JoBeer commited on
Commit
0ac4d87
1 Parent(s): ab39a91

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -39,7 +39,7 @@ interface = gr.Interface(fn = predict,
39
  title = 'ECLASS-Property-Search',
40
  description = "This is a semantic search algorithm that maps unknown pump properties to the ECLASS standard. It is created by the GART-labortory ot the cologne university of applied science for the usecase of semantic interoperable asset administration shells (industry 4.0).",
41
  article = """<center><Strong><font size="5em">Functionality and further development of the demo</font></strong></center>
42
- This demo is based on a sentence-transformer <a href="https://huggingface.co/gart-labor/eng-distilBERT-se-eclass">language model</a>, which is trained on a ECLASS specific <a href="https://huggingface.co/datasets/gart-labor/eclassTrainST">dataset</a>. This dataset consists of manually generated paraphrases of ECLASS pump properties. During Training the language model learns to map these paraphrases to the eclass pump properties. In future work, this approach can be extended to additional ECLASS properties (e.g. heating systems, ventilation, etc.) and thus a general language model can be trained. To reduce the manual effort, the integration of chatGPT is suitable for the automated creation of the paraphrases required for training.
43
  <br>
44
  <br>
45
  <center><img src='https://imagizer.imageshack.com/img923/6324/WOXHiX.png' width=900p></center>""")
 
39
  title = 'ECLASS-Property-Search',
40
  description = "This is a semantic search algorithm that maps unknown pump properties to the ECLASS standard. It is created by the GART-labortory ot the cologne university of applied science for the usecase of semantic interoperable asset administration shells (industry 4.0).",
41
  article = """<center><Strong><font size="5em">Functionality and further development of the demo</font></strong></center>
42
+ This demo is based on a sentence-transformer <a href="https://huggingface.co/gart-labor/eng-distilBERT-se-eclass">language model</a>, which is trained on a ECLASS specific <a href="https://huggingface.co/datasets/gart-labor/eclassTrainST">dataset</a>. This dataset consists of manually generated paraphrases of ECLASS pump properties. During training the language model learns to map these paraphrases to the eclass pump properties. In future work, this approach can be extended to additional ECLASS properties (e.g. heating systems, ventilation, etc.) and thus a general language model can be trained. To reduce the manual effort, the integration of chatGPT is suitable for the automated creation of the paraphrases required for training.
43
  <br>
44
  <br>
45
  <center><img src='https://imagizer.imageshack.com/img923/6324/WOXHiX.png' width=900p></center>""")