As an important fine-grained sentiment analysis task, aspect sentiment triplet extraction (ASTE) aims to identify three elements, i.e., aspect, opinion and sentiment polarity as a triplet. Advanced ASTE researches have mostly explored triplet-wise ability to achieve superior improvement. However, existing models with strong in-house performances may struggle to generalize to the challenging cases with the diverse expression of inter-triplet and intra-triplet elements. To this end, we propose a **M**odel-**A**gnostic **T**raining **O**ptimization (**MATO**) to improve ASTE model inference consistent with expected results facing triplet element diversity. Specifically, we design inter-triplet and intra-triplet metamorphic relations (MRs), and calculate the violation rate (VR) on each element of one triplet through metamorphic testing (MT), indicating the capacity to accommodate the diverse elements. Moreover, we propose an element-wise diversity-aware loss based on the VRs of aspect, opinion and sentiment, which can be jointly trained with existed ASTE models via uncertainty weighing. Conducted on four benchmark datasets and seven ASTE models, experimental results show that our MATO can enhance their diversity capacity, decreasing the average element-wise VRs by 3.28% to 15.36%. Meanwhile, our MATO is comparable to or better than those in terms of F1-score.

As an important fine-grained task of sentiment analysis, Aspect-Category based Sentiment Analysis (ACSA) aims to identify the sentiment polarities of pre-defined categories in text. However, due to subjectivity, the highly semantically similar text has polysemous sentiments to different people, leading to annotation difference. To this end, we propose a MAjority Rules Guided (MARG) for the profound understanding of this difference. Specifically, we firstly design a rule-based prompt generation, and then label word distribution is generated through an autoregression model for token-wise semantic consistency. Last but not least, the impact to the model caused by this commonly prevailing annotation difference can be mitigated by majority rules. 1) Our local majority rule is the ensemble of label word distributions, which alleviates the influence of the difference at the distribution generation stage. And 2) our global majority rule is the refinement based on the label prior knowledge of aspect categories, which further reduces the interference of the difference at the global data level. Conducted on four benchmark datasets, our MARG outperforms the state-of-the-art models by 2.43% to 67.68% in terms of F1-score and by 1.16% to 10.22% in terms of Accuracy.