Abstract
Attribute Value Extraction (AVE) is critical in transforming unstructured text into structured data for various applications. While existing datasets for AVE predominantly focus on e-commerce and English language data, there is a lack of publicly available datasets tailored to other domains. This paper introduces the Real Estate Attribute Value Extraction (RAVE) dataset, specifically designed for extracting structured attributes from unstructured real estate advertisements. The RAVE dataset consists of manually annotated Slovak real estate listings, which have been translated into English for broader applicability. The paper evaluates the performance of multiple publicly available large language models (LLMs) in solving the AVE task on RAVE. Through extensive experimentation, we analyse the impact of additional attribute descriptions, selecting relevant sentences, and using ground-truth-based attribute definition in structured output generation. The findings of our study indicate that providing a schema with only relevant attributes significantly enhances extraction performance, reducing computational overhead while improving the achieved F1 score. The RAVE dataset is publicly available, facilitating further research inAVE and real estate information extraction.
Funding Information
  • VEGA through the Project Developing and Applying Advanced Techniques for Efficient Processing of Large-Scale Data in the Intelligent Transport Systems Environment (1/0192/24)