explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-13 05:07:03 +03:00
Code Issues Packages Projects Releases Wiki Activity

Lower-case text before alignment

Browse Source
This commit is contained in:
Matthew Honnibal 2018-08-16 00:42:36 +02:00
parent 595c893791
commit 66a3f2ba21
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/gold.pyx
View File

@ -76,8 +76,8 @@ def align(cand_words, gold_words):
if cand_words == gold_words: if cand_words == gold_words:
alignment = numpy.arange(len(cand_words)) alignment = numpy.arange(len(cand_words))
return 0, alignment, alignment, {}, {} return 0, alignment, alignment, {}, {}
cand_words = [w.replace(' ', '') for w in cand_words] cand_words = [w.replace(' ', '').lower() for w in cand_words]
gold_words = [w.replace(' ', '') for w in gold_words] gold_words = [w.replace(' ', '').lower() for w in gold_words]
cost, i2j, j2i, matrix = _align.align(cand_words, gold_words) cost, i2j, j2i, matrix = _align.align(cand_words, gold_words)
i2j_multi, j2i_multi = _align.multi_align(i2j, j2i, [len(w) for w in cand_words], i2j_multi, j2i_multi = _align.multi_align(i2j, j2i, [len(w) for w in cand_words],
[len(w) for w in gold_words]) [len(w) for w in gold_words])