return 10 results

app.py

@@ -16,7 +16,7 @@ lex_l12 = LexRankL12()
 # 摘要方法1
 def extract_handler(content):
     summary_length = math.ceil(len(content) / 10)
-    sentences = lex.find_central(content, num=summary_length)
+    sentences = lex.find_central(content)
     output = ""
     for index, sentence in enumerate(sentences):
         output += f"{index}: {sentence}\n"
@@ -26,7 +26,7 @@ def extract_handler(content):
 # 摘要方法2
 def extract_handler_distiluse_v1(content):
     summary_length = math.ceil(len(content) / 10)
-    sentences = lex_distiluse_v1.find_central(content, num=summary_length)
+    sentences = lex_distiluse_v1.find_central(content)
     output = ""
     for index, sentence in enumerate(sentences):
         output += f"{index}: {sentence}\n"
@@ -36,7 +36,7 @@ def extract_handler_distiluse_v1(content):
 # 摘要方法3
 def extract_handler_l12(content):
     summary_length = math.ceil(len(content) / 10)
-    sentences = lex_l12.find_central(content, num=summary_length)
+    sentences = lex_l12.find_central(content)
     output = ""
     for index, sentence in enumerate(sentences):
         output += f"{index}: {sentence}\n"

lex_rank.py

@@ -12,7 +12,7 @@ class LexRank(object):
         self.model = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')
         self.ht = HarvestText()
 
-    def find_central(self, content: str, num=100):
+    def find_central(self, content: str, num=10):
         if self.contains_chinese(content):
             sentences = self.ht.cut_sentences(content)
         else:
@@ -34,7 +34,7 @@ class LexRank(object):
             if num < 0:
                 break
             res.append(sentences[index])
-            num -= len(sentences[index])
+            num -= 1
         return res
 
     def contains_chinese(self, content: str):

lex_rank_L12.py

@@ -12,7 +12,7 @@ class LexRankL12(object):
         self.model = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')
         self.ht = HarvestText()
 
-    def find_central(self, content: str, num=100):
+    def find_central(self, content: str, num=10):
         if self.contains_chinese(content):
             sentences = self.ht.cut_sentences(content)
         else:
@@ -34,7 +34,7 @@ class LexRankL12(object):
             if num < 0:
                 break
             res.append(sentences[index])
-            num -= len(sentences[index])
+            num -= 1
         return res
 
     def contains_chinese(self, content: str):

lex_rank_distiluse_v1.py

@@ -12,7 +12,7 @@ class LexRankDistiluseV1(object):
         self.model = SentenceTransformer('distiluse-base-multilingual-cased-v1')
         self.ht = HarvestText()
 
-    def find_central(self, content: str, num=100):
+    def find_central(self, content: str, num=10):
         if self.contains_chinese(content):
             sentences = self.ht.cut_sentences(content)
         else:
@@ -34,7 +34,7 @@ class LexRankDistiluseV1(object):
             if num < 0:
                 break
             res.append(sentences[index])
-            num -= len(sentences[index])
+            num -= 1
         return res
 
     def contains_chinese(self, content: str):