lukasweber commited on
Commit
eaaf8a1
·
1 Parent(s): 791822c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -5,8 +5,11 @@ tags:
5
  - automotive
6
  ---
7
 
8
- WG_BERT is a pre-trained NLP model to analyze automotive entities in automotive-related texts. WG_BERT is build by continual
9
  pretraining the BERT language model in the automotive domain by using a corpus of automotive (workshop feedback) texts via the masked language modelling (MLM) approach.
10
  WG_BERT is further fine-tuned for automotive entity recognition (subtask of Named Entity Recognition (NER)) to extract components and its complaints out of automotive texts.
11
  The dataset for continual pretraining consists of ~ 4 million sentences.
12
  The dataset for fine-tuning consists of ~5.500 gold annotated sentences by automotive domain experts.
 
 
 
 
5
  - automotive
6
  ---
7
 
8
+ WG_BERT is a pre-trained model to analyze automotive entities in automotive-related texts. WG_BERT is build by continual
9
  pretraining the BERT language model in the automotive domain by using a corpus of automotive (workshop feedback) texts via the masked language modelling (MLM) approach.
10
  WG_BERT is further fine-tuned for automotive entity recognition (subtask of Named Entity Recognition (NER)) to extract components and its complaints out of automotive texts.
11
  The dataset for continual pretraining consists of ~ 4 million sentences.
12
  The dataset for fine-tuning consists of ~5.500 gold annotated sentences by automotive domain experts.
13
+ We choose as the training architecture the BERT-base-uncased version.
14
+
15
+ Please contact Lukas Weber lukas-weber[at]hotmail[dot]de / lukas.l.weber[at]mercedes-benz[dot]com about any WG_BERT related issues and questions.