Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix SumBasicSummarizer with stemmer #166

Merged
merged 1 commit into from
Mar 9, 2022
Merged

Fix SumBasicSummarizer with stemmer #166

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 7 additions & 9 deletions sumy/summarizers/sum_basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,9 @@

class SumBasicSummarizer(AbstractSummarizer):
"""
SumBasic: a frequency-based summarization system that adjusts word frequencies as
SumBasic: a frequency-based summarization system that adjusts word frequencies as
sentences are extracted.
Source: http://www.cis.upenn.edu/~nenkova/papers/ipm.pdf

"""
_stop_words = frozenset()

Expand All @@ -28,12 +27,11 @@ def __call__(self, document, sentences_count):
ratings = self._compute_ratings(sentences)
return self._get_best_sentences(document.sentences, sentences_count, ratings)

@staticmethod
def _get_all_words_in_doc(sentences):
return [w for s in sentences for w in s.words]
def _get_all_words_in_doc(self, sentences):
return self._stem_words([w for s in sentences for w in s.words])

def _get_content_words_in_sentence(self, sentence):
normalized_words = self._normalize_words(sentence.words)
normalized_words = self._normalize_words(sentence.words)
normalized_content_words = self._filter_out_stop_words(normalized_words)
stemmed_normalized_content_words = self._stem_words(normalized_content_words)
return stemmed_normalized_content_words
Expand Down Expand Up @@ -77,7 +75,7 @@ def _compute_average_probability_of_words(word_freq_in_doc, content_words_in_sen
word_freq_sum = sum([word_freq_in_doc[w] for w in content_words_in_sentence])
word_freq_avg = word_freq_sum / content_words_count
return word_freq_avg
else:
else:
return 0

@staticmethod
Expand All @@ -100,13 +98,13 @@ def _find_index_of_best_sentence(self, word_freq, sentences_as_words):
def _compute_ratings(self, sentences):
word_freq = self._compute_tf(sentences)
ratings = {}

# make it a list so that it can be modified
sentences_list = list(sentences)

# get all content words once for efficiency
sentences_as_words = [self._get_content_words_in_sentence(s) for s in sentences]

# Removes one sentence per iteration by adding to summary
while len(sentences_list) > 0:
best_sentence_index = self._find_index_of_best_sentence(word_freq, sentences_as_words)
Expand Down
10 changes: 9 additions & 1 deletion tests/test_summarizers/test_sum_basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,6 @@ def test_empty_document():


def test_single_sentence():

s = Sentence("I am one slightly longer sentence.", Tokenizer("english"))
document = build_document([s])
summarizer = _build_summarizer(EMPTY_STOP_WORDS)
Expand All @@ -39,6 +38,15 @@ def test_single_sentence():
assert len(returned) == 1


def test_stemmer_does_not_cause_crash():
"""https://github.com/miso-belica/sumy/issues/165"""
document = build_document([Sentence("Was ist das längste deutsche Wort?", Tokenizer("german"))])
summarizer = _build_summarizer(EMPTY_STOP_WORDS, Stemmer("german"))

returned = summarizer(document, 10)
assert len(returned) == 1


def test_normalize_words():
summarizer = _build_summarizer(EMPTY_STOP_WORDS)
sentence = "This iS A test 2 CHECk normalization."
Expand Down