ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction

• URL: http://arxiv.org/abs/2310.12537v5
• Date: Fri, 20 Sep 2024 08:49:37 GMT
• Title: ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction
• Authors: Alexander Brinkmann, Roee Shraga, Christian Bizer,
• Abstract summary:
• Score: 52.14681890859275
• License:
• Abstract: 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.

Related papers

• TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification [19.911923049421137]
  We introduce TACLR, the first retrieval-based method for Product Attribute Value Identification (PAVI) It formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity to the item embedding. It offers three key advantages: (1) it effectively handles implicit and OOD values while producing normalized outputs; (2) it scales to thousands of categories, tens of thousands of attributes, and millions of values; and (3) it supports efficient inference for high-load industrial scenarios.
  arXiv  Detail & Related papers  (2025-01-07T14:45:30Z)
• Self-Refinement Strategies for LLM-based Product Attribute Value Extraction [51.45146101802871]
  This paper investigates applying two self-refinement techniques to the product attribute value extraction task. The experiments show that both self-refinement techniques fail to significantly improve the extraction performance while substantially increasing processing costs. For scenarios with development data, fine-tuning yields the highest performance, while the ramp-up costs of fine-tuning are balanced out as the amount of product descriptions increases.
  arXiv  Detail & Related papers  (2025-01-02T12:55:27Z)
• Exploring Large Language Models for Product Attribute Value Identification [25.890927969633196]
  Product attribute value identification (PAVI) involves automatically identifying attributes and their values from product information. Existing methods rely on fine-tuning pre-trained language models, such as BART and T5. This paper explores large language models (LLMs), such as LLaMA and Mistral, as data-efficient and robust alternatives for PAVI.
  arXiv  Detail & Related papers  (2024-09-19T12:09:33Z)
• Using LLMs for the Extraction and Normalization of Product Attribute Values [47.098255866050835]
  This paper explores the potential of using large language models (LLMs) to extract and normalize attribute values from product titles and descriptions. We introduce the Web Data Commons - Product Attribute Value Extraction (WDC-PAVE) benchmark dataset for our experiments.
  arXiv  Detail & Related papers  (2024-03-04T15:39:59Z)
• JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction [59.94977231327573]
  We propose a multi-task learning model with value generation/classification and attribute prediction called JPAVE. Two variants of our model are designed for open-world and closed-world scenarios. Experimental results on a public dataset demonstrate the superiority of our model compared with strong baselines.
  arXiv  Detail & Related papers  (2023-11-07T18:36:16Z)
• AE-smnsMLC: Multi-Label Classification with Semantic Matching and Negative Label Sampling for Product Attribute Value Extraction [42.79022954630978]
  Product attribute value extraction plays an important role for many real-world applications in e-Commerce such as product search and recommendation. Previous methods treat it as a sequence labeling task that needs more annotation for position of values in the product text. We propose a classification model with semantic matching and negative label sampling for attribute value extraction.
  arXiv  Detail & Related papers  (2023-10-11T02:22:28Z)
• Product Information Extraction using ChatGPT [69.12244027050454]
  This paper explores the potential of ChatGPT for extracting attribute/value pairs from product descriptions. Our results show that ChatGPT achieves a performance similar to a pre-trained language model but requires much smaller amounts of training data and computation for fine-tuning.
  arXiv  Detail & Related papers  (2023-06-23T09:30:01Z)
• A Unified Generative Approach to Product Attribute-Value Identification [6.752749933406399]
  We explore a generative approach to the product attribute-value identification (PAVI) task. We finetune a pre-trained generative model, T5, to decode a set of attribute-value pairs as a target sequence from the given product text. Experimental results confirm that our generation-based approach outperforms the existing extraction and classification-based methods.
  arXiv  Detail & Related papers  (2023-06-09T00:33:30Z)
• AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators [98.11286353828525]
  GPT-3.5 series models have demonstrated remarkable few-shot and zero-shot ability across various NLP tasks. We propose AnnoLLM, which adopts a two-step approach, explain-then-annotate. We build the first conversation-based information retrieval dataset employing AnnoLLM.
  arXiv  Detail & Related papers  (2023-03-29T17:03:21Z)
• What Makes Good In-Context Examples for GPT-$3$? [101.99751777056314]
  GPT-$3$ has attracted lots of attention due to its superior performance across a wide range of NLP tasks. Despite its success, we found that the empirical results of GPT-$3$ depend heavily on the choice of in-context examples. In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples.
  arXiv  Detail & Related papers  (2021-01-17T23:38:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.