Assessing the quality of information extraction

Filip Seitl, Tomas Kovarik, Soheyla Mirshahi, Jan Kryštůfek, Rastislav Dujava, Matus Ondreicka, Herbert Ullrich, Petr Gronat

Keywords: information extraction, large language models, quality evaluation, name entity recognition, needle in a haystack test, schema.org

Abstract: Advances in large language models have notably enhanced the efficiency of information extraction from unstructured and semi-structured data sources. As these technologies become integral to various applications, establishing an objective measure for the quality of information extraction becomes imperative. However, the scarcity of labeled data presents significant challenges to this endeavor. In this paper, we introduce an automatic framework to assess the quality of the information extraction/retrieval and its completeness. The framework focuses on information extraction in the form of entity and its properties. We discuss how to handle the input/output size limitations of the large language models and analyze their performance when extracting the information. In particular, we introduce scores to evaluate the quality of the extraction and provide an extensive discussion on how to interpret them.

Primary Area: Natural language processing

Submission Number: 16110