How to build a search engine in 2 days
1 like187 views
This document provides instructions on how to build a basic search engine in two days. It discusses implementing semantic search capabilities to better understand user intent through techniques like handling synonyms, generalizations, concept matching and natural language queries. It also outlines the architecture required, including using Flask as a web framework, Spacy for query parsing, Gensim and Fasttext for word embeddings, and generating word clouds and results. Feedback from testing is suggested to improve reliability and user-friendliness.
![Master
WIT -> Wiskundige Ingenieurstechnieken
Master
1
Sem -> Semester
2
Crypto -> Cryptography
Readings
Pickpocketing
Mifare
[pdf]
+ NER](https://image.slidesharecdn.com/dsleuvenmeetup-feb20-180223160453/85/How-to-build-a-search-engine-in-2-days-32-320.jpg)
How to build a search engine in 2 days
- 1. HOW TO BUILD A SEARCH ENGINE (IN TWO DAYS)
- 5. I don’t have anything against the search idea, but it just doesn’t click for me at this point.
- 9. HOW TO BUILD A SEARCH ENGINE (IN TWO DAYS)
- 12. SEMANTIC SEARCH?
- 13. Semantic search seeks to improve search accuracy by understanding the searcher's intent and the contextual meaning of search terms
- 14. HANDLING - synonyms - generalizations - concept matching - natural language queries and questions
- 16. ILLNESS I’m sick = I’m ill = What is the policy for sickness?
- 17. PARKING Where can I park? = Where can I park my car? = I’m looking for a parking spot
- 18. HANDLING - synonyms - generalizations - concept matching - natural language queries and questions
- 19. PARKING Where can I park? = Where can I park my car? = I’m looking for a parking spot
- 21. PARKING Where can I park? = Where can I park my car? = I’m looking for a parking spot VB VB NN NN NN
- 22. ILLNESS I’m sick = I’m ill = What is the policy for sickness NN NN NN NN
- 23. HANDLING - synonyms - generalizations - concept matching - natural language queries and questions
- 29. FULL-TEXT?
- 32. Master WIT -> Wiskundige Ingenieurstechnieken Master 1 Sem -> Semester 2 Crypto -> Cryptography Readings Pickpocketing Mifare [pdf] + NER
- 34. MAKING IT FAST
- 42. Flask Web Framework Query Spacy Query Parsing Concepts Gensim & Fasttext Word Embedding Documents Word Clouds Results ARCHITECTURE
- 43. Feedback? Questions? Want to start a study group? :-) hello@willworkfor.coffee twitter.com/@lienmichiels medium.com/@Paliendroom