Natural Language Processing in Google Cloud Flashcards

1
Q

What are key features on NLP API?

A
  • Entity extraction
  • Sentiment analysis
  • Entity sentiment analysis
  • Text classification
  • Syntax analysis
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is stemming?

A

Stemming is a process of converting a word to its root representations ex. playing -> play

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is normalization in NLP?

A

Normalization is a process of converting a phrase to its normal form ex. lol -> laugh out loud, wtf -> what the fuck. It is useful for social networks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Explain bag-of-words approach.

A

Bag-of-words represents a tecnique for converting text to numeric representation. It is similar to one-hot encoding but in this case each occurence of the word in the sentece is marked in vocabulary. You can track the occurence for each word like marking 2 for a dog or ignore number of occurence of the same word.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is word2vec?

A

word2vec reprents a family of model architectures and optimization that are used to learn word embeddings from a large dataset.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are 2 most common model architectures in word2vec?

A

CBOW (continous bag-of-words) - predicts center word by providing a surrounding context
Skip-gram - predicts surrounding context by providing a center word

For both architectures you first need to traing a neural network by creating training data.

CBOW
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is a Tensorflow Hub?

A

Tensorflow Hub is platform that contains pretrained models that you can use to fine-tune and deploy.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

How do you decide if pretrained embeddings model should be fine-tuned or not?

A

It depends on the amount of training data. You should not fine-tune the model if you don’t have too much data to avoid overfitting.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the difference between ANN (artificial neural network) and DNN (deep neural network)?

A

ANN has only one hidden layer.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly