Procedural Text Mining with Large Language Models
Anisa Rula, Jennifer D’Souza · ACM International Conference on Knowledge Capture (K-CAP) · 2023
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.
Cited by 18 works. doi:10.1145/3587259.3627572 Open-access PDF
Authors
References
- Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey
- Extracting Business Process Entities and Relations from Text Using Pre-trained Language Models and In-Context Learning
- Transformation from human-readable documents and archives in arc welding domain to machine-interpretable data
- K-Hub: A Modular Ontology to Support Document Retrieval and Knowledge Extraction in Industry 5.0
- Semantic modeling and analysis of complex data-aware processes and their executions