Intro to NLP End Term: 22 December 2024 (September 2024 term)

Select all that apply.

1. A

   “sleep” in “sleeping”

2. B

   “un-” in “undo”

3. C

   “book” in “booked”

4. D

   “-s” in “books”

Select all that apply.

1. A

   Computing Shapley values requires evaluating an exponential number of feature coalitions.

2. B

   Shapley values assume independence between features, which may not hold in real-world data.

3. C

   Shapley values are computationally efficient for deep neural networks.

4. D

   Shapley values provide additive explanations, ensuring the contributions of all features sum up to the model's output.