Data Science

Curiosity, Data Science, and I, Nephi

Book of Mormon Central claims that the first sentence of the Book of Mormon attests to its ancient and authentic origin. Suppose you had an alternate hypothesis, would you be able to test it using data science?

Read

Fast N-gram Tool

We've built some fast rust-based n-gram research tools for the Mac OS, Linux, or Windows command line.

Read

DIY Mosiah Priority with BomDB

We recently created BomDB as a tool for Book of Mormon researchers. This post shows how to use it to replicate some of the analysis that led to the Mosiah Priority hypothesis. This is especially for you if you like to do-it-yourself for the sake of skeptical inquiry.

Read

Using TextGrams.jl

A rundown of the use of TextGrams.jl, a library used to score the relatedness of 2 or more books based on the similarity of their ngrams.

Read

Understanding ARPA and Language Models

I started off today thinking I’d be able to transform a previous n-gram library we wrote in the Julia programming language over to KenLM, a very fast Language Model generator. Instead, I ended up spending most of the day learning about language models and data formats. I thought I’d pass along some of this information and any insights I’ve had.

Read