Top of page
Skip to main content
Main content

Jinho ChoiAssistant Professor | QTM & Computer scienceAssistant Professor | Program in Linguistics

Biography

Jinho Choi is an assistant professor in the Department of Computer Science, the Department of Quantitative Theory and Methods, and the Program in Linguistics at Emory University. He conducted his postdoctoral research at the University of Massachusetts Amherst in 2014 with Andrew McCallum. He was a full-time lecturer in the Department of Computer Science at the Korea Military Academy from 2004 to 2007 while he was serving his military duty in South Korea.

He was a R&D team lead of the Amelia project, the next generation machine reading system developed at IPsoft Inc. He is the founder of the Natural Language Processing Research lab at Emory University.

Jinho Choi has been active in research on natural language processing; especially, on the optimization of low-level NLP (e.g., dependency parsing, named entity recognition, sentiment analysis) for robustness on various data and scalability on large data.

He has developed an open source project called NLP4J, providing NLP components with state-of-the-art accuracy and speed, which has been widely used for both academic and industrial research.

His current research focuses on the development of NLP components for different domains (e.g., social media, radiology reports, dialogs) and the applications of these NLP components for end-user systems such as question-answering, character mining, text generation, etc. He is also interested in interdisciplinary research where NLP can enhance researches in other areas.

Education

  • Ph.D., Joint Degree in Computer Science and Cognitive Science, University of Colorado at Boulder, 2012
  • M.S.E., Computer and Information Science, University of Pennsylvania, 2003
  • B.A., Dual Degree in Mathematics and Computer Science, Coe College, 2001

Research

  • My research focuses on the advancement of Natural Language Processing (NLP) for "robustness" on diverse data and "scalability" on large data. The goal is to develop NLP models that are readily available for interdisciplinary research. I believe that NLP models we develop will open up many new opportunities to conduct innovative research. All our models are publicly available through our open-source project.
  • In 2019, I started a new project, Emora, to develop a chatbot that aims to be a social companion who cares about you, learns from you, and shares thoughts and feelings with you. Our team has been selected as one of the 10 participants of the Alexa Prize Socialbot Grand Challenge 3. The goal is to develop a chatbot that helps people with mental illness such as depression or Alzheimer's Disease through natural conversations.
  • In 2018, we started developing a cloud-based NLP platform called ELIT, Evolution of Language and Information Technology, that brings the latest NLP technology into the cloud. Researchers can take advantage of the ELIT platform through web-APIs, which requires no installation on local machines and minimum knowledge in any programming language, while developers can contribute to the platform by deploying their own models.
  • In 2015, I started a new project, Character Mining, aiming to extract implicit and explicit information about individual characters in multiparty dialogue. The goal is to develop a machine comprehension system that understands entity-centric contexts from human conversations and helps us reason better about those contexts. This project has many novel tasks such as character identification, emotion detection, reading comprehension, question answering, and personality detection.

Teaching

  • QTM/CS 329: Computational Linguistics
  • QTM 340: Practical Approaches to Data Science w/Text