Generating Memorable Mnemonic Encodings of Numbers

TL;DR

This paper introduces a method to automatically generate memorable mnemonic sentences for numbers, combining language models and sentence templates, to improve password memorability.

Contribution

It presents novel encoding models for number-to-sentence conversion and evaluates their effectiveness in enhancing password memorability.

Findings

The combined model yields the most memorable passwords.

Language models improve mnemonic sentence quality.

Part-of-speech templates enhance memorability.

Abstract

The major system is a mnemonic system that can be used to memorize sequences of numbers. In this work, we present a method to automatically generate sentences that encode a given number. We propose several encoding models and compare the most promising ones in a password memorability study. The results of the study show that a model combining part-of-speech sentence templates with an $n$-gram language model produces the most memorable password representations.