Changes between Version 18 and Version 19 of private/AdvancedNlpCourse/NamedEntityRecognition


Ignore:
Timestamp:
Oct 2, 2019, 10:05:58 AM (12 months ago)
Author:
Zuzana Nevěřilová
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • private/AdvancedNlpCourse/NamedEntityRecognition

    v18 v19  
    56561. train the model using the default settings (cnec.prop), N.B. that the `convert_cnec_stanford.py` only recognizes PERSON, LOCATION and ORGANIZATION, you can extend the markup conversion later:
    5757{{{
    58 java -cp stanford-ner-2017-06-09/stanford-ner.jar \
     58java -cp stanford-ner-2018-10-16/stanford-ner.jar \
    5959  edu.stanford.nlp.ie.crf.CRFClassifier \
    6060  -prop cnec.prop
     
    67671. evaluate the model on `dtest`:
    6868{{{
    69 java -cp stanford-ner-2017-06-09/stanford-ner.jar \
     69java -cp stanford-ner-2018-10-16/stanford-ner.jar \
    7070  edu.stanford.nlp.ie.crf.CRFClassifier \
    7171  -loadClassifier cnec-3class-model.ser.gz \
     
    858510. evaluate the model on `dtest` with only NEs that are not present in the train data:
    8686 {{{
    87 java -cp stanford-ner-2017-06-09/stanford-ner.jar \
     87java -cp stanford-ner-2018-10-16/stanford-ner.jar \
    8888  edu.stanford.nlp.ie.crf.CRFClassifier \
    8989  -loadClassifier cnec-3class-model.ser.gz \
     
    949411. test on your own input:
    9595 {{{
    96 java -mx600m -cp stanford-ner-2017-06-09/stanford-ner.jar \
     96java -mx600m -cp stanford-ner-2018-10-16/stanford-ner.jar \
    9797  edu.stanford.nlp.ie.crf.CRFClassifier \
    9898  -loadClassifier cnec-3class-model.ser.gz -textFile sample.txt