pages/Basic_Terminologies.py

import streamlit as st 

st.markdown(
    """
    <style>
    /* App Background */
    .stApp {
        background: linear-gradient(to right , 	#EE82EE, #FFA500 ,#87CEEB); /* Gradient dark professional background */
        color: #00FFFF;
        padding: 20px;
    }
    /* Align content to the left */
    .block-container {
        text-align: left; /* Left align for content */
        padding: 2rem; /* Padding for aesthetics */
    }
    
    /* Header and Subheader Text */
    h1 {
        color: #800080 !important; /* Custom styling for the main header */
        font-family: 'Arial', sans-serif !important;
        font-weight: bold !important;
        text-align: center;
    }
    h2, h3, h4 {
        color: 	#FFFF00 !important; /* Custom styling for subheaders */
        font-family: 'Arial', sans-serif !important;
        font-weight: bold !important;
    }
    /* Paragraph Text */
    p {
        color: #0000FF !important; /* Custom styling for paragraphs */
        font-family: 'Arial', sans-serif !important;
        line-height: 1.6;
    }
    </style>
    """,
    unsafe_allow_html=True
)
st.markdown(
    """
    <h1 style="text-align: center;">Basic Terminology in NLP</h1>
    """,
    unsafe_allow_html=True
)

st.markdown(
    """
    <h5>Before diving deep into the concepts of NLP we must know about the frequently used terminologies in NLP</h5>
    <h5 style="color: ##00FF00;">1.Key Terminologies in NLP</h5>
    <ul style="color: #008000; line-height: 1.8;">
        <li><b>Corpus:</b> A collection of text documents. Example: {d1, d2, d3, ...}</li>
        <li><b>Document:</b> A single unit of text (e.g., a sentence, paragraph, or article).</li>
        <li><b>Paragraph:</b> A collection of sentences.</li>
        <li><b>Sentence:</b> A collection of words forming a meaningful expression.</li>
        <li><b>Word:</b> A collection of characters.</li>
        <li><b>Character:</b> A basic unit like an alphabet, number, or special symbol.</li>
    </ul>
    """,
    unsafe_allow_html=True
)
st.markdown(
    """
    <h5 style="color: #00FFFF;">2.Tokenization</h5>
    <p style="color: #FFA500;">Tokenization is the process of breaking down a large piece of text into smaller units called tokens. These tokens can be words, sentences, or subwords, depending on the granularity required for the task.</p>
    <h6>Types of Tokenization:</h6>
    <ul style="color: #d4e6f1; line-height: 1.8;">
        <li><b>Sentence Tokenization:</b> Splitting text into sentences. <br> Example: "I love ice-cream. I love chocolate." → ["I love  ice-cream", "I love chocolate"]</li>
        <li><b>Word Tokenization:</b> Splitting sentences into words. <br> Example: "I love biryani" → ["I", "love", "biryani"]</li>
        <li><b>Character Tokenization:</b> Splitting words into characters. <br> Example: "Love" → ["L", "o", "v","e"]</li>
    </ul>
    """,
    unsafe_allow_html=True
)
st.markdown(
    """
    <h5 style="color: #008080;">3.Stop Words</h5>
    <p style="color: #000080;">Stop words are commonly used words in a language that carry little or no meaningful information for text analysis. </p>
    <h6>Example:</h6>
    <p style="color: #d4e6f1;">"In Hyderabad, we can eat famous biryani." <br> Stop words: ["in", "we", "can"]</p>
    """,
    unsafe_allow_html=True
)
st.markdown(
    """
    <h5 style="color: #20B2AA;">4.Vectorization</h5>
    <p style="color: #d4e6f1;">Vectorization is the process of converting text data into numerical representations so that machine learning models can process and analyze it.</p>
    <h6>Types of Vectorization:</h6>
    <ul style="color: #d4e6f1; line-height: 1.8;">
        <li><b>One-Hot Encoding:</b> Represents each word as a binary vector.</li>
        <li><b>Bag of Words (BoW):</b> Represents text based on word frequencies.</li>
        <li><b>TF-IDF:</b> Adjusts word frequency by importance.</li>
        <li><b>Word2Vec:</b> Embeds words in a vector space using deep learning.</li>
        <li><b>GloVe:</b> Uses global co-occurrence statistics for embedding.</li>
        <li><b>FastText:</b> Similar to Word2Vec but includes subword information.</li>
    </ul>
    """,
    unsafe_allow_html=True
)
st.markdown(
    """
    <h5 style="color: #20B2AA;">5. Stemming</h5>
    <p style="color: #d4e6f1;">Stemming is the process of reducing words to their base or root form, often by removing prefixes or suffixes. It is a rule-based, heuristic approach to standardize words by removing derivational affixes.</p>
    <h6>Example:</h6>
    <ul style="color: #d4e6f1; line-height: 1.8;">
        <li><b>Original Words:</b> "running", "runner", "runs"</li>
        <li><b>Stemmed Form:</b> "run"</li>
    </ul>
    """,
    unsafe_allow_html=True
)
st.markdown(
    """
    <h5 style="color: #20B2AA;">6. Lemmatization</h5>
    <p style="color: #d4e6f1;">Lemmatization is the process of reducing a word to its base or root form (called a lemma) using linguistic rules and a vocabulary (dictionary). Unlike stemming, lemmatization ensures that the resulting word is a valid word in the language.</p>
    <h6>Example:</h6>
    <ul style="color: #d4e6f1; line-height: 1.8;">
        <li><b>Original Words:</b> "studying", "better", "carrying"</li>
        <li><b>Lemmatized Form:</b> "study", "good", "carry"</li>
    </ul>
    <p style="color: #d4e6f1;">Lemmatization is more accurate than stemming but computationally more intensive as it requires a language dictionary.</p>
    """,
    unsafe_allow_html=True
)