方面级情感分析的知识增强提示模板构建OA

Currently,aspect-level sentiment analysis models based on neural networks primarily in-volve discrete training of two subtasks:aspect term extraction and aspect polarity classification,or fine-tun-ing of pre-trained language models.These approaches neglect the interplay between the two subtasks,mak-ing it challenging to fully leverage the language model knowledge acquired during pre-training.This paper proposes an external knowledge-enhanced prompt template approach(KPT),which constructs the vocabu-lary of the pre-trained language model into a K-dimensional tree.The K-nearest neighbor search algorithm is employed to search for optimal prompt words on this K-dimensional tree,thereby constructing an optim-al prompt template.In this process,external knowledge is integrated into the vocabulary to enrich its se-mantic information.Features from the aspect term extraction task are utilized to further enhance the per-formance of the aspect polarity classification task.A multi-head attention mechanism is employed to enable interaction between the two tasks and integrate them,thereby improving the accuracy of sentiment polarity judgment by the external knowledge-enhanced prompt template.Experimental results on three public data-sets,namely Lap14,Rest14,and Twitter,demonstrate that the proposed method outperforms existing mod-els such as ASGCN,BiGCN,CDT,and others.