ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction
This work addresses the need for structured product data in e-commerce platforms, offering incremental improvements in extraction efficiency and robustness for vendors and platforms.
The paper tackled the problem of extracting product attribute-value pairs from unstructured e-commerce descriptions by exploring large language models (LLMs) as a more data-efficient and robust alternative to BERT-based methods. The result showed that GPT-4 achieved the highest average F1-score of 85%, surpassing the best baseline by 5%, with Llama-3-70B offering a competitive open-source alternative.
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.