Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -38,11 +38,11 @@ interface = gr.Interface(fn = predict,
|
|
38 |
#theme = 'huggingface',
|
39 |
title = 'ECLASS-Property-Search',
|
40 |
description = "This is a semantic search algorithm that mapps unknown pump properties to the ECLASS standard. It is created by the GART-labortory ot the cologne university of applied science for the use case of semantic interoperable asset administration shells.",
|
41 |
-
article = """<center><Strong><font size="5em">Functionality and further development of the demo</font></strong>
|
42 |
<br>
|
43 |
This demo is based on a sentence-transformer [language model](https://huggingface.co/gart-labor/eng-distilBERT-se-eclass), which is trained on a ECLASS specific [dataset](https://huggingface.co/datasets/gart-labor/eclassTrainST). 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.
|
44 |
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.
|
45 |
<br>
|
46 |
-
<img src='https://imagizer.imageshack.com/img923/6324/WOXHiX.png' width=900p></center>""")
|
47 |
|
48 |
interface.launch()
|
|
|
38 |
#theme = 'huggingface',
|
39 |
title = 'ECLASS-Property-Search',
|
40 |
description = "This is a semantic search algorithm that mapps unknown pump properties to the ECLASS standard. It is created by the GART-labortory ot the cologne university of applied science for the use case of semantic interoperable asset administration shells.",
|
41 |
+
article = """<center><Strong><font size="5em">Functionality and further development of the demo</font></strong></center>
|
42 |
<br>
|
43 |
This demo is based on a sentence-transformer [language model](https://huggingface.co/gart-labor/eng-distilBERT-se-eclass), which is trained on a ECLASS specific [dataset](https://huggingface.co/datasets/gart-labor/eclassTrainST). 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.
|
44 |
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.
|
45 |
<br>
|
46 |
+
<center><img src='https://imagizer.imageshack.com/img923/6324/WOXHiX.png' width=900p></center>""")
|
47 |
|
48 |
interface.launch()
|