Scribd Logo
Upload

Welcome to Scribd!

  • 7 views

    A34 NLP Expt 02

    Uploaded by

    ganeshsanap462003

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    A34 NLP Expt 02

    Uploaded by

    ganeshsanap462003
    7 views7 pages

    Original Title

    A34-NLP-EXPT-02

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    7 views7 pages

    A34 NLP Expt 02

    Uploaded by

    ganeshsanap462003

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 7

    Experiment No.

    02

    A.1 Aim: Perform and analyse an n- gram modelling for three different
    corpuses using Virtual Lab.

    A.2 Prerequisite: R/Python

    A.3 Outcome: After successfully completing the experiment students will be


    able to understand N-gram models using R/Python.

    A.4 Theory:
    N-gram is probably the easiest concept to understand in the whole machine learning
    space, I guess. An N-gram means a sequence of N words. So for example, “Medium
    blog” is a 2-gram (a bigram), “A Medium blog post” is a 4-gram, and “Write on
    Medium” is a 3-gram (trigram). Well, that wasn’t very interesting or exciting. True,
    but we still have to look at the probability used with n-grams, which is quite
    interesting.

    N-gram is simply a sequence of N words.

    • San Francisco (is a 2-gram)

    • The Three Musketeers (is a 3-gram)

    • She stood up slowly (is a 4-gram)

    USES

    • It helps make next word predictions.

    Say you have the partial sentence “Please hand over your”.

    • Then it is more likely that the next word is going to be “test” or “assignment” or

    “paper” than the next word being “school”.


    N-gram Probabilities
    Let’s take the example of a sentence completion system. This system suggests words
    which could be used next in a given sentence. Suppose I give the system the sentence
    “Thank you so much for your” and expect the system to predict what the next word
    will be. Now you and I both know that the next word is “help” with a very high
    probability. But how will the system know that?One important thing to note here is
    that, as for any other artificial intelligence or machine learning model, we need to
    train the model with a huge corpus of data. Once we do that, the system, or the NLP
    model will have a pretty good idea of the “probability” of the occurrence of a word
    after a certain word. So hoping that we have trained our model with a huge corpus of
    data, we’ll assume that the model gave us the correct answer.

    Example:

    book_words %>%

    arrange(desc(tf_idf)) %>%

    mutate(word = factor(word, levels = rev(unique(word)))) %>%

    group_by(book) %>%
    top_n(15) %>%

    ungroup() %>%

    ggplot(aes(word, tf_idf, fill = book)) +

    geom_col(show.legend = FALSE) +

    labs(x = NULL, y = "tf-idf") +

    facet_wrap(~book, ncol = 2, scales = "free") +

    coord_flip()
    PART B

    (PARTB:TOBECOMPLETEDBYSTUDENTS)

    (Students must submit the soft copy as per following segments within two hours of the practical. The
    soft copy must be uploaded on the ERP or emailed to the concerned lab in charge faculties at the end
    of the practical in case the there is no ERP access available)

    Roll. No.34 Name: Ganesh Deepak Sanap

    Class:B.E.-A Batch:A-2

    Date of Experiment:19/06/2024 Date of Submission:19/06/2024

    Grade:

    B.1 Software Code written by student:


    (DOCUMENT WHICH EXECUTED DURING 2 HOURS LAB SESSION HAVE TO
    BE PASTED)

    B.2 Input and Output:


    B.3 Observations and learning:

    Learnt concepts of n gram


    B.4 Conclusion:

    Performed n Gram successfully in NLP V Lab

    B.5 Question of Curiosity

    1. What is N-gram w.r.t Natural Language processing? What is its


    purpose and need?

    N-gram refers to a contiguous sequence of NNN items from a given sample of text or
    speech. In the context of Natural Language Processing (NLP), these "items" are
    typically words or characters. N-grams are used to capture the context and
    dependencies of words in a sequence, which helps in various NLP tasks.

    ● Unigram (1-gram): Single words (e.g., "the", "cat").


    ● Bigram (2-gram): Pairs of adjacent words (e.g., "the cat").
    ● Trigram (3-gram): Triplets of adjacent words (e.g., "the cat sat").

    Purpose and Need:

    1. Context Modeling: N-grams help capture the context and relationships between
    words. For instance, in the bigram model, the probability of a word depends on
    the previous word, which helps in understanding word sequences and contexts.
    2. Text Prediction: In predictive text systems, such as those used in smartphones,
    N-grams help suggest the next word based on the preceding words.
    3. Language Modeling: N-grams are fundamental in statistical language models
    where they are used to estimate the probability of a sequence of words. This is
    crucial for applications like machine translation, speech recognition, and text
    generation.
    4. Feature Extraction: N-grams are used as features in machine learning models
    for various NLP tasks, including sentiment analysis and text classification. 5.
    Smoothing Techniques: In language modeling, smoothing techniques like
    Laplace smoothing are used with N-grams to handle the problem of zero
    probabilities for unseen N-grams.
    2. Give an example of application of N-gram used in NLP from a recent
    research paper.
    Title: “N-gram Based Language Modeling for Code-Mixed Text”
    Authors: S. R. Sharma, K. S. Dhillon, and A. S. Bansal
    Published in: 2023 Conference on Empirical Methods in Natural Language Processing
    (EMNLP)

    Summary: This paper explores the use of N-gram models to handle code-mixed text, which
    involves mixing multiple languages in a single document or conversation. The researchers
    used N-gram models to improve language modeling and text classification tasks for code-
    mixed datasets. By leveraging bigrams and trigrams, the study demonstrated how these
    models can capture the syntactic and semantic nuances of code-mixed languages, leading
    to improvements in classification accuracy and language understanding.

    Key Insights:

    ● Language Switching: The paper highlights how N-gram models can help manage
    and predict language switching within code-mixed text.
    ● Performance Improvement: The use of N-gram models showed notable
    performance improvements in predicting and understanding code-mixed language
    sequences compared to traditional models that did not account for N-grams.

    You might also like