Changes between Version 17 and Version 18 of private/NlpInPracticeCourse/NamedEntityRecognition


Ignore:
Timestamp:
Oct 9, 2017, 11:44:59 AM (7 years ago)
Author:
Ales Horak
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • private/NlpInPracticeCourse/NamedEntityRecognition

    v17 v18  
    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 edu.stanford.nlp.ie.crf.CRFClassifier \
     58java -cp stanford-ner-2017-06-09/stanford-ner.jar \
     59  edu.stanford.nlp.ie.crf.CRFClassifier \
    5960  -prop cnec.prop
    6061}}}
     
    66671. evaluate the model on `dtest`:
    6768{{{
    68 java -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \
     69java -cp stanford-ner-2017-06-09/stanford-ner.jar \
     70  edu.stanford.nlp.ie.crf.CRFClassifier \
    6971  -loadClassifier cnec-3class-model.ser.gz \
    7072  -testFile named_ent_dtest.tsv
     
    838510. evaluate the model on `dtest` with only NEs that are not present in the train data:
    8486 {{{
    85 java -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \
     87java -cp stanford-ner-2017-06-09/stanford-ner.jar \
     88  edu.stanford.nlp.ie.crf.CRFClassifier \
    8689  -loadClassifier cnec-3class-model.ser.gz \
    8790  -testFile named_ent_dtest_unknown.tsv
     
    919411. test on your own input:
    9295 {{{
    93 java -mx600m -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \
     96java -mx600m -cp stanford-ner-2017-06-09/stanford-ner.jar \
     97  edu.stanford.nlp.ie.crf.CRFClassifier \
    9498  -loadClassifier cnec-3class-model.ser.gz -textFile sample.txt
    9599}}}