You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
43 lines
1.5 KiB
Python
43 lines
1.5 KiB
Python
5 years ago
|
# Natural Language Toolkit: Translation metrics
|
||
|
|
#
|
||
|
|
# Copyright (C) 2001-2019 NLTK Project
|
||
|
|
# Author: Will Zhang <wilzzha@gmail.com>
|
||
|
|
# Guan Gui <ggui@student.unimelb.edu.au>
|
||
|
|
# Steven Bird <stevenbird1@gmail.com>
|
||
|
|
# URL: <http://nltk.org/>
|
||
|
|
# For license information, see LICENSE.TXT
|
||
|
|
from __future__ import division
|
||
|
|
|
||
|
|
|
||
|
|
def alignment_error_rate(reference, hypothesis, possible=None):
|
||
|
|
"""
|
||
|
|
Return the Alignment Error Rate (AER) of an alignment
|
||
|
|
with respect to a "gold standard" reference alignment.
|
||
|
|
Return an error rate between 0.0 (perfect alignment) and 1.0 (no
|
||
|
|
alignment).
|
||
|
|
|
||
|
|
>>> from nltk.translate import Alignment
|
||
|
|
>>> ref = Alignment([(0, 0), (1, 1), (2, 2)])
|
||
|
|
>>> test = Alignment([(0, 0), (1, 2), (2, 1)])
|
||
|
|
>>> alignment_error_rate(ref, test) # doctest: +ELLIPSIS
|
||
|
|
0.6666666666666667
|
||
|
|
|
||
|
|
:type reference: Alignment
|
||
|
|
:param reference: A gold standard alignment (sure alignments)
|
||
|
|
:type hypothesis: Alignment
|
||
|
|
:param hypothesis: A hypothesis alignment (aka. candidate alignments)
|
||
|
|
:type possible: Alignment or None
|
||
|
|
:param possible: A gold standard reference of possible alignments
|
||
|
|
(defaults to *reference* if None)
|
||
|
|
:rtype: float or None
|
||
|
|
"""
|
||
|
|
|
||
|
|
if possible is None:
|
||
|
|
possible = reference
|
||
|
|
else:
|
||
|
|
assert reference.issubset(possible) # sanity check
|
||
|
|
|
||
|
|
return 1.0 - (len(hypothesis & reference) + len(hypothesis & possible)) / float(
|
||
|
|
len(hypothesis) + len(reference)
|
||
|
|
)
|