Changes between Version 8 and Version 9 of private/AdvancedNlpCourse/NamedEntityRecognition


Ignore:
Timestamp:
Oct 12, 2015, 9:53:28 AM (5 years ago)
Author:
Ales Horak
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • private/AdvancedNlpCourse/NamedEntityRecognition

    v8 v9  
    5656         Totals 0.7814  0.7711  0.7763  994     278     295
    5757}}}
    58 In the output, the first column is the input tokens, the second column is the correct (gold) answers. Observe the differences. Copy the training result to `<YOUR_FILE>`. Try to estimate in how many the model missed an entity, detected incorrectly the boundaries, or classified an entity incorrectly.
     58In the output, the first column is the input tokens, the second column is the correct (gold) answers. Observe the differences. Copy the training result to `<YOUR_FILE>`. Try to estimate in how many cases the model missed an entity, detected incorrectly the boundaries, or classified an entity incorrectly.
    595910. evaluate the model on `dtest` with only NEs that are not present in the train data: `java -cp stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier cnec-3class-model.ser.gz -testFile named_ent_dtest_unknown.tsv`. Copy the result to `<YOUR_FILE>`.
    606011. test on your own input: `java -mx600m -cp stanford-ner.jar edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier cnec-3class-model.ser.gz -textFile sample.txt`. Copy the result to `<YOUR_FILE>`.
    6161
    6262(optional) 12. try to improve the train data
    63 suggestions: set useKnownLCWords to false, add gazetteers, remove punctuation, try to change the wordshape (something following the pattern: `dan[12](bio)?(UseLC)?, jenny1(useLC)?, chris[1234](useLC)?, cluster1)` or word shape features (see the documentation). Copy the result to `<YOUR_FILE>`.
     63suggestions: set `useKnownLCWords` to false, add gazetteers, remove punctuation, try to change the wordshape (something following the pattern: `dan[12](bio)?(UseLC)?, jenny1(useLC)?, chris[1234](useLC)?, cluster1)` or word shape features (see the documentation). Copy the result to `<YOUR_FILE>`.
    6464(optional) 13. evaluate the model on dtest, final evaluation on etest
    6565