Chemical Entity Recognition (CER) is a fundamental task in biomedical text mining and Natural Language Processing (NLP). It involves the identification and classification of chemical entities in textual data, such as scientific literature. These entities can encompass a broad range of concepts including chemical compounds, drugs, elements, ions or functional groups. Given the complexity and variety of chemical nomenclature, the CER task represents a significant challenge for LLMs, and their performance in this task can provide important insights into their overall capabilities in the biomedical domain.
데이터셋
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
The dataset contains two few-shot chemical fine-grained entity extraction datasets, based on human-annotated ChemNER+ and CHEMET. For each dataset, we randomly sample a subset based on the frequency of each type class. Specifically, given a dataset, we first set the number of maximum entity mentions $k$ for the most frequent entity type in the dataset. We then randomly sample other types and ensure that the distribution of each type remains the same as in the original dataset. We choose the values $6, 9, 12, 15, 18$ as the potential maximum entity mentions for $k$. The ChemNER+ and CHEMET few-shot datasets contain 52 and 28 types respectively.