Update

README.md

@@ -1,9 +1,9 @@
 ---
-title: NamedEntityRecognition Romanian
-emoji: 📚
-colorFrom: blue
-colorTo: gray
-sdk: gradio
+title: Turkish Named Entity Recognition
+emoji: 🏃
+colorFrom: indigo
+colorTo: indigo
+sdk: streamlit
 app_file: app.py
 pinned: false
 ---
@@ -34,4 +34,4 @@ Path to your main application file (which contains either `gradio` or `streamlit
 Path is relative to the root of the repository.
 
 `pinned`: _boolean_  
-Whether the Space stays on top of your list.
+Whether the Space stays on top of your list.

app.py

@@ -1,7 +1,90 @@
-import gradio as gr
+import sentencepiece
+import streamlit as st
+import pandas as pd
+import spacy
+import roner
 
-def greet(name):
-    return "Hello " + name + "!!"
+example_list = [
+    "Ana merge în București.",
+    """Ana merge în București. Ana merge în București. Ana merge în București. Ana merge în București. Ana merge în București. Ana merge în București."""
+]
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+st.set_page_config(layout="wide")
+
+st.title("Demo for Romanian NER")
+
+model_list = ['dumitrescustefan/bert-base-romanian-ner']
+
+st.sidebar.header("Select NER Model")
+model_checkpoint = st.sidebar.radio("", model_list)
+
+st.sidebar.write("For details of models: 'https://huggingface.co/dumitrescustefan/")
+st.sidebar.write("")
+
+xlm_agg_strategy_info = "'aggregation_strategy' can be selected as 'simple' or 'none' for 'xlm-roberta' because of the RoBERTa model's tokenization approach."
+
+st.sidebar.header("Select Aggregation Strategy Type")
+if model_checkpoint == "akdeniz27/xlm-roberta-base-turkish-ner":
+    aggregation = st.sidebar.radio("", ('simple', 'none'))
+    st.sidebar.write(xlm_agg_strategy_info)
+elif model_checkpoint == "xlm-roberta-large-finetuned-conll03-english":
+    aggregation = st.sidebar.radio("", ('simple', 'none'))
+    st.sidebar.write(xlm_agg_strategy_info)
+    st.sidebar.write("")
+    st.sidebar.write("This English NER model is included just to show the zero-shot transfer learning capability of XLM-Roberta.")
+else:
+    aggregation = st.sidebar.radio("", ('first', 'simple', 'average', 'max', 'none'))
+    
+st.sidebar.write("Please refer 'https://huggingface.co/transformers/_modules/transformers/pipelines/token_classification.html' for entity grouping with aggregation_strategy parameter.")
+
+st.subheader("Select Text Input Method")
+input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text'))
+if input_method == 'Select from Examples':
+    selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
+    st.subheader("Text to Run")
+    input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
+elif input_method == "Write or Paste New Text":
+    st.subheader("Text to Run")
+    input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
+
+@st.cache(allow_output_mutation=True)
+def setModel(named_persons_only):
+    ner = roner.NER(named_persons_only=named_persons_only)
+    return ner
+
+@st.cache(allow_output_mutation=True)
+def get_html(html: str):
+    WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
+    html = html.replace("\n", " ")
+    return WRAPPER.format(html)
+        
+Run_Button = st.button("Run", key=None)
+if Run_Button == True:
+    
+    ner = setModel(named_persons_only = False)
+    output = ner(input_text)[0]
+
+    df = pd.DataFrame.from_dict(output)
+
+    st.subheader("Recognized Entities")
+    st.dataframe(df)
+
+    """
+    st.subheader("Spacy Style Display")
+    spacy_display = {}
+    spacy_display["ents"] = []
+    spacy_display["text"] = input_text
+    spacy_display["title"] = None
+
+    for entity in output:
+        if aggregation != "none":
+            spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity_group"]})
+        else:
+            spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity"]})
+    
+    entity_list = ["PER", "LOC", "ORG", "MISC"]
+    colors = {'PER': '#85DCDF', 'LOC': '#DF85DC', 'ORG': '#DCDF85', 'MISC': '#85ABDF',}
+    html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True, options={"ents": entity_list, "colors": colors})
+    style = "<style>mark.entity { display: inline-block }</style>"
+    st.write(f"{style}{get_html(html)}", unsafe_allow_html=True)
+    """

gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+torch
+transformers
+sentencepiece
+pandas
+spacy
+roner