mirror of https://github.com/explosion/spaCy.git
0e08e49e87
* Add Romanian lemmatizer lookup table. Adapted from http://www.lexiconista.com/datasets/lemmatization/ by replacing cedillas with commas (ș and ț). The original dataset is licensed under the Open Database License. * Fix one blatant issue in the Romanian lemmatizer * Romanian examples file * Add ro_tokenizer in conftest * Add Romanian lemmatizer test |
||
|---|---|---|
| .. | ||
| cli | ||
| data | ||
| displacy | ||
| lang | ||
| syntax | ||
| tests | ||
| tokens | ||
| __init__.pxd | ||
| __init__.py | ||
| __main__.py | ||
| _ml.py | ||
| about.py | ||
| attrs.pxd | ||
| attrs.pyx | ||
| compat.py | ||
| errors.py | ||
| glossary.py | ||
| gold.pxd | ||
| gold.pyx | ||
| language.py | ||
| lemmatizer.py | ||
| lexeme.pxd | ||
| lexeme.pyx | ||
| matcher.pyx | ||
| morphology.pxd | ||
| morphology.pyx | ||
| parts_of_speech.pxd | ||
| parts_of_speech.pyx | ||
| pipeline.pxd | ||
| pipeline.pyx | ||
| scorer.py | ||
| strings.pxd | ||
| strings.pyx | ||
| structs.pxd | ||
| symbols.pxd | ||
| symbols.pyx | ||
| tokenizer.pxd | ||
| tokenizer.pyx | ||
| typedefs.pxd | ||
| typedefs.pyx | ||
| util.py | ||
| vectors.pyx | ||
| vocab.pxd | ||
| vocab.pyx | ||