Scribd
Upload
18 views2 pages

Deep Learning NLP Question Bank

This document is a question bank for the Deep Learning (BCS714A) course, specifically focusing on interactive applications of deep learning in natural language processing (NLP). It includes various questions related to NLP concepts, techniques, and implementations, such as tokenization, word embeddings, sentiment classification, and recurrent neural networks. The questions are designed to assess understanding and application of deep learning principles in NLP, with each question linked to specific course outcomes.

Uploaded by

Mr. Study
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
18 views2 pages

Deep Learning NLP Question Bank

This document is a question bank for the Deep Learning (BCS714A) course, specifically focusing on interactive applications of deep learning in natural language processing (NLP). It includes various questions related to NLP concepts, techniques, and implementations, such as tokenization, word embeddings, sentiment classification, and recurrent neural networks. The questions are designed to assess understanding and application of deep learning principles in NLP, with each question linked to specific course outcomes.

Uploaded by

Mr. Study
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

DEEP LEARNING (BCS714A) Question Bank

MODULE-5
[Interactive Applications of Deep Learning]
Q.
Questions COs CL Marks
No.
1 Define Natural Language Processing (NLP) and explain any 4 applications in CO5 L2 10M
brief.

2 Explain how tokenization, lowercasing, stop word removal, and stemming CO5 L2 10M
contribute to preprocessing natural language data.

3 Describe the essential theory behind word2vec and how it creates word CO5 L2 10M
embeddings.

4 Explain how to run word2vec with an example. CO5 L2 10M

5 Demonstrate how to calculate the Area Under the ROC Curve (AUC) for a CO5 L2 10M
sentiment classification model.
Illustrate the role of the confusion matrix in evaluating natural language CO5 10M
6 classification models. L2

7 Describe the process of standardizing the length of reviews in the IMDB CO5 L2 10M
dataset for model input.

8 With code snippets, explain how to load and examine the IMDb film CO5 L2 10M
reviews.
Explain Dense sentiment classifier architecture to classify film reviews by
9 CO5 L2 10M
their sentiment.

10 Describe the process of standardizing the length of reviews in the IMDB CO5 L2 10M
dataset for model input using a c0onvolutional sentiment classifier.

11 Explain RNN with implementation using Keras. CO5 L2 10M

12 Explain LSTM with implementation using Keras. CO5 L2

13 Explain Bidirectional LSTM sentiment classifier architecture with code CO5 L2


snippet.

14 Explain stacked recurrent model architecture. CO5 L2

Department of CSE
DEEP LEARNING (BCS714A) Question Bank

15 Explain the effectiveness of seq2seq with attention for complex NLP tasks CO5 L2
like translation.

16 Explain transfer learning in NLP. CO5 L2

Course Faculty
[[Link] M V/[Link] G]

Department of CSE

You might also like