Skip to content

kingafy/Books

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Books

Interview questions https://www.analyticsvidhya.com/blog/2017/01/must-know-questions-deep-learning/

Pyspark ml support :-- http://spark.apache.org/docs/latest/api/python/pyspark.ml.html

Bio tagging applicable for NER

Knowledge bases L--wordnet,conceptual,wikitext

Which of the following statement is the best description of early stopping? = Simulate the network on a test dataset after every epoch of training. Stop training when the generalization error starts to increase

Vocabulary size of above corpus :--15

Identify the following activation function : φ(V) = Z + (1/ 1 + exp (– x * V + Y) ), Z, X, Y are parameters 

Sigmoid

which of the following is not a step for word normalization ==run sentences

Sequence of tasks in perceptron--> 1432

How many times I will appear with love in cooccurence matrix :--2

which of these are built in models/functions in Gensim==all options

Spell correction assumption :--false

While creating a machine learning model on text data, you created a document term matrix of the input data of 100K documents. Which of the following remedies can be used to reduce the dimensions of data – 1. Latent Dirichlet Allocation 2. Latent Semantic Indexing 3. Keyword Normalization

Ans --1,2,3

Social Media platforms are the most intuitive form of text data. You are given a corpus of complete social media data of tweets. How can you create a model that suggests the hashtags?

From https://www.analyticsvidhya.com/blog/2017/07/30-questions-test-data-scientist-natural-language-processing-solution-skilltest-nlp/

A) Perform Topic Models to obtain most significant words of the corpus B) Train a Bag of Ngrams model to capture top n-grams – words and their combinations C) Train a word2vector model to learn repeating contexts in the sentences D) All of these Solution: (D)

While working with context extraction from a text data, you encountered two different sentences: The tank is full of soldiers. The tank is full of nitrogen. Which of the following measures can be used to remove the problem of word sense disambiguation in the sentences? A) Compare the dictionary definition of an ambiguous word with the terms contained in its neighborhood B) Co-reference resolution in which one resolute the meaning of ambiguous word with the proper noun present in the previous sentence C) Use dependency parsing of sentence to understand the meanings (A) From https://www.analyticsvidhya.com/blog/2017/07/30-questions-test-data-scientist-natural-language-processing-solution-skilltest-nlp/

While working with text data obtained from news sentences, which are structured in nature, which of the grammar-based text parsing techniques can be used for noun phrase detection, verb phrase detection, subject detection and object detection. A) Part of speech tagging B) Dependency Parsing and Constituency Parsing C) Skip Gram and N-Gram extraction D) Continuous Bag of Words Solution: (B) Dependency and constituent parsing extract these relations from the text

Types of parsing:--Deep parsing andShallow parsing  A ReLU unit in neural network never gets saturated--True

when does a neural network become a deep learning model-- add more hidden layers and increase depth of neural network For k fold cross validation , smaller k value implies less variance:--true One fast growing language for building semantic web applications is RSS.

CRF is discrimative and HMM is generative

Hyperparams in neural network--learning rate, batch size and number of epochs

In Gradient Descent or Batch Gradient Descent, we use the whole training data per epoch whereas, in Stochastic Gradient Descent, we use only single training example per epoch and Mini-batch Gradient Descent lies in between of these two extremes, in which we can use a mini-batch(small portion) of training data per epoch, thumb rule for selecting the size of mini-batch is in power of 2 like 32, 64, 128 etc.

From https://datascience.stackexchange.com/questions/36450/what-is-the-difference-between-gradient-descent-and-stochastic-gradient-descent

Can be computationally efficient Can be used to improve convergence

https://www.kdnuggets.com/2020/01/intro-guide-nlp-data-scientists.html

https://www.analyticsvidhya.com/blog/2017/01/must-know-questions-deep-learning/ https://www.analyticsvidhya.com/blog/2017/07/30-questions-test-data-scientist-natural-language-processing-solution-skilltest-nlp/

https://www.mygreatlearning.com/blog/nlp-interview-questions/

https://compsciedu.com/Neural-Networks/UGC-NET-computer-science-question-paper/discussion/7522 https://www.analyticsvidhya.com/blog/2017/07/30-questions-test-data-scientist-natural-language-processing-solution-skilltest-nlp/

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published