build version:1.8

NLP_History_and_Facts.txt

@@ -22,7 +22,7 @@ Natural Language Processing (NLP) has its roots in the early days of computing a
 
 5. **2000s - The Neural Era**:
    - The introduction of neural networks revolutionized NLP tasks.
-   - Word embeddings, such as Word2Vec (2013) and GloVe, created dense, continuous vector representations of words, capturing semantic relationships.
+   - Word embeddings, such as Word2Vec and GloVe, created dense, continuous vector representations of words, capturing semantic relationships.
 
 6. **2010s - The Transformer Revolution**:
    - The paper "Attention Is All You Need" (2017) introduced the Transformer architecture, which addressed the limitations of recurrent neural networks (RNNs).

app.py

@@ -5,9 +5,11 @@ from transformers import AutoModelForSeq2SeqLM , AutoTokenizer, TranslationPipel
 
 
 
-st.title('NLP Question Answering 🕵️‍♂️')
+st.title('Question Answering 🕵️‍♂️')
 st.write('Ask a question about NLP, and I will answer based on the provided context! 🔄')
-user_input = st.text_area("enter question about NLP", "What is tokenizer?")
+context_input = st.text_area("please provice some context", "Many NLP tasks are now benchmarked using datasets like GLUE and SuperGLUE.  Multilingual NLP models like mBERT support multiple languages in a single framework.")
+
+# question_input = st.text_area("enter question about NLP", "what model support multilingual nlp?")
 @st.cache_resource
 def load_model():
     print("Loading model...")
@@ -15,21 +17,24 @@ def load_model():
 
 
 dunno_answerer  = load_model()
-with open('NLP_History_and_Facts.txt', 'r') as file:
-    context = file.read()
-
-if st.button("Answer!"):
-    if user_input.strip():
-        # Generate an answer using the model
-        result = dunno_answerer(question=user_input, context=context)
-
-        # Display the answer and additional information
-        st.write(f"**Answer:** {result['answer']}")
-        st.write(f"**Confidence Score:** {round(result['score'], 4)}")
-        st.write(f"**Answer Start Position:** {result['start']}")
-        st.write(f"**Answer End Position:** {result['end']}")
-    else:
-        st.write("Please enter a valid question!")
+# with open('NLP_History_and_Facts.txt', 'r') as file:
+#     context = file.read()
+
+
+if context_input.strip():
+    question_input = st.text_area("enter question about NLP", "what model support multilingual nlp?")
+    if st.button("Answer!"):
+        if question_input.strip():
+            # Generate an answer using the model
+            result = dunno_answerer(question=question_input, context=context_input)
+
+            # Display the answer and additional information
+            st.write(f"**Answer:** {result['answer']}")
+            st.write(f"**Confidence Score:** {round(result['score'], 4)}")
+            st.write(f"**Answer Start Position:** {result['start']}")
+            st.write(f"**Answer End Position:** {result['end']}")
+        else:
+            st.write("Please enter a valid question!")
 
 # x = st.slider('Select a value')
 # st.write(x, 'squared is', x * x)