Updade devfinition
Browse filesadded serbian version, add HTML link
app.py
CHANGED
@@ -20,11 +20,18 @@ iface = gr.Interface(
|
|
20 |
outputs=[gr.outputs.Label(num_top_classes=3), "text"],
|
21 |
title="Sentiment Analysis for Serbian",
|
22 |
description="""
|
|
|
|
|
|
|
|
|
|
|
23 |
This tool performs sentiment analysis on the input text using a model trained on Serbian dictionary definitions.
|
24 |
-
The
|
25 |
-
|
26 |
The outputs represent the Positive (POS), Negative (NEG), and Objective (OBJ) sentiment scores.
|
27 |
""",
|
|
|
|
|
28 |
examples=[
|
29 |
["osoba koja ne prihvata nove ideje"],
|
30 |
["intenzivna ojađenost"],
|
|
|
20 |
outputs=[gr.outputs.Label(num_top_classes=3), "text"],
|
21 |
title="Sentiment Analysis for Serbian",
|
22 |
description="""
|
23 |
+
Ovaj alat vrši analizu sentimenta na uneseni tekst koristeći model obučen na definicijama srpskog rečnika.
|
24 |
+
Model je prvobitno bio prethodno obučen na <a href='https://huggingface.co/JeRTeh/sr-gpt2-large' target='_blank'>sr-gpt2-large modelu Mihaila Škorića</a>,
|
25 |
+
a potom je bio usavršen na odabranim definicijama iz srpskog WordNeta. Molimo vas da ograničite unos na 300 tokena.
|
26 |
+
Izlazi predstavljaju pozitivne (POS), negativne (NEG) i objektivne (OBJ) ocene sentimenta.
|
27 |
+
|
28 |
This tool performs sentiment analysis on the input text using a model trained on Serbian dictionary definitions.
|
29 |
+
The model was initially pretrained on the <a href='https://huggingface.co/JeRTeh/sr-gpt2-large' target='_blank'>sr-gpt2-large model by Mihailo Škorić</a>,
|
30 |
+
then fine-tuned on selected definitions from the Serbian WordNet. Please limit the input to 300 tokens.
|
31 |
The outputs represent the Positive (POS), Negative (NEG), and Objective (OBJ) sentiment scores.
|
32 |
""",
|
33 |
+
,
|
34 |
+
,
|
35 |
examples=[
|
36 |
["osoba koja ne prihvata nove ideje"],
|
37 |
["intenzivna ojađenost"],
|