ABOUT SEARCHING AND SEARCH PRACTICIES

On average, 20% of a knowledge worker’s day is spent looking for the information they need to get their work done. If you think about a typical work week, that means an entire day is dedicated to this task! To help our users find more time in their day, the Search, Learning, and Intelligence team set […]

Using Pandas to compute Mean Reciprical Rank using the MSMarco Dataset

Let’s explore this key bias in search systems towards the old algorithm and how to overcome it!

TLDR; When searching across most social networks, your direct contacts will be ranked higher than other users. Let’s take a look at the search of Linkedin and see if we can replicate something similar with Elasticsearch. Note, that this post only deals with autocomplete/search as you type suggestions and will not deep dive into the search results once a search has been sent, resulting in a search result page. Let’s look at Linkedin So let’s check out this search response.

We’ll be focusing on the algorithms or techniques that we used to convert the corpus into a full fledged autocomplete suggester.

This is the first post in a series describing the work that we did at OLX for improving the user search experience by enhancing the…

In this text I will explain what is spell correction in the area of search functionality, how it works in Google, Amazon and Pinterest and…

Search as a term is overloaded: it describes both the desire to find something and the process for doing so.

Automatic spelling correction, despite being worked on since the 70’s, remain hard to solve in the absence of significant user data.

TL;DR

TL;DR: Knowledge graphs are becoming increasingly popular in tech. We explore how they can be used in the retail industry to enrich data…

In English Language, people generally type the queries which are separated by space, but sometimes and somehow this space is found to be…

Conventional wisdom and textbooks say BK-trees are especially suited for spelling correction and fuzzy string search. But does this really…

Text Mining — Extracting Synonyms and Antonyms

An effective way of reducing the dimensionality of your data

Introduction

When is the right time to move to a machine learned search ranker from a simpler score-based one

How to learn similar terms in a given unsupervised corpus using Word2Vec

Most search boxes feature an autosuggestion or search query typeahead service to offer suggestions of the terms to search to the end users. If you don’t

Amazon.com: Click Models for Web Search (Synthesis Lectures on Information Concepts, Retrieval, and Services): 9781627056472: Aleksandr Chuklin, Ilya Markov, Maarten de Rijke: Books

Cambridge Core - Computing and Society - Interactions with Search Systems

Datafari open source enterprise search

A well-tuned search experience keeps your users and customers coming back. A poor experience can send them to the wrong pages, or worse, your competitors. Learn how you can analyze search interaction ...

People want to buy things that have many great reviews. But when sorting by average rating, the best results are buried by things that have one or two perfect reviews. You can solve this problem by ba...