Abstract
Natural language processing (NLP) practitioners are leveraging large language models (LLM) to create structured datasets from semi-structured and unstructured data sources such as patents, papers, and theses, without having domain-specific knowledge. At the same time, ecological experts are searching for a variety of means to preserve biodiversity. To contribute to these efforts, we focused on endangered species and through in-context learning, we distilled knowledge from GPT-4. In effect, we created datasets for both named entity recognition (NER) and relation extraction (RE) via a two-stage process: 1) we generated synthetic data from GPT-4 of four classes of endangered species, 2) humans verified the factual accuracy of the synthetic data, resulting in gold data. Eventually, our novel dataset contains a total of 3.6K sentences, evenly divided between 1.8K NER and 1.8K RE sentences. The constructed dataset was then used to fine-tune both general BERT and domain-specific BERT variants, completing the knowledge distillation process from GPT-4 to BERT, because GPT-4 is resource intensive. Experiments show that our knowledge transfer approach is effective at creating a NER model suitable for detecting endangered species from texts.
Abstract (translated)
自然语言处理(NLP)从业者利用大型语言模型(LLM)将半结构化和非结构化数据源(如专利、论文和论据)构建为结构化数据,而无需具备专业知识。同时,生态专家正在寻找各种方法来保护生物多样性。为了为这些努力做出贡献,我们专注于濒危物种,并通过上下文学习从GPT-4中提炼知识。实际上,我们通过两个阶段创建了数据集:1)我们从GPT-4的四个濒危物种生成了合成数据;2)人类验证了合成数据的准确性,从而获得了金数据。最终,我们的新数据集包含3.6K个句子,其中1.8K个用于命名实体识别(NER)和1.8K个用于关系提取(RE)。构建的数据集随后用于微调 both general BERT 和 domain-specific BERT 版本,完成从GPT-4到BERT的 knowledge distillation 过程,因为GPT-4资源密集。实验结果表明,我们的知识传递方法在从文本中检测濒危物种方面是有效的。
URL
https://arxiv.org/abs/2403.15430