mirror of https://github.com/explosion/spaCy.git
2da16adcc2
Dropout can now be specified in the `Parser.update()` method via
the `drop` keyword argument, e.g.
nlp.entity.update(doc, gold, drop=0.4)
This will randomly drop 40% of features, and multiply the value of the
others by 1. / 0.4. This may be useful for generalising from small data
sets.
This commit also patches the examples/training/train_new_entity_type.py
example, to use dropout and fix the output (previously it did not output
the learned entity).
|
||
|---|---|---|
| .. | ||
| load_ner.py | ||
| train_ner.py | ||
| train_ner_standalone.py | ||
| train_new_entity_type.py | ||
| train_parser.py | ||
| train_tagger.py | ||