NLP Quiz

What is the process of splitting up text into smaller units called?

• Tokenization

• Encoding

• Vocab size

• Embeddings

Which level of tokenization involves breaking text into individual characters?

• Word

• Sentence

• Character

• Paragraph

What is the term used for representing words or phrases as numerical vectors?

• Tokenization

• Encoding

• Vocab size

• Embeddings

Which field of Natural Language Processing deals with generating text?

• Generative

• Classification

• Question answering

• Translation

What is the main drawback of RNN Encoder-Decoder models?

• Lack of attention

• Inability to handle long sequences

• Limited vocabulary size

• Slow training process

Why is subword tokenization used over character level and word level tokenization

(there are 2 correct answers)

• To prevent longer sequences of tokens to be generated

• To increase the parameter size of the model

• To allow the model to understand all possible text inputs

• To allow the model to train faster

What is attention in the context of Machine Learning

• A mechanism that allows the model to generate shorter output sequences

• A feature of the model that allows it to train faster

• The encoder of a model

• A mechanism that allows the model to focus on specific parts of the input

What is masking?

• To increase the dimensionality of the input data

• Hiding certain parts of the input sequence

• Hiding some of the model's parameters

• Hindering the model's ability to learn effectively

What are some examples of NLP tasks?

(There are multiple answers to this question)

• Sentiment Analysis

• Object Detection

• Summarization

• Translation

Why do we encode text data into numerical values?

• The model can't understand text data

• Because numbers are cool :)

• Improves readability of the model's outputs

• The numerical values contain semantic meaning of each token