3

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.

Hedieh
  • 43
  • 8
  • LingPipe has an NE tutorial here, which covers regex, exact, and statistical named entity extraction: http://alias-i.com/lingpipe/demos/tutorial/ne/read-me.html It's a server-oriented Java API with demos of how to run from the command line in the tutorial. – Bob Carpenter Jun 13 '16 at 16:58

3 Answers3

3

You can use dictionary (or regular expression-based) named entity recognition with Stanford CoreNLP. See the RegexNER annotator. For some applications, we run this with quite large dictionaries of entities. Nevertheless, for us this is typically a secondary tool to using statistical (CRF-based) NER.

Christopher Manning
  • 9,360
  • 34
  • 46
1

Stanford-NER is based on CRFs, which is a statistic model. I'm afraid it doesn't support extra dictionary or lexicon. However, you can train a new model according to your own task.

Friedmannn
  • 138
  • 1
  • 1
  • 9
  • Thanks @Friedmannn. i read a little about Stanford NER and figured out how it works. I also tried to use its Gazette but wasn't helpful. I switched to LingPipe and that is working fine. – Hedieh Sep 13 '16 at 10:06
1

you can use MER: http://labs.fc.ul.pt/mer/

a minimal entity recognizer developed in bash: https://github.com/lasigeBioTM/MER

that only requires a lexicon (text file) as input

FCouto
  • 66
  • 4