Procedural Text Mining with Large Language Models
This work addresses the problem of procedure extraction for knowledge engineering, offering an incremental improvement by adapting existing LLM methods to a specific domain.
The paper tackled extracting procedures from unstructured PDF text using GPT-4 in zero-shot and in-context learning settings, finding that customizations like ontology integration and few-shot samples show promise in addressing training data scarcity.
Recent advancements in the field of Natural Language Processing, particularly the development of large-scale language models that are pretrained on vast amounts of knowledge, are creating novel opportunities within the realm of Knowledge Engineering. In this paper, we investigate the usage of large language models (LLMs) in both zero-shot and in-context learning settings to tackle the problem of extracting procedures from unstructured PDF text in an incremental question-answering fashion. In particular, we leverage the current state-of-the-art GPT-4 (Generative Pre-trained Transformer 4) model, accompanied by two variations of in-context learning that involve an ontology with definitions of procedures and steps and a limited number of samples of few-shot learning. The findings highlight both the promise of this approach and the value of the in-context learning customisations. These modifications have the potential to significantly address the challenge of obtaining sufficient training data, a hurdle often encountered in deep learning-based Natural Language Processing techniques for procedure extraction.