Large Language Models for Few-Shot Automatic Term Extraction

Automatic term extraction is the process of identifying domain-specific terms in a text using automated algorithms and is a key first step in ontology learning and knowledge graph creation. Large language models have shown good few-shot capabilities, thus, in this paper, we present a study to evaluate the few-shot in-context learning performance of GPT-3.5-Turbo on automatic term extraction. To benchmark the performance we compare the results with fine-tuning of a BERT-sized model. We also carry out experiments with count-based term extractors to assess their applicability to few-shot scenarios. We quantify prompt sensitivity with experiments to analyze the variation in performance of large language models across different prompt templates. Our results show that in-context learning with GPT-3.5-Turbo outperforms the BERT-based model and unsupervised count-based methods in few-shot scenarios.