magistermilitum
/

roberta-multilingual-medieval-ner

Token Classification Transformers PyTorch 4 languages xlm-roberta text named entity recognition roberta historical languages precision recall Eval Results Inference Endpoints

Model card Files Files and versions Community

magistermilitum commited on Oct 9, 2023

Commit

098aa7e

•

1 Parent(s): a276bc9

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -75,6 +75,7 @@ class TextProcessor:
         self.stripped_BIO_TAGS = []
     def read_file(self):
         with open(self.filename, 'r') as f:
             text = f.read()
         self.sentences = self.sent_detector.tokenize(text.strip())
@@ -157,7 +158,7 @@ class TextProcessor:
             output_file.write("TOKEN\tPERS\tLOCS\n"+"\n".join(["\t".join(x) for x in self.stripped_BIO_TAGS]))
 # Usage:
-processor = TextProcessor('sentence.txt')
 processor.read_file()
 processor.process_sentences()
 processor.apply_model(pipe)

         self.stripped_BIO_TAGS = []
     def read_file(self):
+        #Reading a txt file with one document per line.
         with open(self.filename, 'r') as f:
             text = f.read()
         self.sentences = self.sent_detector.tokenize(text.strip())
             output_file.write("TOKEN\tPERS\tLOCS\n"+"\n".join(["\t".join(x) for x in self.stripped_BIO_TAGS]))
 # Usage:
+processor = TextProcessor('my_docs_file.txt')
 processor.read_file()
 processor.process_sentences()
 processor.apply_model(pipe)