几种基于机器学习的生物命名实体识别模型比较

已有的大量生物医学文本为人们提供了充足的资料,但却没有足够好的工具来帮助人们从中获取信息和知识。而命名实体识别则在信息检索、信息抽取及知识发现等这样的应用中起着很重要的作用。本文基于JNLPBA生物命名实体识别任务,简要介绍了目前几种在生物医学文本中常用的基于机器学习的命名实体识别模型,并进行比较及常规讨论,同时也提供了一些相关的背景信息。

The Comparison Of the Biomedical Named Entity Recognition Models Based On Machine Learning

A great number of biomedical texts have offered enough information for people. Yet the lack of good tools prevents people from getting information and knowledge from them. NER plays a very important role in information retrieval, information extraction, knowledge discovery and so on. Based on the bio-entity recognition task at JNLPBA, this paper focuses on the introduction to the NER models based on machine learning usually used in biomedical texts. It presents a general comparison and discussion in them, and also provides some relative information.