MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet Extraction

TL;DR

MiniConGTS introduces a minimalist contrastive grid tagging scheme for aspect sentiment triplet extraction, achieving comparable or better results with less complexity and computational cost, while also evaluating GPT-4's few-shot capabilities.

Contribution

The paper presents a novel minimalist tagging scheme combined with contrastive learning, reducing complexity and computational overhead in aspect sentiment triplet extraction.

Findings

Comparable or superior performance to state-of-the-art methods

Effective utilization of pretrained representations with a simpler scheme

GPT-4 performs well in few-shot and Chain-of-Thought scenarios for this task

Abstract

Aspect Sentiment Triplet Extraction (ASTE) aims to co-extract the sentiment triplets in a given corpus. Existing approaches within the pretraining-finetuning paradigm tend to either meticulously craft complex tagging schemes and classification heads, or incorporate external semantic augmentation to enhance performance. In this study, we, for the first time, re-evaluate the redundancy in tagging schemes and the internal enhancement in pretrained representations. We propose a method to improve and utilize pretrained representations by integrating a minimalist tagging scheme and a novel token-level contrastive learning strategy. The proposed approach demonstrates comparable or superior performance compared to state-of-the-art techniques while featuring a more compact design and reduced computational overhead. Additionally, we are the first to formally evaluate GPT-4's performance in few-shot learning and Chain-of-Thought scenarios for this task. The results demonstrate that the pretraining-finetuning paradigm remains highly effective even in the era of large language models.