Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models

TL;DR

This paper enhances aspect-level sentiment classification by fine-tuning large language models to better handle coreference resolution, supported by a new dataset and demonstrating improved performance in CR-related reviews.

Contribution

It introduces a fine-tuning framework targeting coreference resolution in ALSC and releases a new dataset for CR-focused sentiment analysis.

Findings

Improved LLM performance on CR-containing reviews.

Fine-tuning enhances coreference resolution ability.

New dataset facilitates CR in ALSC tasks.

Abstract

Customer feedback is invaluable to companies as they refine their products. Monitoring customer feedback can be automated with Aspect Level Sentiment Classification (ALSC) which allows us to analyse specific aspects of the products in reviews. Large Language Models (LLMs) are the heart of many state-of-the-art ALSC solutions, but they perform poorly in some scenarios requiring Coreference Resolution (CR). In this work, we propose a framework to improve an LLM's performance on CR-containing reviews by fine tuning on highly inferential tasks. We show that the performance improvement is likely attributed to the improved model CR ability. We also release a new dataset that focuses on CR in ALSC.