Rename sentence summarization to sentence shortening for clarity

run.py

@@ -72,7 +72,7 @@ if __name__ == '__main__':
                         required=True)
     parser.add_argument('--length_constraint',
                         type=str,
-                        choices=['sentences', 'tokens'], default='sentences',
+                        choices=['sentences', 'tokens'], default='tokens',
                         help='what constraint to impose on the length of the generated timeline '
                              '(number of sentences or number of tokens)')
     parser.add_argument('--shorten_sentences',

sentence_summarization.py → sentence_shortening.py

@@ -8,11 +8,11 @@ with open('data/in/sentence_summarization_vocab.txt', encoding='utf-8') as f:
     vocab = [line.strip() for line in f.readlines() if line.strip()]
 
 
-def summarization(sentence, num_tokens, do_deunk=True):
+def shorten(sentence, num_tokens, do_resolve_unks=True):
     try:
         summarized_sentence = summarized_sentences[sentence.lower()][num_tokens]
-        if do_deunk:
-            summarized_sentence = deunk(sentence, summarized_sentence)
+        if do_resolve_unks:
+            summarized_sentence = resolve_unks(sentence, summarized_sentence)
         return summarized_sentence
     except KeyError:
         print(sentence)
@@ -21,7 +21,7 @@ def summarization(sentence, num_tokens, do_deunk=True):
         return sentence
 
 
-def deunk(sentence, summarized_sentence):
+def resolve_unks(sentence, summarized_sentence):
     sentence = sentence.split()
     summarized_sentence = summarized_sentence.split()
 
@@ -54,4 +54,4 @@ def deunk(sentence, summarized_sentence):
 
 
 if __name__ == '__main__':
-    print(summarization('and this was on - going in egypt before january 25 .', 10))
+    print(shorten('and this was on - going in egypt before january 25 .', 10))

timeline_generation.py

@@ -5,7 +5,7 @@ import date_selection
 import evaluation
 import sentence_selection
 import summarization
-import sentence_summarization
+import sentence_shortening
 import util
 
 
@@ -44,8 +44,8 @@ def make_timeline(articles, gold_timeline, keywords, by_tokens, shorten_sentence
             new_candidate_sentences = []
             for i in range(len(candidate_sentences)):
                 new_candidate_sentences.append({
-                    'text': sentence_summarization.summarization(candidate_sentences[i]['text'], shortening_length,
-                                                                 resolve_unks),
+                    'text': sentence_shortening.shorten(candidate_sentences[i]['text'], shortening_length,
+                                                        resolve_unks),
                     'mentioned_dates': candidate_sentences[i]['mentioned_dates']
                 })
             candidate_sentences = new_candidate_sentences
@@ -58,7 +58,7 @@ def make_timeline(articles, gold_timeline, keywords, by_tokens, shorten_sentence
 
         # shorten sentences if needed
         if shorten_sentences == 'after_summarization':
-            summary_for_date = [sentence_summarization.summarization(sentence, 8, resolve_unks)
+            summary_for_date = [sentence_shortening.shorten(sentence, shortening_length, resolve_unks)
                                 for sentence in summary_for_date]
 
         timeline[date] = summary_for_date