Saved in:
Bibliographic Details
Main Authors: Brinkmann, Alexander, Shraga, Roee, Bizer, Christian
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.12537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909320093892608
author Brinkmann, Alexander
Shraga, Roee
Bizer, Christian
author_facet Brinkmann, Alexander
Shraga, Roee
Bizer, Christian
contents E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison. However, vendors often provide unstructured product descriptions, necessitating the extraction of attribute-value pairs from these texts. BERT-based extraction methods require large amounts of task-specific training data and struggle with unseen attribute values. This paper explores using large language models (LLMs) as a more training-data efficient and robust alternative. We propose prompt templates for zero-shot and few-shot scenarios, comparing textual and JSON-based target schema representations. Our experiments show that GPT-4 achieves the highest average F1-score of 85% using detailed attribute descriptions and demonstrations. Llama-3-70B performs nearly as well, offering a competitive open-source alternative. GPT-4 surpasses the best PLM baseline by 5% in F1-score. Fine-tuning GPT-3.5 increases the performance to the level of GPT-4 but reduces the model's ability to generalize to unseen attribute values.
format Preprint
id arxiv_https___arxiv_org_abs_2310_12537
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction
Brinkmann, Alexander
Shraga, Roee
Bizer, Christian
Computation and Language
E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison. However, vendors often provide unstructured product descriptions, necessitating the extraction of attribute-value pairs from these texts. BERT-based extraction methods require large amounts of task-specific training data and struggle with unseen attribute values. This paper explores using large language models (LLMs) as a more training-data efficient and robust alternative. We propose prompt templates for zero-shot and few-shot scenarios, comparing textual and JSON-based target schema representations. Our experiments show that GPT-4 achieves the highest average F1-score of 85% using detailed attribute descriptions and demonstrations. Llama-3-70B performs nearly as well, offering a competitive open-source alternative. GPT-4 surpasses the best PLM baseline by 5% in F1-score. Fine-tuning GPT-3.5 increases the performance to the level of GPT-4 but reduces the model's ability to generalize to unseen attribute values.
title ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction
topic Computation and Language
url https://arxiv.org/abs/2310.12537