243 lines
8.0 KiB
Plaintext
243 lines
8.0 KiB
Plaintext
.. Copyright (C) 2001-2019 NLTK Project
|
|
.. For license information, see LICENSE.TXT
|
|
|
|
.. -*- coding: utf-8 -*-
|
|
|
|
=========
|
|
Alignment
|
|
=========
|
|
|
|
Corpus Reader
|
|
-------------
|
|
|
|
>>> from nltk.corpus import comtrans
|
|
>>> words = comtrans.words('alignment-en-fr.txt')
|
|
>>> for word in words[:6]:
|
|
... print(word)
|
|
Resumption
|
|
of
|
|
the
|
|
session
|
|
I
|
|
declare
|
|
>>> als = comtrans.aligned_sents('alignment-en-fr.txt')[0]
|
|
>>> als # doctest: +NORMALIZE_WHITESPACE
|
|
AlignedSent(['Resumption', 'of', 'the', 'session'],
|
|
['Reprise', 'de', 'la', 'session'],
|
|
Alignment([(0, 0), (1, 1), (2, 2), (3, 3)]))
|
|
|
|
|
|
Alignment Objects
|
|
-----------------
|
|
|
|
Aligned sentences are simply a mapping between words in a sentence:
|
|
|
|
>>> print(" ".join(als.words))
|
|
Resumption of the session
|
|
>>> print(" ".join(als.mots))
|
|
Reprise de la session
|
|
>>> als.alignment
|
|
Alignment([(0, 0), (1, 1), (2, 2), (3, 3)])
|
|
|
|
|
|
Usually we look at them from the perspective of a source to a target language,
|
|
but they are easily inverted:
|
|
|
|
>>> als.invert() # doctest: +NORMALIZE_WHITESPACE
|
|
AlignedSent(['Reprise', 'de', 'la', 'session'],
|
|
['Resumption', 'of', 'the', 'session'],
|
|
Alignment([(0, 0), (1, 1), (2, 2), (3, 3)]))
|
|
|
|
|
|
We can create new alignments, but these need to be in the correct range of
|
|
the corresponding sentences:
|
|
|
|
>>> from nltk.translate import Alignment, AlignedSent
|
|
>>> als = AlignedSent(['Reprise', 'de', 'la', 'session'],
|
|
... ['Resumption', 'of', 'the', 'session'],
|
|
... Alignment([(0, 0), (1, 4), (2, 1), (3, 3)]))
|
|
Traceback (most recent call last):
|
|
...
|
|
IndexError: Alignment is outside boundary of mots
|
|
|
|
|
|
You can set alignments with any sequence of tuples, so long as the first two
|
|
indexes of the tuple are the alignment indices:
|
|
|
|
>>> als.alignment = Alignment([(0, 0), (1, 1), (2, 2, "boat"), (3, 3, False, (1,2))])
|
|
|
|
>>> Alignment([(0, 0), (1, 1), (2, 2, "boat"), (3, 3, False, (1,2))])
|
|
Alignment([(0, 0), (1, 1), (2, 2, 'boat'), (3, 3, False, (1, 2))])
|
|
|
|
|
|
Alignment Algorithms
|
|
--------------------
|
|
|
|
EM for IBM Model 1
|
|
~~~~~~~~~~~~~~~~~~
|
|
|
|
Here is an example from Koehn, 2010:
|
|
|
|
>>> from nltk.translate import IBMModel1
|
|
>>> corpus = [AlignedSent(['the', 'house'], ['das', 'Haus']),
|
|
... AlignedSent(['the', 'book'], ['das', 'Buch']),
|
|
... AlignedSent(['a', 'book'], ['ein', 'Buch'])]
|
|
>>> em_ibm1 = IBMModel1(corpus, 20)
|
|
>>> print(round(em_ibm1.translation_table['the']['das'], 1))
|
|
1.0
|
|
>>> print(round(em_ibm1.translation_table['book']['das'], 1))
|
|
0.0
|
|
>>> print(round(em_ibm1.translation_table['house']['das'], 1))
|
|
0.0
|
|
>>> print(round(em_ibm1.translation_table['the']['Buch'], 1))
|
|
0.0
|
|
>>> print(round(em_ibm1.translation_table['book']['Buch'], 1))
|
|
1.0
|
|
>>> print(round(em_ibm1.translation_table['a']['Buch'], 1))
|
|
0.0
|
|
>>> print(round(em_ibm1.translation_table['book']['ein'], 1))
|
|
0.0
|
|
>>> print(round(em_ibm1.translation_table['a']['ein'], 1))
|
|
1.0
|
|
>>> print(round(em_ibm1.translation_table['the']['Haus'], 1))
|
|
0.0
|
|
>>> print(round(em_ibm1.translation_table['house']['Haus'], 1))
|
|
1.0
|
|
>>> print(round(em_ibm1.translation_table['book'][None], 1))
|
|
0.5
|
|
|
|
And using an NLTK corpus. We train on only 10 sentences, since it is so slow:
|
|
|
|
>>> from nltk.corpus import comtrans
|
|
>>> com_ibm1 = IBMModel1(comtrans.aligned_sents()[:10], 20)
|
|
>>> print(round(com_ibm1.translation_table['bitte']['Please'], 1))
|
|
0.2
|
|
>>> print(round(com_ibm1.translation_table['Sitzungsperiode']['session'], 1))
|
|
1.0
|
|
|
|
|
|
Evaluation
|
|
----------
|
|
The evaluation metrics for alignments are usually not interested in the
|
|
contents of alignments but more often the comparison to a "gold standard"
|
|
alignment that has been been constructed by human experts. For this reason we
|
|
often want to work just with raw set operations against the alignment points.
|
|
This then gives us a very clean form for defining our evaluation metrics.
|
|
|
|
.. Note::
|
|
The AlignedSent class has no distinction of "possible" or "sure"
|
|
alignments. Thus all alignments are treated as "sure".
|
|
|
|
Consider the following aligned sentence for evaluation:
|
|
|
|
>>> my_als = AlignedSent(['Resumption', 'of', 'the', 'session'],
|
|
... ['Reprise', 'de', 'la', 'session'],
|
|
... Alignment([(0, 0), (3, 3), (1, 2), (1, 1), (1, 3)]))
|
|
|
|
Precision
|
|
~~~~~~~~~
|
|
``precision = |A∩P| / |A|``
|
|
|
|
**Precision** is probably the most well known evaluation metric and it is implemented
|
|
in `nltk.metrics.scores.precision`_. Since precision is simply interested in the
|
|
proportion of correct alignments, we calculate the ratio of the number of our
|
|
test alignments (*A*) that match a possible alignment (*P*), over the number of
|
|
test alignments provided. There is no penalty for missing a possible alignment
|
|
in our test alignments. An easy way to game this metric is to provide just one
|
|
test alignment that is in *P* [OCH2000]_.
|
|
|
|
Here are some examples:
|
|
|
|
>>> from nltk.metrics import precision
|
|
>>> als.alignment = Alignment([(0,0), (1,1), (2,2), (3,3)])
|
|
>>> precision(Alignment([]), als.alignment)
|
|
0.0
|
|
>>> precision(Alignment([(0,0), (1,1), (2,2), (3,3)]), als.alignment)
|
|
1.0
|
|
>>> precision(Alignment([(0,0), (3,3)]), als.alignment)
|
|
0.5
|
|
>>> precision(Alignment.fromstring('0-0 3-3'), als.alignment)
|
|
0.5
|
|
>>> precision(Alignment([(0,0), (1,1), (2,2), (3,3), (1,2), (2,1)]), als.alignment)
|
|
1.0
|
|
>>> precision(als.alignment, my_als.alignment)
|
|
0.6
|
|
|
|
|
|
.. _nltk.metrics.scores.precision:
|
|
http://www.nltk.org/api/nltk.metrics.html#nltk.metrics.scores.precision
|
|
|
|
|
|
Recall
|
|
~~~~~~
|
|
``recall = |A∩S| / |S|``
|
|
|
|
**Recall** is another well known evaluation metric that has a set based
|
|
implementation in NLTK as `nltk.metrics.scores.recall`_. Since recall is
|
|
simply interested in the proportion of found alignments, we calculate the
|
|
ratio of the number of our test alignments (*A*) that match a sure alignment
|
|
(*S*) over the number of sure alignments. There is no penalty for producing
|
|
a lot of test alignments. An easy way to game this metric is to include every
|
|
possible alignment in our test alignments, regardless if they are correct or
|
|
not [OCH2000]_.
|
|
|
|
Here are some examples:
|
|
|
|
>>> from nltk.metrics import recall
|
|
>>> print(recall(Alignment([]), als.alignment))
|
|
None
|
|
>>> recall(Alignment([(0,0), (1,1), (2,2), (3,3)]), als.alignment)
|
|
1.0
|
|
>>> recall(Alignment.fromstring('0-0 3-3'), als.alignment)
|
|
1.0
|
|
>>> recall(Alignment([(0,0), (3,3)]), als.alignment)
|
|
1.0
|
|
>>> recall(Alignment([(0,0), (1,1), (2,2), (3,3), (1,2), (2,1)]), als.alignment)
|
|
0.66666...
|
|
>>> recall(als.alignment, my_als.alignment)
|
|
0.75
|
|
|
|
|
|
.. _nltk.metrics.scores.recall:
|
|
http://www.nltk.org/api/nltk.metrics.html#nltk.metrics.scores.recall
|
|
|
|
|
|
Alignment Error Rate (AER)
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
``AER = 1 - (|A∩S| + |A∩P|) / (|A| + |S|)``
|
|
|
|
**Alignment Error Rate** is commonly used metric for assessing sentence
|
|
alignments. It combines precision and recall metrics together such that a
|
|
perfect alignment must have all of the sure alignments and may have some
|
|
possible alignments [MIHALCEA2003]_ [KOEHN2010]_.
|
|
|
|
.. Note::
|
|
[KOEHN2010]_ defines the AER as ``AER = (|A∩S| + |A∩P|) / (|A| + |S|)``
|
|
in his book, but corrects it to the above in his online errata. This is
|
|
in line with [MIHALCEA2003]_.
|
|
|
|
Here are some examples:
|
|
|
|
>>> from nltk.translate import alignment_error_rate
|
|
>>> alignment_error_rate(Alignment([]), als.alignment)
|
|
1.0
|
|
>>> alignment_error_rate(Alignment([(0,0), (1,1), (2,2), (3,3)]), als.alignment)
|
|
0.0
|
|
>>> alignment_error_rate(als.alignment, my_als.alignment)
|
|
0.333333...
|
|
>>> alignment_error_rate(als.alignment, my_als.alignment,
|
|
... als.alignment | Alignment([(1,2), (2,1)]))
|
|
0.222222...
|
|
|
|
|
|
.. [OCH2000] Och, F. and Ney, H. (2000)
|
|
*Statistical Machine Translation*, EAMT Workshop
|
|
|
|
.. [MIHALCEA2003] Mihalcea, R. and Pedersen, T. (2003)
|
|
*An evaluation exercise for word alignment*, HLT-NAACL 2003
|
|
|
|
.. [KOEHN2010] Koehn, P. (2010)
|
|
*Statistical Machine Translation*, Cambridge University Press
|
|
|
|
|