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).
|
||
|---|---|---|
| .. | ||
| __init__.pxd | ||
| __init__.py | ||
| _parse_features.pxd | ||
| _parse_features.pyx | ||
| _state.pxd | ||
| _state.pyx | ||
| arc_eager.pxd | ||
| arc_eager.pyx | ||
| beam_parser.pxd | ||
| beam_parser.pyx | ||
| iterators.pxd | ||
| iterators.pyx | ||
| ner.pxd | ||
| ner.pyx | ||
| nonproj.pxd | ||
| nonproj.pyx | ||
| parser.pxd | ||
| parser.pyx | ||
| stateclass.pxd | ||
| stateclass.pyx | ||
| transition_system.pxd | ||
| transition_system.pyx | ||