From 92689087ab0711cd607ddcb68c56948e2fe54ff9 Mon Sep 17 00:00:00 2001
From: vvye <ekaiser.hellwege@gmail.com>
Date: Wed, 19 Jan 2022 15:37:42 +0100
Subject: [PATCH] Rename sentence summarization to sentence shortening for
clarity
---
sentence_shortening.py | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/sentence_shortening.py b/sentence_shortening.py
index 708db6c..34890e1 100644
--- a/sentence_shortening.py
+++ b/sentence_shortening.py
@@ -3,17 +3,17 @@ from Bio import pairwise2
import pickle
import string
-summarized_sentences = pickle.load(open('data/in/summarized_sentences.pkl', 'rb'))
+shortened_sentences = pickle.load(open('data/in/summarized_sentences.pkl', 'rb'))
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 shorten(sentence, num_tokens, do_resolve_unks=True):
try:
- summarized_sentence = summarized_sentences[sentence.lower()][num_tokens]
+ shortened_sentence = shortened_sentences[sentence.lower()][num_tokens]
if do_resolve_unks:
- summarized_sentence = resolve_unks(sentence, summarized_sentence)
- return summarized_sentence
+ shortened_sentence = resolve_unks(sentence, shortened_sentence)
+ return shortened_sentence
except KeyError:
print(sentence)
with open('missing-sentences_' + str(num_tokens) + '.txt', 'a', encoding='utf-8') as f:
--
GitLab