Changes between Version 17 and Version 18 of private/NlpInPracticeCourse/NamedEntityRecognition
- Timestamp:
- Oct 9, 2017, 11:44:59 AM (7 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
private/NlpInPracticeCourse/NamedEntityRecognition
v17 v18 56 56 1. 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: 57 57 {{{ 58 java -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \ 58 java -cp stanford-ner-2017-06-09/stanford-ner.jar \ 59 edu.stanford.nlp.ie.crf.CRFClassifier \ 59 60 -prop cnec.prop 60 61 }}} … … 66 67 1. evaluate the model on `dtest`: 67 68 {{{ 68 java -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \ 69 java -cp stanford-ner-2017-06-09/stanford-ner.jar \ 70 edu.stanford.nlp.ie.crf.CRFClassifier \ 69 71 -loadClassifier cnec-3class-model.ser.gz \ 70 72 -testFile named_ent_dtest.tsv … … 83 85 10. evaluate the model on `dtest` with only NEs that are not present in the train data: 84 86 {{{ 85 java -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \ 87 java -cp stanford-ner-2017-06-09/stanford-ner.jar \ 88 edu.stanford.nlp.ie.crf.CRFClassifier \ 86 89 -loadClassifier cnec-3class-model.ser.gz \ 87 90 -testFile named_ent_dtest_unknown.tsv … … 91 94 11. test on your own input: 92 95 {{{ 93 java -mx600m -cp stanford-ner-2017-06-09/stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier \ 96 java -mx600m -cp stanford-ner-2017-06-09/stanford-ner.jar \ 97 edu.stanford.nlp.ie.crf.CRFClassifier \ 94 98 -loadClassifier cnec-3class-model.ser.gz -textFile sample.txt 95 99 }}}