update parser

ResumeParser.py

@@ -84,26 +84,30 @@ class ResumeParser:
         self.parsed_cv["Job History"] = job_history 
 
     def get_job_titles(self, resume_segment):
-        classes = ["organization", "institution", "job title", "role"]
+        classes = ["organization", "institution", "company", "job title", "work details"]
         idx_line = []
         for idx, line in enumerate(resume_segment):
             has_verb = False
-            sentence = self.models.get_flair_sentence(line)
+            line_modifed = ''.join(i for i in line if not i.isdigit())
+            sentence = self.models.get_flair_sentence(line_modifed)
             self.tagger.predict(sentence)
+            tags = []
             for entity in sentence.get_spans('pos'):
+                tags.append(entity.tag)
                 if entity.tag.startswith("V"): 
                     has_verb = True
-                    break
-            if not has_verb:
-                out = self.zero_shot_classifier(line, classes)
-                class_score = zip(out["labels"], out["scores"])
-                highest = sorted(class_score, key=lambda x: x[1])[-1]
 
-                if highest[0] == "job title":
-                    idx_line.append((idx, line))
+            most_common_tag = max(set(tags), key=tags.count)
+            if most_common_tag == "NNP":
+                if not has_verb:
+                    out = self.zero_shot_classifier(line, classes)
+                    class_score = zip(out["labels"], out["scores"])
+                    highest = sorted(class_score, key=lambda x: x[1])[-1]
+
+                    if highest[0] == "job title":
+                        idx_line.append((idx, line))
 
         return idx_line
-    
 
     def get_job_dates(self, st, end, resume_segment):
         search_span = resume_segment[st:end]