arXiv 2406.112342024-09-30cs.CLcs.AI

MiniConGTS：一种面向方面情感三元组抽取的近乎终极极简对比网格标注方案

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

Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Academy of Engineering and Technology, Fudan University（复旦大学工程与技术学院）；Shanghai Jiao Tong University（上海交通大学）；School of Information Science and Technology, Fudan University（复旦大学信息科学与技术学院）

Qiao Sun, Liujia Yang, Minghao Ma, Nanyang Ye, Qinying Gu

备注：: arXiv admin note: text overlap with arXiv:2403.07342

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出MiniConGTS，通过极简标注方案与令牌级对比学习改进预训练表示，以更低计算开销实现与最先进方法相当或更优的方面情感三元组抽取性能，并首次评估GPT-4在该任务上的表现。

摘要：

方面情感三元组抽取（ASTE）旨在从给定语料中联合抽取情感三元组。在预训练-微调范式下的现有方法往往要么精心设计复杂的标注方案和分类头，要么引入外部语义增强来提升性能。在本研究中，我们首次重新审视了标注方案中的冗余性以及预训练表示中的内部增强。我们提出了一种方法，通过整合极简标注方案和一种新颖的令牌级对比学习策略来改进并利用预训练表示。所提出的方法在性能上与最先进技术相比具有可比性或更优，同时具有更紧凑的设计和更低的计算开销。此外，我们首次正式评估了GPT-4在该任务的少样本学习和思维链场景中的表现。结果表明，即使在大语言模型时代，预训练-微调范式仍然非常有效。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。