用大模型少样本完成情感四元组抽取，大幅减少人工标注需求。
Do we still need Human Annotators? Prompting Large Language Models for Aspect Sentiment Quad Prediction
- 直接提示大模型完成零样本/少样本四元组预测，无需微调。
- 20次提示下在餐厅数据集上达到51.54的F1，接近最优微调模型的60.39。
- 适合需要快速部署、标注成本高的情感分析场景。
情感四元组预测（ASQP）通过识别每条意见中的观点词、方面词、方面类别和情感极性，实现对文本观点的精细理解。然而，为训练模型标注完整数据集耗时耗力。本研究探索大语言模型（LLMs）在五个不同数据集上的零样本与少样本学习能力。结果显示，其F1分数几乎媲美最先进的微调模型，并超过此前零样本与少样本表现。在餐厅领域数据集Rest16的20次提示设置下，LLMs取得51.54的F1分数，而最佳微调方法MVP为60.39。此外，在目标方面情感检测（TASD）任务中，30次提示下取得68.93的F1，接近微调模型的72.76。尽管人工标注仍对最优性能至关重要，但大模型可显著降低ASQP任务对大规模人工标注的依赖。
原文摘要 · Abstract (English)
Aspect sentiment quad prediction (ASQP) facilitates a detailed understanding of opinions expressed in a text by identifying the opinion term, aspect term, aspect category and sentiment polarity for each opinion. However, annotating a full set of training examples to fine-tune models for ASQP is a resource-intensive process. In this study, we explore the capabilities of large language models (LLMs) for zero- and few-shot learning on the ASQP task across five diverse datasets. We report F1 scores almost up to par with those obtained with state-of-the-art fine-tuned models and exceeding previously reported zero- and few-shot performance. In the 20-shot setting on the Rest16 restaurant domain dataset, LLMs achieved an F1 score of 51.54, compared to 60.39 by the best-performing fine-tuned method MVP. Additionally, we report the performance of LLMs in target aspect sentiment detection (TASD), where the F1 scores were close to fine-tuned models, achieving 68.93 on Rest16 in the 30-shot setting, compared to 72.76 with MVP. While human annotators remain essential for achieving optimal performance, LLMs can reduce the need for extensive manual annotation in ASQP tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。