QAIE:基于 LLM 的数量扩增和信息增强技术,适用于基于几个方面的情感分析

IF 7.4 1区 管理学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Information Processing & Management Pub Date : 2024-10-22 DOI:10.1016/j.ipm.2024.103917
Heng-yang Lu , Tian-ci Liu , Rui Cong , Jun Yang , Qiang Gan , Wei Fang , Xiao-jun Wu
{"title":"QAIE:基于 LLM 的数量扩增和信息增强技术,适用于基于几个方面的情感分析","authors":"Heng-yang Lu ,&nbsp;Tian-ci Liu ,&nbsp;Rui Cong ,&nbsp;Jun Yang ,&nbsp;Qiang Gan ,&nbsp;Wei Fang ,&nbsp;Xiao-jun Wu","doi":"10.1016/j.ipm.2024.103917","DOIUrl":null,"url":null,"abstract":"<div><div>Aspect-based Sentiment Analysis (ABSA) aims to extract fine-grained sentiment information from online reviews. Few-shot ABSA faces challenges with limited labeled data and recent generative models have outperformed traditional classification models. Existing methods use Question Answering (QA) templates with Text-to-Text Transfer Transformer (T5) to extract sentiment elements, introducing a generative sentiment analysis paradigm. However, these models often fail to fully grasp ABSA rules, generating non-standard or incorrect outputs. This issue also arises with large language models (LLMs) due to insufficient labeled data for tuning and learning. Additionally, ABSA datasets often include many short, uninformative reviews, complicating sentiment element extraction in few-shot scenarios. This paper addresses two major challenges in few-shot ABSA: (1) <em>How to let the generative model well understand the ABSA rules under few-shot scenarios</em>. (2) <em>How to enhance the review text with richer information</em>. We propose a <strong>Q</strong>uantity <strong>A</strong>ugmentation and <strong>I</strong>nformation <strong>E</strong>nhancement (<strong>QAIE</strong>) approach, leveraging LLMs to generate fluent texts and infer implicit information. First, we propose a quantity augmentation module, which leverages the large language model (LLM) to obtain sufficient labeled data for the generative model to learn the ABSA rules better. Then, we introduce an information enhancement module, which brings more informative input to the generative model by enhancing the information in the review. Comprehensive experiments on five ABSA tasks using three widely-used datasets demonstrate that our QAIE model achieves approximately 10% improvement over state-of-the-art models. Specifically, for the most challenging ASQP task, our LLM-based model is compared with the existing state-of-the-art models on datasets Rest15 and Rest16, achieving F1 gains of 9.42% and 6.45% respectively in the <span><math><mrow><mi>k</mi><mo>=</mo><mn>5</mn></mrow></math></span> few-shot setting.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4000,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"QAIE: LLM-based Quantity Augmentation and Information Enhancement for few-shot Aspect-Based Sentiment Analysis\",\"authors\":\"Heng-yang Lu ,&nbsp;Tian-ci Liu ,&nbsp;Rui Cong ,&nbsp;Jun Yang ,&nbsp;Qiang Gan ,&nbsp;Wei Fang ,&nbsp;Xiao-jun Wu\",\"doi\":\"10.1016/j.ipm.2024.103917\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Aspect-based Sentiment Analysis (ABSA) aims to extract fine-grained sentiment information from online reviews. Few-shot ABSA faces challenges with limited labeled data and recent generative models have outperformed traditional classification models. Existing methods use Question Answering (QA) templates with Text-to-Text Transfer Transformer (T5) to extract sentiment elements, introducing a generative sentiment analysis paradigm. However, these models often fail to fully grasp ABSA rules, generating non-standard or incorrect outputs. This issue also arises with large language models (LLMs) due to insufficient labeled data for tuning and learning. Additionally, ABSA datasets often include many short, uninformative reviews, complicating sentiment element extraction in few-shot scenarios. This paper addresses two major challenges in few-shot ABSA: (1) <em>How to let the generative model well understand the ABSA rules under few-shot scenarios</em>. (2) <em>How to enhance the review text with richer information</em>. We propose a <strong>Q</strong>uantity <strong>A</strong>ugmentation and <strong>I</strong>nformation <strong>E</strong>nhancement (<strong>QAIE</strong>) approach, leveraging LLMs to generate fluent texts and infer implicit information. First, we propose a quantity augmentation module, which leverages the large language model (LLM) to obtain sufficient labeled data for the generative model to learn the ABSA rules better. Then, we introduce an information enhancement module, which brings more informative input to the generative model by enhancing the information in the review. Comprehensive experiments on five ABSA tasks using three widely-used datasets demonstrate that our QAIE model achieves approximately 10% improvement over state-of-the-art models. Specifically, for the most challenging ASQP task, our LLM-based model is compared with the existing state-of-the-art models on datasets Rest15 and Rest16, achieving F1 gains of 9.42% and 6.45% respectively in the <span><math><mrow><mi>k</mi><mo>=</mo><mn>5</mn></mrow></math></span> few-shot setting.</div></div>\",\"PeriodicalId\":50365,\"journal\":{\"name\":\"Information Processing & Management\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.4000,\"publicationDate\":\"2024-10-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information Processing & Management\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0306457324002760\",\"RegionNum\":1,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Processing & Management","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306457324002760","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

基于方面的情感分析(ABSA)旨在从在线评论中提取细粒度的情感信息。由于标注的数据有限,很少有样本的 ABSA 面临着挑战,而最近的生成模型在性能上优于传统的分类模型。现有方法使用带有文本到文本转换器(T5)的问题解答(QA)模板来提取情感元素,从而引入了一种生成式情感分析范式。然而,这些模型往往无法完全掌握 ABSA 规则,从而产生非标准或不正确的输出。由于用于调整和学习的标注数据不足,大型语言模型(LLM)也会出现这个问题。此外,ABSA 数据集通常包含许多短小、无信息量的评论,这就使少量评论场景中的情感元素提取变得更加复杂。本文主要探讨了少量评论 ABSA 的两大挑战:(1)如何让生成模型很好地理解少量评论场景下的 ABSA 规则。(2) 如何用更丰富的信息来增强评论文本。我们提出了一种数量增强和信息增强(QAIE)方法,利用 LLM 生成流畅的文本并推断隐含信息。首先,我们提出了一个数量增强模块,利用大语言模型(LLM)获得足够的标注数据,以便生成模型更好地学习 ABSA 规则。然后,我们引入了信息增强模块,通过增强评论中的信息为生成模型带来更多信息输入。利用三个广泛使用的数据集对五项 ABSA 任务进行的综合实验表明,我们的 QAIE 模型比最先进的模型提高了约 10%。具体来说,在最具挑战性的 ASQP 任务中,我们基于 LLM 的模型与现有数据集 Rest15 和 Rest16 上的先进模型进行了比较,在 k=5 few-shot 设置下,F1 增益分别为 9.42% 和 6.45%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
QAIE: LLM-based Quantity Augmentation and Information Enhancement for few-shot Aspect-Based Sentiment Analysis
Aspect-based Sentiment Analysis (ABSA) aims to extract fine-grained sentiment information from online reviews. Few-shot ABSA faces challenges with limited labeled data and recent generative models have outperformed traditional classification models. Existing methods use Question Answering (QA) templates with Text-to-Text Transfer Transformer (T5) to extract sentiment elements, introducing a generative sentiment analysis paradigm. However, these models often fail to fully grasp ABSA rules, generating non-standard or incorrect outputs. This issue also arises with large language models (LLMs) due to insufficient labeled data for tuning and learning. Additionally, ABSA datasets often include many short, uninformative reviews, complicating sentiment element extraction in few-shot scenarios. This paper addresses two major challenges in few-shot ABSA: (1) How to let the generative model well understand the ABSA rules under few-shot scenarios. (2) How to enhance the review text with richer information. We propose a Quantity Augmentation and Information Enhancement (QAIE) approach, leveraging LLMs to generate fluent texts and infer implicit information. First, we propose a quantity augmentation module, which leverages the large language model (LLM) to obtain sufficient labeled data for the generative model to learn the ABSA rules better. Then, we introduce an information enhancement module, which brings more informative input to the generative model by enhancing the information in the review. Comprehensive experiments on five ABSA tasks using three widely-used datasets demonstrate that our QAIE model achieves approximately 10% improvement over state-of-the-art models. Specifically, for the most challenging ASQP task, our LLM-based model is compared with the existing state-of-the-art models on datasets Rest15 and Rest16, achieving F1 gains of 9.42% and 6.45% respectively in the k=5 few-shot setting.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Information Processing & Management
Information Processing & Management 工程技术-计算机:信息系统
CiteScore
17.00
自引率
11.60%
发文量
276
审稿时长
39 days
期刊介绍: Information Processing and Management is dedicated to publishing cutting-edge original research at the convergence of computing and information science. Our scope encompasses theory, methods, and applications across various domains, including advertising, business, health, information science, information technology marketing, and social computing. We aim to cater to the interests of both primary researchers and practitioners by offering an effective platform for the timely dissemination of advanced and topical issues in this interdisciplinary field. The journal places particular emphasis on original research articles, research survey articles, research method articles, and articles addressing critical applications of research. Join us in advancing knowledge and innovation at the intersection of computing and information science.
期刊最新文献
ME3A: A Multimodal Entity Entailment framework for multimodal Entity Alignment Hierarchical multi-label text classification of tourism resources using a label-aware dual graph attention network Impact of economic and socio-political risk factors on sovereign credit ratings Higher-order structure based node importance evaluation in directed networks Membership inference attacks via spatial projection-based relative information loss in MLaaS
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1