learn.ifs.name

Information Retrieval and Retrieval-Augmented Generation

Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 11

5 cards in “Historical notes” · whole deck

Historical notes

  1. How did the 1961 BASEBALL system answer questions?
    It parsed the question (with a cascade of finite-state transducers), mapped words to meaning fragments (“Where” → Place = ?), and matched the resulting attribute-value query against a structured database of games.
  2. How did Protosynthex (1964) choose answer sentences?
    It retrieved candidate sentences by frequency-weighted term overlap with the question, then dependency-parsed them and picked the one whose structure best matched the question (“What do worms eat?” matches “worms eat grass”, not “birds eat worms”).
  3. What meaning representation did 1970s QA systems like LUNAR use?
    Predicate calculus / logical forms, as natural language interfaces to databases (LUNAR: lunar geology samples).
  4. What role did TREC play in QA history?
    The US Text REtrieval Conference evaluations (since 1992) provided testbeds for IR; its QA track (1999) drove many factoid and non-factoid QA systems.
  5. Where did RAG first come from?
    Retrieval augmentation was first introduced to improve language-model word prediction (Khandelwal et al., 2019), then quickly applied to question answering.

Source