Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 17 published solutions
Question 157 MCQ · 2.0 marks
FastText differs from traditional word embedding models like Word2Vec because it can handle
out-of-vocabulary (OOV) words more effectively. Which of the following best explains how FastText
achieves this capability?
6406533484169.
FastText predicts context words using an entire sentence rather than just
nearby words.
6406533484170.
FastText generates embeddings by averaging multiple pre-trained word
vectors.
6406533484171.
FastText breaks words down into smaller subword units (character n-grams)
and creates embeddings based on these subwords, allowing it to estimate embeddings for
unseen words.
6406533484172.
FastText uses neural networks with an additional layer dedicated to identifying
unknown words.
A published solution is not available for this question yet.
Consider the following statements about statistical-based (SMT) and example-based (EBMT)
machine translation techniques. Select all statements that are correct:
6406533484190.
SMT uses probabilistic models to estimate the likelihood of translating one
phrase to another.
6406533484191.
EBMT relies on a database of example translations and reuses similar
examples to translate new sentences.
6406533484192.
SMT requires extensive linguistic rules and manually defined grammar to
create effective translations.
6406533484193.
When EBMT encounters an unseen sentence, it decomposes the sentence into
smaller segments and reuses similar examples from its database to generate translations.
A published solution is not available for this question yet.
Consider a scenario where you are fine-tuning a large language model using LoRA (Low-Rank
Adaptation) and QLoRA (Quantized LoRA) techniques. Each technique has specific ways of
reducing the model's memory and computational requirements. Select all statements that are
correct about LoRA ans QLoRa.
6406533484194.
LoRA achieves computational efficiency by performing inference with only a
subset of the model's original parameters, completely ignoring any layers that are not low-rank.
6406533484195.
QLoRA enables the model to dynamically switch between full and low-rank
matrices during inference, improving accuracy while saving memory.
6406533484196.
QLoRA applies quantization to the low-rank matrices introduced by LoRA,
combining memory efficiency through quantization with a reduced number of trainable
parameters from low-rank adaptation.
6406533484197.
LoRA reduces the number of parameters by introducing low-rank matrices to
approximate the weight updates, which minimizes the number of parameters that need to be
stored and trained.
A published solution is not available for this question yet.
You are analysing a collection of customer reviews using the Bag of Words (BoW) model. Here are
three sample reviews:
• Review 1: "This product is amazing, I absolutely love it!"
• Review 2: "The product is terrible, I hate it."
• Review 3: "Not the best, but it works okay."
Assume that each unique word from the vocabulary appears in at least one of the three reviews
and each unique word from reviews are added in the vocabulary. A word that appears in a review
contributes 1 non-zero entry to that review's BoW vector.
A published solution is not available for this question yet.
Based on the above data, answer the given subquestions.
At training time, consider a training sample, "this is good", where each word is a token. At the last
time step (while processing "good"), the word probabilities output by the RNN for these three
tokens are:
