Open-domain QA basics in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Open-domain Question Answering (QA)?

Open-domain QA is a system that answers questions on any topic using a large collection of documents or knowledge sources, without being limited to a specific subject area.

beginner

What are the two main steps in an Open-domain QA system?

1. Document Retrieval: Finding relevant documents or passages.<br>2. Answer Extraction: Selecting the exact answer from those documents.

beginner

Why is document retrieval important in Open-domain QA?

Because it narrows down the huge amount of information to a smaller set of relevant texts, making it easier and faster to find the correct answer.

intermediate

What is a common model type used for answer extraction in Open-domain QA?

Transformer-based models like BERT are commonly used because they understand context well and can find precise answers within text passages.

beginner

How does Open-domain QA differ from Closed-domain QA?

Open-domain QA can answer questions on any topic using large, general knowledge sources, while Closed-domain QA focuses on a specific area with limited data.

What is the first step in an Open-domain QA system?

A Document Retrieval

B Answer Extraction

C Training the model

D Data labeling

The system first finds relevant documents before extracting answers.

Which model type is often used for extracting answers in Open-domain QA?

A Transformer-based models

B Linear Regression

C K-means clustering

D Decision Trees

Transformer models like BERT understand context and extract answers well.

Open-domain QA systems can answer questions about:

A Only legal topics

B Any topic

C Only medical topics

D Only sports topics

Open-domain QA covers any topic using large knowledge sources.

Why is document retrieval necessary in Open-domain QA?

A To label data automatically

B To train the model faster

C To reduce the search space for answers

D To generate questions

Retrieval narrows down documents to find relevant information quickly.

Closed-domain QA differs from Open-domain QA because it:

A Answers questions on any topic

B Uses only images

C Does not use machine learning

D Focuses on a specific subject area

Closed-domain QA specializes in a limited topic or dataset.

Explain the two main steps of an Open-domain QA system and why each is important.

Think about how the system finds and then picks the answer.

Describe how Open-domain QA differs from Closed-domain QA in terms of scope and data.

Consider the range of questions each can answer.