arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.02130cs.CL
收藏

使用大语言模型进行产品属性值的抽取与归一化

Using LLMs for the Extraction and Normalization of Product Attribute Values

University of Mannheim(曼海姆大学)

Alexander Brinkmann, Nick Baumann, Christian Bizer

AI总结:

本文研究利用GPT-3.5和GPT-4等大语言模型从电商产品标题与描述中抽取并归一化属性值,引入WDC-PAVE基准数据集,实验表明GPT-4以91%的F1分数优于现有PLM方法,且在字符串整理和名称扩展上表现突出。

摘要:

电子商务网站上的产品信息通常由产品标题和文本形式的产品描述组成。为了支持分面产品搜索或生成产品对比表等功能,需要从非结构化的产品标题和描述中抽取结构化的属性-值对,并将抽取出的值归一化到每个属性统一、单一的尺度上。本文探讨了使用大语言模型(LLMs),如GPT-3.5和GPT-4,从产品标题和描述中抽取并归一化属性值的潜力。我们尝试了不同的零样本和少样本提示模板,以指导大语言模型抽取并归一化属性-值对。我们引入了Web Data Commons - Product Attribute Value Extraction(WDC-PAVE)基准数据集用于实验。WDC-PAVE包含来自59个不同网站的产品信息,这些网站提供了schema.org标注。这些产品信息属于五个不同的产品类别,每个类别都有一组特定的属性。该数据集以两种形式提供了经人工验证的属性-值对:(i)直接抽取的值和(ii)归一化后的属性值。属性值的归一化要求系统执行以下类型的操作:名称扩展、泛化、计量单位转换和字符串整理。我们的实验表明,GPT-4比基于预训练语言模型(PLM)的抽取方法SU-OpenTag、AVEQA和MAVEQA高出10%,达到了91%的F1分数。对于产品属性值的抽取与归一化,GPT-4取得了与抽取场景相似的性能,同时在字符串整理和名称扩展方面表现尤为突出。

英文摘要:

Product offers on e-commerce websites often consist of a product title and a textual product description. In order to enable features such as faceted product search or to generate product comparison tables, it is necessary to extract structured attribute-value pairs from the unstructured product titles and descriptions and to normalize the extracted values to a single, unified scale for each attribute. This paper explores the potential of using large language models (LLMs), such as GPT-3.5 and GPT-4, to extract and normalize attribute values from product titles and descriptions. We experiment with different zero-shot and few-shot prompt templates for instructing LLMs to extract and normalize attribute-value pairs. We introduce the Web Data Commons - Product Attribute Value Extraction (WDC-PAVE) benchmark dataset for our experiments. WDC-PAVE consists of product offers from 59 different websites which provide schema.org annotations. The offers belong to five different product categories, each with a specific set of attributes. The dataset provides manually verified attribute-value pairs in two forms: (i) directly extracted values and (ii) normalized attribute values. The normalization of the attribute values requires systems to perform the following types of operations: name expansion, generalization, unit of measurement conversion, and string wrangling. Our experiments demonstrate that GPT-4 outperforms the PLM-based extraction methods SU-OpenTag, AVEQA, and MAVEQA by 10%, achieving an F1-score of 91%. For the extraction and normalization of product attribute values, GPT-4 achieves a similar performance to the extraction scenario, while being particularly strong at string wrangling and name expansion.

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。

↑