explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add case expansion to Brown clusters

Browse Source
This commit is contained in:
Matthew Honnibal 2015-05-31 05:50:50 +02:00
parent 5ab0f233a1
commit c037f80638
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
bin/init_model.py
View File

@ -52,6 +52,14 @@ def _read_clusters(loc):
clusters[word] = cluster clusters[word] = cluster
else: else:
clusters[word] = '0' clusters[word] = '0'
# Expand clusters with re-casing
for word, cluster in clusters.items():
if word.lower() not in clusters:
clusters[word.lower()] = cluster
if word.title() not in clusters:
clusters[word.title()] = cluster
if word.upper() not in clusters
clusters[word.upper()] = cluster
return clusters return clusters