import streamlit as st from st_pages import Page, show_pages st.set_page_config(page_title="Information Retrieval", page_icon="🏠") show_pages( [ Page("app.py", "Home", "🏠"), Page( "Information_Retrieval.py", "Information Retrieval", "📝" ), ] ) st.title("Project in Text Mining and Application - Information Retrieval") st.markdown( """ **Team members:** | Student ID | Full Name | Email | | ---------- | ------------------------ | ------------------------------ | | 1712603 | LĂȘ Quang Nam | 1712603@student.hcmus.edu.vn | | 19120582 | LĂȘ Nhá»±t Minh | 19120582@student.hcmus.edu.vn | | 19120600 | BĂči NguyĂȘn NghÄ©a | 19120600@student.hcmus.edu.vn | | 21120198 | Nguyễn Thị Lan Anh | 21120198@student.hcmus.edu.vn | """ ) st.header("The Need for Information Retrieval") st.markdown( """ The task of classifying whether a question and a context paragraph are related to each other is based on two main steps: word embedding and classifier. Both of these steps together constitute the process of analyzing and evaluating the relationship between the question and the context. """ ) st.header("Technology used") st.markdown( """ The ELECTRA model, specifically the "google/electra-small-discriminator" used here, is a deep learning model in the field of natural language processing (NLP) developed by Google. This model is an intelligent variation of the supervised learning model based on the Transformer architecture, designed to understand and process natural language efficiently. For this text classification task, we choose two related classes: ElectraTokenizer and FElectraForSequenceClassification to implement. """ )