Fast N-gram Tool
We've built some fast rust-based n-gram research tools for the Mac OS, Linux, or Windows command line.
ReadAll Posts tagged as "n-gram"
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.
ReadPresentation: The Late War & The Book of Mormon
Duane Johnson gave a presentation to the Salt Lake City PostMormon group summarizing some of the similarities between The Late War and the Book of Mormon, as well as further research made since the original work in 2014
ReadUnderstanding 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