiment Triplet Extraction (ASTE) aims to extract the spans of aspect, opinion, and their sentiment relations as sentiment triplets. Existing works usually formulate the span detection as a 1D token tagging problem, and model the sentiment recognition with a 2D tagging matrix of token pairs. Moreover, by leveraging the token representation of Pretrained Language Encoders (PLEs) like BERT, they can achieve better performance. However, they simply leverage PLEs as feature extractors to build their modules but never have a deep look at what specific knowledge does PLEs contain. In this paper, we argue that instead of further designing modules to capture the inductive bias of ASTE, PLEs themselves contain "enough" features for 1D and 2D tagging: (1) The token representation contains the contextualized meaning of token itself, so this level feature carries necessary information for 1D tagging. (2) The attention matrix of different PLE layers can further capture multi-level linguistic knowledge existing in token pairs, which benefits 2D tagging. (3) Furthermore, with simple transformations, these two features can also be easily converted to the 2D tagging matrix and 1D tagging sequence, respectively. That will further boost the tagging results. By doing so, PLEs can be natural tagging frameworks and achieve a new state of the art, which is verified by extensive experiments and deep analyses.
翻译:Aspect Sentition Triplet Expliton (ASTE) 旨在提取方方面面、观点和情绪关系的广度,作为情绪三重线。 现有的作品通常将频谱检测作为 1D 象征性标记标记问题, 并将情感识别模型与 2D 标记配对矩阵建模。 此外, 通过利用像 BERT 那样的训练有素的语言编码(PLE) 的象征性表示方式, 它们可以取得更好的性能。 但是, 它们只是利用 PLE 作为特性提取器来建立模块, 却从未深入查看 PLE 包含的具体知识。 在本文中, 我们争论说, PLES 本身不是进一步设计模块来捕捉 ASTE 的感化偏差标记问题, 而是用 2D 标记配对一和 2D 标记配对一的“ 增强” 特征识别特征。 象征性表示本身的背景含义, 因此这个级别特性为 1D 的注意矩阵可以进一步捕捉到 标记配对 2D 的多级语言知识, 。 此外, 通过简单的变换, 这两个特性的标记将分别转换到2D 标签 进行新的标签 进行新的标签 进行新的标签 和标签 将进一步的标签 进行新的标记 。