MS-DS Master of Data science Natural Language Processing 5

Question 1

In coreference resolution, what does it mean for two mentions to be 'coreferent'?

Accepted Answer

They refer to the same entity or event in the world

Answer

Coreference resolution links noun phrases (e.g., 'Barack Obama' and 'he') that refer to the same real-world entity, forming coreference chains across a document.

Question 2

What distinguishes nucleus sampling (top-p sampling) from top-k sampling in text generation?

Accepted Answer

Nucleus sampling dynamically selects the smallest set of tokens whose cumulative probability exceeds threshold p, adapting to the distribution shape

Answer

Unlike top-k which fixes the number of candidates, top-p sampling includes tokens until their cumulative probability reaches p, allowing a larger or smaller candidate set depending on distribution sharpness.

Question 3

In multi-task learning for NLP, what is the key assumption that justifies sharing parameters across tasks?

Accepted Answer

Tasks share useful linguistic features in their input representations, enabling positive transfer

Answer

Multi-task learning assumes that related NLP tasks (e.g., POS tagging and NER) rely on overlapping syntactic or semantic features, so shared lower layers transfer knowledge beneficially.

Question 4

Which of the following is a key limitation of the BLEU metric when evaluating natural language generation quality?

Accepted Answer

BLEU ignores recall and does not correlate well with human judgments for fluency or meaning preservation

Answer

BLEU is a precision-focused n-gram overlap metric that ignores synonymy, paraphrase, and sentence-level meaning, resulting in poor correlation with human quality judgments on many generation tasks.

Question 5

What is 'catastrophic forgetting' in the context of sequential fine-tuning of pre-trained language models?

Accepted Answer

The model's performance on previously learned tasks degrades significantly when fine-tuned on a new task

Answer

When a neural network is fine-tuned on a new task, the parameter updates can overwrite knowledge from prior tasks, a phenomenon called catastrophic forgetting or catastrophic interference.

MS-DS Master of Data science Practice Test

MS-DS Master of Data science Practice Test

MS-DS Master of Data science Natural Language Processing 5