first draft of the space

README.md

@@ -2,7 +2,7 @@
 title: Semantic Frame Augmentation
 emoji: 🚀
 colorFrom: gray
-colorTo: pink
+colorTo: yellow
 sdk: streamlit
 sdk_version: 1.31.1
 app_file: app.py

app.py

@@ -0,0 +1,44 @@
+import torch
+import streamlit as st
+from transformers import pipeline
+from random import choice
+
+with open("sentences.pt", 'rb') as f:
+    sentences = torch.load(f)
+
+baseline_classifier = pipeline(
+    model="Dagobert42/mobilebert-uncased-biored-finetuned-ner",
+    task="ner",
+    aggregation_strategy="simple"
+    )
+augmented_classifier = pipeline(
+    model="Dagobert42/mobilebert-uncased-biored-augmented-ner",
+    task="ner",
+    aggregation_strategy="simple"
+    )
+
+st.title("Semantic Frame Augmentation")
+st.caption("Analysing difficult low-resource domains with only a handful of examples")
+
+st.write("This space uses a googel/mobilebert-uncased model for named entity ")
+augment = st.toggle('Use augmented model for ', value=False)
+
+sentence = choice(sentences)
+
+if augment:
+    st.write("with augmentation:")
+    tokens = augmented_classifier(sentence)
+else:
+    st.write("without augmentation:")
+    tokens = baseline_classifier(sentence)
+
+txt = st.text_area(
+    "Text to analyze",
+    sentence,
+    max_chars=500
+    )
+
+st.subheader("Entity analysis:")
+for token in tokens:
+    st.write(token['entity_group'])
+    st.write(sentence[token["start"] : token["end"]])

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers
+torch

sentences.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2081e318c8b942b60a480ce78c4b9938e68be208359a43e27c702f7a6d531f43
+size 178144