Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 18 published solutions
Question 2 SHORT_TEXT · 2.0 marks
Answer the subquestions for the given transformer architecture for one (N = 1) **Encoder Decoder**
**Block**
In the given Transformer architecture for one Encoder Decoder block, identify every **Add & Norm**
layer. Submit the corresponding component alphabets in **alphabetical (ascending) order** as a
single uppercase string without spaces, commas, or quotation marks.
Example: If the correct components are Q, G, and S, your answer should be GQS
A published solution is not available for this question yet.
Answer the subquestions for the given transformer architecture for one (N = 1) **Encoder Decoder**
**Block**
Based on the architecture shown in the given image, identify all components that appear more
than once. Assume the architecture contains exactly one Encoder block and one Decoder block.
6406537135080.
Positional Encoding
6406537135081.
Feed-Forward Network
6406537135082.
Masked Multi-Head Self-Attention
6406537135083.
Multi-Head Cross-Attention
6406537135084.
tokenizer
6406537135085.
Add & Norm
A published solution is not available for this question yet.
A baseline T5 model with denoising objective on a span of corrupted tokens is used for
unsupervised pre-training. Consider the phrase **"life is like a box of chocolates"**. If the word "life"
and the span "box of chocolates" are selected for corruption, which of the following statements
correctly describe the training process?
6406537135123.
The input sequence replaces the corrupted spans with unique sentinal tokens
as: "<X> is like a <Y>".
6406537135124.
The output sequence generated takes the form "<X> life <Y> box of chocolates
<Z>", with the final sentinal token to indicate sequence completion.
6406537135125.
The loss is calculated exclusively over the generated sentinal tokens and the
missing text.
6406537135126.
The decoder reconstructs the entire original sequence autoregressively to
compute the total loss over all positions.
A published solution is not available for this question yet.
During the fine-tuning of a decoder-only Transformer for sequence classification, why is the
hidden representation of the final input token used as the input to the classification layer?
6406537135094.
The first token's representation relies exclusively on absolute positional
encodings and lacks semantic context for classification.
6406537135095.
The final token's representation is computed independently of self-attention,
making its gradients more stable during the fine-tuning process.
6406537135096.
Selecting the final token aligns with the autoregressive objective, eliminating
the need for teacher forcing during the classification forward pass.
6406537135097.
Causal self-attention ensures that only the final token's representation
aggregates information from all preceding tokens in the sequence.
A published solution is not available for this question yet.
Consider the T5 "text-to-text" paradigm. How does the model process fundamentally different
tasks such as Semantic Similarity (continuous regression) and Sentiment Analysis (discrete
classification) during the fine-tuning phase?
6406537135119.
The model uses the encoder to output the regression score and decoder for
the classification tokens switching based on the input prompt.
6406537135120.
The decoder part of the model is appended with separate prediction heads for
regression and classification which are updated based on Mean Squared Error and Cross-Entropy
respectively.
6406537135121.
The model treats both tasks as sequence generation objectives with task-
specific prefix added in the input and all output is generated as strings.
6406537135122.
None of these.
A published solution is not available for this question yet.
In the context of the BART (Bidirectional AutoRegressive Transformer) architecture, how does the
model handle corrupted input sequences compared to its output?
6406537135127.
The decoder ignores the encoder output and performs standard causal
language modeling.
6406537135128.
The encoder processes the original sequence and the decoder predicts the
corrupted tokens.
6406537135129.
The encoder processes the corrupted sequence and the decoder predicts the
entire original sequence.
6406537135130.
Both the encoder and decoder process the corrupted sequence to calculate
masked loss.
A published solution is not available for this question yet.
Consider the following corpus consisting of 4 words (ignore spaces and punctuation).
**there is no spoon**
The vocabulary is constructed using the whole words in this corpus and the individual characters
in this corpus. The vocabulary should now have 13 tokens. Use this vocabulary for the given
subquestions.
Using the vocabulary constructed, two new continuous strings: "prison" and "rhino" are to be
segmented. Which of the following proposed segmentations are valid?
6406537135110.
prison
6406537135111.
p, r, is, o, n
6406537135112.
p, r, is, on
6406537135113.
r, h, i, n, o
6406537135114.
r, h, i, no
A published solution is not available for this question yet.
Consider the following corpus consisting of 4 words (ignore spaces and punctuation).
**there is no spoon**
The vocabulary is constructed using the whole words in this corpus and the individual characters
in this corpus. The vocabulary should now have 13 tokens. Use this vocabulary for the given
subquestions.
Using a unigram language model, identify the segment with the highest probability from the
given
6406537135115.
n, o, i, s, e, s
6406537135116.
no, is, e, s
6406537135117.
nois, e, s
6406537135118.
no, i, s, e, s
A published solution is not available for this question yet.
