Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis
This work addresses inefficiencies in aspect-based sentiment analysis for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles the problem of aspect-based sentiment analysis by addressing inefficiencies and errors in multi-view prompting methods, proposing a Dynamic Order Template method that dynamically generates views based on instance-level entropy. This approach improves F1-scores on ASQP and ACOS datasets and significantly reduces inference time.
Aspect-based sentiment analysis (ABSA) assesses sentiments towards specific aspects within texts, resulting in detailed sentiment tuples. Previous ABSA models often use static templates to predict all of the elements in the tuples, and these models often fail to accurately capture dependencies between elements. Multi-view prompting method improves the performance of ABSA by predicting tuples with various templates and then ensembling the results. However, this method suffers from inefficiencies and out-of-distribution errors. In this paper, we propose a Dynamic Order Template (DOT) method for ABSA, which dynamically generates necessary views for each instance based on instance-level entropy. Ensuring the diverse and relevant view generation, our proposed method improves F1-scores on ASQP and ACOS datasets while significantly reducing inference time.