Code Monkey home page Code Monkey logo

words-as-classifiers's Introduction

Hi, I'm Bethany E. Toma!

Data Scientist at Theta Lake
M.Sc in Cognitive Systems from the University of Potsdam
BA in Linguistics & Chinese from The Ohio State University

Github: betoma    Facebook: /sparksbet    Twitter: @sparksbet    Instagram: bethanyetoma    Twitch: sparksbet    Steam: sparksbet    Goodreads: sparksbet    LinkedIn: Bethany Toma    Xing: BethanyElise_Toma   

Currently I work as a data scientist at Theta Lake, where I apply my knowledge of NLP in building and training our classifiers. I'm an experienced python programmer and have good literacy with most common packages and frameworks for NLP and machine learning (nltk, spacy, pytorch, scikit-learn, etc). I'm of the opinion that gathering and curating a good dataset is 90% of the work when it comes to machine learning, especially in NLP. It's not as glamorous as coming up with cool new architectures, but it's far more important in the grand scheme of things.

I wrote my master's thesis on an approach to interpreting references to objects in pictures using a vocabulary of image region classifiers and rational speech act theory. While I enjoy the technical side of things in NLP, my true passion is for theoretical linguistics, particularly semantics and pragmatics. One of the best parts of my master's thesis was that it gave me the opportunity to approach the problem from such a perspective and in the process become more familiar with rational speech act theory, a super interesting formal approach to pragmatics that has intrigued me since undergrad. Feel free to ask me about it!

I also love talking about interesting little phrases and ways of speaking in languages throughout the world. For instance, my bachelor's thesis was inspired by friends from the UK who often ended their sentences with "that." It's the little details like that which end up having surprising linguistic depth, and that's exactly the sort of thing that fascinates me.

I'm also hugely into conlanging -- the art of inventing new languages. Different people who make conlangs (short for "constructed languages") do it for different reasons. For me personally, it's solely for fun. No one has to use or even care about the languages I create for me to derive enjoyment from the act of putting together little intricate linguistic systems. That said, if you do care about the languages I create, please ask! I could go on about conlanging for hours, and many of my closest friends (including my spouse) are people I met through the conlanging community.

😄 Pronouns: they/them
💬 Ask me about formal semantics, right dislocation, rational speech act theory, or constructed languages
🖼 Avatar commissioned from Plague Birb (@BirbPlague on Twitter)

Languages & Frameworks:

python   jupyter   numpy   pandas   scikit-learn   spacy   r   latex  

words-as-classifiers's People

Contributors

betoma avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.