Understanding Question Answering




  • For open-domain QA, the models are not restricted to a specific domain. The texts are retrieved from sources such as books, the internet, Wikipedia, tables, graphs, knowledge bases, etc. (View Highlight)
  • In closed-domain QA, the models are geared towards a specific domain, such as documents focused on the legal and healthcare sectors. (View Highlight)
  • Open-book QA is where the model has access to external sources of data to answer questions, including Wikipedia, internal/company documents, etc. It is similar to open-book exams, where students can access information in their books (View Highlight)
  • In closed-book QA, the model responds to questions without being explicitly given a context because it has learned some information encoded into its parameters during training. (View Highlight)
  • This model doesn’t extract answers from a context; it generates text directly to answer the question using language models such as GPT-3 and optionally takes a context. (View Highlight)
  • (View Highlight)
  • (View Highlight)
  • (View Highlight)
  • (View Highlight)
  • The reader model then takes in the most similar contexts and the question to provide a span selection of the answer. (View Highlight)
  • We use this system to answer more abstract questions that don’t require exact answers. The system returns answers that are more suggestions or opinions, not direct. (View Highlight)