Exploring Rollback Inference for Aspect-based Sentiment Analysis

Anonymous

Abstract: With the giant help from pre-trained large language models, templated sequence of how to organize the aspect-level elements become the hottest research target while only a few of them move their steps to inference, not to mention utilizing the semantic connection between aspect-level elements during it. We argue that, compared with the high computational cost methods of training language models, considering the inference process can also bring us potential benefits. Motivated by this, we propose Rollback Inference strategies for aspect-based sentiment analysis, which can boost the performance of fine-tuned large language models with a tiny cost, and adapt to various language models. Extensive experiments in three datasets and multiple language models underscore the effectiveness of our proposed rollback inference strategies and the value of the semantic connections in inference.

Paper Type: long

Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Contribution Types: NLP engineering experiment, Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English