It is estimated that more than half of the world’s population is multilingual; therefore, it is not surprising that many texts and conversations incorporate multiple languages, resulting in a linguistic phenomenon called code-switching. This workshop covers how linguists gather, process and analyze code-switched data. We will explore the NPL pipeline for processing multilingual texts and discuss various approaches to language identification.


Jacqueline Serigos is an Assistant Professor of Spanish Linguistics in the Department of Modern and Classical Languages at George Mason University. Her research explores various forms of language contact, such as lexical borrowings, code-switching, and calques. She employs approaches from multiple linguistic subfields, including corpus linguistics, computational linguistics, sociolinguistics, and semantics, as well as the discipline of statistics. She received her BA in Anthropology and Latin American Studies from Emory University and a PhD in Hispanic Linguistics from the University of Texas at Austin.

  • Linguistic Diversity Around The World
    One Text / Two Languages

    This workshop covered how linguists gather, process and analyze code-switched data, exploring the NPL pipeline for processing multilingual texts and discussing various approaches to language identification.

  • Analytics student Ratnadeep Mitra stands in front of his poster next to program director Dr. Ami Gates.
    Analytics Student Showcase

    MS Analytics students showcased what they learned this semester by applying contemporary deep learning techniques to a variety of exciting topics and problems.

  • Neural attention model
    Commonsense Reasoning without Commonsense Knowledge

    Reading comprehension tasks measure the ability to answer questions that require inference from a free text story. This talk explores two machine learning approaches.

  • MS Analytics Students Selected as Finalists in Adobe Analytics Challenge
    MS Analytics Students Win Third Place in Adobe Analytics Challenge

    Shengye Hang, Ju Huang, and Tianyi Yang represented Georgetown as Team "Don't Stop Bayesian" at the 2018 Adobe Analytics Challenge.