def evaluate(parallel_corpus, model, N=100):
"""
Returns statistics for N document alignment trials.
The documents are generated from the parallel corpus.
- `parallel_corpus`: A file object
- `model`: A YalignModel
- `N`: Number of trials
"""
results = []
for idx, docs in enumerate(generate_documents(parallel_corpus)):
A, B, alignments = training_scrambling_from_documents(*docs)
predicted_alignments = model.align_indexes(A, B)
scores = F_score(predicted_alignments, alignments)
results.append(scores)
if idx >= N - 1:
break
return _stats(results)
def evaluate(parallel_corpus, model, N=100):
"""
Returns statistics for N document alignment trials.
The documents are generated from the parallel corpus.
- `parallel_corpus`: A file object
- `model`: A YalignModel
- `N`: Number of trials
"""
results = []
for idx, docs in enumerate(generate_documents(parallel_corpus)):
A, B, alignments = training_scrambling_from_documents(*docs)
predicted_alignments = model.align_indexes(A, B)
scores = F_score(predicted_alignments, alignments)
results.append(scores)
if idx >= N - 1:
break
return _stats(results)
def basic_model(corpus_filepath,
word_scores_filepath,
lang_a=None,
lang_b=None):
"""
Creates and trains a `YalignModel` with the basic configuration and
default values.
`corpus_filepath` is the path to a parallel corpus used for training,
it can be:
- a csv file with two sentences and alignement information, or
- a tmx file with correct alignments (a regular parallel corpus), or
- a text file with interleaved sentences (one line in language A, the
next in language B)
`word_scores_filepath` is the path to a csv file (possibly gzipped) with
word dictionary data. (for ex. "house,casa,0.91").
`lang_a` and `lang_b` are requiered for the tokenizer in the case of a tmx
file. In the other cases is not necesary because it's assumed that the
words are already tokenized.
"""
# Word score
word_pair_score = WordPairScore(word_scores_filepath)
if corpus_filepath.endswith(".tmx"):
A, B = tmx_file_to_documents(corpus_filepath, lang_a, lang_b)
else:
A, B = parallel_corpus_to_documents(corpus_filepath)
alignments = training_alignments_from_documents(A, B)
sentence_pair_score = SentencePairScore()
sentence_pair_score.train(alignments, word_pair_score)
# Yalign model
metadata = {"lang_a": lang_a, "lang_b": lang_b}
gap_penalty = 0.49
threshold = 1.0
document_aligner = SequenceAligner(sentence_pair_score, gap_penalty)
model = YalignModel(document_aligner, threshold, metadata=metadata)
A, B, correct = training_scrambling_from_documents(
A[:OPTIMIZE_SAMPLE_SET_SIZE], B[:OPTIMIZE_SAMPLE_SET_SIZE])
model.optimize_gap_penalty_and_threshold(A, B, correct)
return model
def setUp(self):
random.seed(hash("Y U NO?"))
base_path = os.path.dirname(os.path.abspath(__file__))
word_scores = os.path.join(base_path, "data", "test_word_scores_big.csv")
parallel_corpus = os.path.join(base_path, "data", "parallel-en-es.txt")
A, B = parallel_corpus_to_documents(parallel_corpus)
A = A[:25]
B = B[:25]
self.alignments = list(training_alignments_from_documents(A, B))
self.A, self.B, self.correct_alignments = list(training_scrambling_from_documents(A, B))
# Word score
word_pair_score = WordPairScore(word_scores)
# Sentence Score
sentence_pair_score = SentencePairScore()
sentence_pair_score.train(self.alignments, word_pair_score)
# Yalign model
self.min_ = sentence_pair_score.min_bound
self.max_ = sentence_pair_score.max_bound
gap_penalty = (self.min_ + self.max_) / 2.0
document_aligner = SequenceAligner(sentence_pair_score, gap_penalty)
self.model = YalignModel(document_aligner, 1)
def basic_model(corpus_filepath, word_scores_filepath,
lang_a=None, lang_b=None):
"""
Creates and trains a `YalignModel` with the basic configuration and
default values.
`corpus_filepath` is the path to a parallel corpus used for training,
it can be:
- a csv file with two sentences and alignement information, or
- a tmx file with correct alignments (a regular parallel corpus), or
- a text file with interleaved sentences (one line in language A, the
next in language B)
`word_scores_filepath` is the path to a csv file (possibly gzipped) with
word dictionary data. (for ex. "house,casa,0.91").
`lang_a` and `lang_b` are requiered for the tokenizer in the case of a tmx
file. In the other cases is not necesary because it's assumed that the
words are already tokenized.
"""
# Word score
word_pair_score = WordPairScore(word_scores_filepath)
if corpus_filepath.endswith(".tmx"):
A, B = tmx_file_to_documents(corpus_filepath, lang_a, lang_b)
else:
A, B = parallel_corpus_to_documents(corpus_filepath)
alignments = training_alignments_from_documents(A, B)
sentence_pair_score = SentencePairScore()
sentence_pair_score.train(alignments, word_pair_score)
# Yalign model
metadata = {"lang_a": lang_a, "lang_b": lang_b}
gap_penalty = 0.49
threshold = 1.0
document_aligner = SequenceAligner(sentence_pair_score, gap_penalty)
model = YalignModel(document_aligner, threshold, metadata=metadata)
A, B, correct = training_scrambling_from_documents(A[:OPTIMIZE_SAMPLE_SET_SIZE], B[:OPTIMIZE_SAMPLE_SET_SIZE])
model.optimize_gap_penalty_and_threshold(A, B, correct)
return model
def setUp(self):
random.seed(hash("Y U NO?"))
base_path = os.path.dirname(os.path.abspath(__file__))
word_scores = os.path.join(base_path, "data",
"test_word_scores_big.csv")
parallel_corpus = os.path.join(base_path, "data", "parallel-en-es.txt")
A, B = parallel_corpus_to_documents(parallel_corpus)
A = A[:25]
B = B[:25]
self.alignments = list(training_alignments_from_documents(A, B))
self.A, self.B, self.correct_alignments = \
list(training_scrambling_from_documents(A, B))
# Word score
word_pair_score = WordPairScore(word_scores)
# Sentence Score
sentence_pair_score = SentencePairScore()
sentence_pair_score.train(self.alignments, word_pair_score)
# Yalign model
self.min_ = sentence_pair_score.min_bound
self.max_ = sentence_pair_score.max_bound
gap_penalty = (self.min_ + self.max_) / 2.0
document_aligner = SequenceAligner(sentence_pair_score, gap_penalty)
self.model = YalignModel(document_aligner, 1)
