This page contains the reliably extracted subset, not the complete original paper.
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 19 published solutions
Question 103 MCQ · 0.0 marks
General Note:
• If you find the given information is insufficient in any of the Numerical Answer Type (NAT)
questions, enter -1 as the answer.
• In all your calculations, take at least two digits. For example, if the intermediate result is
1.860875, then take it as 1.86 to the next step.
6406533822518.
Instructions has been mentioned above.
6406533822519.
This Instructions is just for a reference & not for an evaluation.
A published solution is not available for this question yet.
Consider following assertion and reason pair:
**Assertion**: A transformer model cannot be trained in autogregressive mode for machine
translation task.
**Reason**: Teacher forcing improves the convergence rate.
Choose the correct statements
6406533822524.
Assertion and Reason are both true and Reason is a correct explanation of
Assertion.
6406533822525.
Assertion and Reason are both true and Reason is not a correct explanation of
Assertion.
6406533822526.
Assertion is true but Reason is false.
6406533822527.
Assertion is false but Reason is true.
A published solution is not available for this question yet.
Suppose we use a pre-trained model for text generation with the given prompt “I am going to”.
Which of the following decoding strategies can be used such that the pre-trained model generates
different text completion each time it is executed
6406533822532.
Beam search with beam size 1
6406533822533.
Greedy approach
6406533822534.
Top-K with k = 2
6406533822535.
None of these
A published solution is not available for this question yet.
Which of the following decoding strategies is (are) appropriate for machine translation tasks?
Assume we have infinite compute and the values for k ≥ 3, p > 0.35 where required.
6406533822543.
Top-k sampling
6406533822544.
Beam search with the beam size K = 2
6406533822545.
Top-p sampling
6406533822546.
Exhaustive search
6406533822547.
None of these
A published solution is not available for this question yet.
Based on the above data, answer the given subquestions.
Suppose the number of learnable parameters in the source input-embedding layer is 3200, how
many parameters are there in the positional embedding layer of the source language?
A published solution is not available for this question yet.
Based on the above data, answer the given subquestions.
How many parameters are there in the multi-head attention layer of the encoder (exclude the
parameters in the WO matrix used for linear transformation and FFN layer)?
A published solution is not available for this question yet.
Once the model is sufficiently trained, which of the following tokens will have the highest
probability to be the next token, if the input is “Sachin has”:
6406533822558.
broken
6406533822559.
acted
6406533822560.
highest
6406533822561.
None of these
**i-NLP**
**Section Id :** 64065379955
**Section Number :** 8
**Section type :** Online
**Mandatory or Optional :** Mandatory
**Number of Questions :** 31
**Number of Questions to be attempted :** 31
**Section Marks :** 50
**Display Number Panel :** Yes
**Section Negative Marks :** 0
**Group All Questions :** No
**Enable Mark as Answered Mark for Review and**
No
**Clear Response :**
**Section Maximum Duration :** 0
**Section Minimum Duration :** 0
**Section Time In :** Minutes
**Maximum Instruction Time :** 0
A published solution is not available for this question yet.
