java - Exact Dictionary based Named Entity Recognition with Stanford

Question

I have a dictionary of named entities, extracted from Wikipedia. I want to use it as the dictionary of an NER. I wanted to know how can I use Stanford-NER with this data of mine. I have also downloaded Lingpipe, although I have no idea how can I use it. I would appreciate all kinds of information.

Thanks for your helps.

Answer 1

您可以在 Stanford CoreNLP 中使用字典（或基于正则表达式）命名实体识别。请参阅RegexNER 注释器。对于某些应用程序，我们使用相当大的实体字典来运行它。尽管如此，对我们来说，这通常是使用统计（基于 CRF）NER 的辅助工具。

Answer 2

您可以使用 MER： http: //labs.fc.ul.pt/mer/

用 bash 开发的最小实体识别器：https ://github.com/lasigeBioTM/MER

只需要一个词典（文本文件）作为输入

Answer 3

Stanford-NER 基于 CRFs，这是一种统计模型。恐怕它不支持额外的字典或词典。但是，您可以根据自己的任务训练新模型。