Inspire the Large Language Model by External Knowledge on BioMedical Named Entity Recognition
This work addresses the challenge of domain-specific information extraction for biomedical researchers, but it is incremental as it adapts existing Chain-of-thought methods to a specific task.
The authors tackled the problem of large language models (LLMs) underperforming in Biomedical Named Entity Recognition (NER) due to a lack of domain-specific knowledge by breaking the task into entity span extraction and entity type determination with external knowledge injection, resulting in significant improvements over previous few-shot LLM baselines.
Large language models (LLMs) have demonstrated dominating performance in many NLP tasks, especially on generative tasks. However, they often fall short in some information extraction tasks, particularly those requiring domain-specific knowledge, such as Biomedical Named Entity Recognition (NER). In this paper, inspired by Chain-of-thought, we leverage the LLM to solve the Biomedical NER step-by-step: break down the NER task into entity span extraction and entity type determination. Additionally, for entity type determination, we inject entity knowledge to address the problem that LLM's lack of domain knowledge when predicting entity category. Experimental results show a significant improvement in our two-step BioNER approach compared to previous few-shot LLM baseline. Additionally, the incorporation of external knowledge significantly enhances entity category determination performance.