How Does Search Find an Answer So Quickly?
In short: From medieval indexes and the Library of Congress card drawers to word weighting, link-based ranking and learned retrieval, a short history of how answers are found and ordered, and of the trade-offs and questions still open.
A 1:37 short film in the series “From Fingers to Qubits”, narrated by intellect_voice_01.
Sources used in this film: Library of Congress (Research Guides), “Research Guides: The Library of Congress Card Catalog: Origins and Development of the Card Catalog”; National Institute of Standards and Technology (NIST), “Text REtrieval Conference (TREC)”; arXiv (Cornell University), preprint of a paper presented at EMNLP 2020, “Dense Passage Retrieval for Open-Domain Question Answering”; Academia.edu (hosting Larry Page, 'The PageRank Citation Ranking: Bringing Order to the Web', ilpubs.stanford.edu, 1999), “The PageRank Citation Ranking: Bringing Order to the Web”; Academia.edu (hosted copy of the survey 'The Probabilistic Relevance Framework: BM25 and Beyond'), “The Probabilistic Relevance Framework: BM25 and Beyond”; now Publishers (Foundations and Trends series), hosted on IEEE Xplore, “The Probabilistic Relevance Framework | now eBooks | IEEE Xplore”; arXiv (Cornell University); survey by Jimmy Lin et al., published as a volume in Morgan & Claypool's Synthesis Lectures on Human Language Technologies, “Pretrained Transformers for Text Ranking: BERT and Beyond”; Springer Nature (Springer Cham), book overview page for Lin, Nogueira & Yates, 'Pretrained Transformers for Text Ranking: BERT and Beyond' (Synthesis Lectures on Human Language Technologies), “Pretrained Transformers for Text Ranking”; Washington Independent Review of Books (review by Peggy Kurkowski of Dennis Duncan's 'Index, A History of the'), “Index, A History of the: A Bookish Adventure from Medieval Manuscripts to the Digital Age | Washington Independent Review of Books”.
Sources used in this film
- Library of Congress (Research Guides) — Research Guides: The Library of Congress Card Catalog: Origins and Development of the Card Catalog · View →
- National Institute of Standards and Technology (NIST) — Text REtrieval Conference (TREC) · View →
- arXiv (Cornell University), preprint of a paper presented at EMNLP 2020 — Dense Passage Retrieval for Open-Domain Question Answering · View →
- Academia.edu (hosting Larry Page, 'The PageRank Citation Ranking: Bringing Order to the Web', ilpubs.stanford.edu, 1999) — The PageRank Citation Ranking: Bringing Order to the Web · View →
- Academia.edu (hosted copy of the survey 'The Probabilistic Relevance Framework: BM25 and Beyond') — The Probabilistic Relevance Framework: BM25 and Beyond · View →
- now Publishers (Foundations and Trends series), hosted on IEEE Xplore — The Probabilistic Relevance Framework | now eBooks | IEEE Xplore · View →
- arXiv (Cornell University); survey by Jimmy Lin et al., published as a volume in Morgan & Claypool's Synthesis Lectures on Human Language Technologies — Pretrained Transformers for Text Ranking: BERT and Beyond · View →
- Springer Nature (Springer Cham), book overview page for Lin, Nogueira & Yates, 'Pretrained Transformers for Text Ranking: BERT and Beyond' (Synthesis Lectures on Human Language Technologies) — Pretrained Transformers for Text Ranking · View →
- Washington Independent Review of Books (review by Peggy Kurkowski of Dennis Duncan's 'Index, A History of the') — Index, A History of the: A Bookish Adventure from Medieval Manuscripts to the Digital Age | Washington Independent Review of Books · View →
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: Library of Congress (Research Guides): Research Guides: The Library of Congress Card Catalog: Origins and Development of the Card Catalog
- Also: National Institute of Standards and Technology (NIST): Text REtrieval Conference (TREC)
- Also: arXiv (Cornell University), preprint of a paper presented at EMNLP 2020: Dense Passage Retrieval for Open-Domain Question Answering
- Also: Academia.edu (hosting Larry Page, 'The PageRank Citation Ranking: Bringing Order to the Web', ilpubs.stanford.edu, 1999): The PageRank Citation Ranking: Bringing Order to the Web
- Also: Academia.edu (hosted copy of the survey 'The Probabilistic Relevance Framework: BM25 and Beyond'): The Probabilistic Relevance Framework: BM25 and Beyond
- Also: now Publishers (Foundations and Trends series), hosted on IEEE Xplore: The Probabilistic Relevance Framework | now eBooks | IEEE Xplore
- Also: arXiv (Cornell University); survey by Jimmy Lin et al., published as a volume in Morgan & Claypool's Synthesis Lectures : Pretrained Transformers for Text Ranking: BERT and Beyond
- Also: Springer Nature (Springer Cham), book overview page for Lin, Nogueira & Yates, 'Pretrained Transformers for Text Ranking: Pretrained Transformers for Text Ranking
- Also: Washington Independent Review of Books (review by Peggy Kurkowski of Dennis Duncan's 'Index, A History of the'): Index, A History of the: A Bookish Adventure from Medieval Manuscripts to the Digital Age | Washington Independent Review of Books
To cite this card, link to https://intellectplus.co.uk/app/how-does-search-find-an-answer-so-quickly.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics
