IITP-03 Quiz 3

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

IITP-03 Quiz 3

Your response will be recorded and sent to your email. Only your first submission will be accepted. Please make sure your email address is entered correctly!

Email *

Select the statement that is NOT a possible problem of using discrete word representations *

1 point

Too coarse

Data sparsity

It is hard to compute word relationships from the representation

Using float type in the representation

Select two statements/quotes that are most directly related to distributional hypothesis *

1 point

If A and B have almost identical environments we say that they are synonyms.

A sense is the meaning component of a word

You shall know a word by the company it keeps

We can represent the meaning of words with their lemmas, senses, and definitions

Required

Which of the following embeddings does 'word2vec' belong to?

1 point

Count-based

Class-based

Distributed prediction-based embedding

Distributed contextual embeddings from language models

Clear selection

Which of the following statements is FALSE? *

1 point

SVD is one way to do dimensionality reduction

SVD is simple and computationally efficient

The intuition of Brown clustering is that similar words have similar distribution of words to their immediate left and right

In Brown clusters, representation is created through hierarchical clustering

If we know the vector representation of word "happy" is [0,2,0,0], the vector representation of word "joy" is [1,1,1,1]. What is the cosine similarity between word "happy" and "joy"? *

1 point

A copy of your responses will be emailed to the address you provided.

Submit

Clear form

Never submit passwords through Google Forms.

reCAPTCHA

Privacy Terms

This form was created inside of Carnegie Mellon University. Report Abuse

Forms