Exploring Natural Language Processing in Ruby

Agenda

19:00 〜 19:30 Doors open

Grab a drink and catch up with your fellow Rubyists.

19:30 〜 20:00 Exploring Natural Language Processing in Ruby Kevin Dias

This presentation will cover 3 natural language processing gems I’ve released over the past year:
* Pragmatic Segmenter (a sentence boundary detection gem)
* Chat Correct (a gem for English teachers/students that provides error analysis when an incorrect sentence is diffed with a correct sentence)
* Word Count Analyzer (a gem that analyzes a string for potential “word count gray areas” which cause tools to report different word counts)

The talk will cover various aspects of building these gems including working from first principles, testing edge cases, and getting comfortable with regular expressions. I’ll also introduce a project that is currently in-progress - a new algorithm for parallel text alignment and some of the related challenges with building it.

Profile

I am an American living in Japan interested in the intersection of Natural Language Processing (NLP), web development, and the translation industry. I’m currently a developer at TM-Town, a new translation enablement platform that matches professional translators with clients based on the translator's prior work. Before TM-Town I built an online CAT (Computer-assisted translation) Tool called Transdraft which is aimed at making CAT software easy and accessible for freelance translators. I have also developed a wide range of other applications and sites including a language acquisition application, a language chat correction application, as well as an alumni networking application.

Github: https://github.com/diasks2
Twitter: https://twitter.com/diasks2

20:00 〜 22:00 Open Networking

Discuss the presentations or anything else Ruby related with the other attendees.

Warning about the Venue

• From 7pm, the front doors will no longer open automatically from the outside. Wait for someone to come out, and then you can go in.
• From 9pm, the front door will be locked, so please make sure you arrive before then.