Ruohao Guo

Ruohao Guo

CS Ph.D. Student

Georgia Institute of Technology

Hi!

I am a Ph.D. student in the School of Interactive Computing at Georgia Tech and my advisor is Prof. Alan Ritter. I previously received my Bachelor’s Degree in Mathematics and Computer Science from University of Illinois at Urbana-Champaign. During my time at UIUC, I was fortunate to work with Prof. Dan Roth.

Interests
  • Natural Language Processing
  • Machine Learning
Education

  • Ph.D. Student in Computer Science, 2021 - Present

    Georgia Institute of Technology

  • BSc in Mathematics and Computer Science, 2018 - 2021

    University of Illinois at Urbana-Champaign

Publications

IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
Current foundation models exhibit impressive capabilities when prompted either with text only or with both image and text inputs. But …
Deqing Fu, Ruohao Guo, Ghazal Khalighinejad, Ollie Liu, Bhuwan Dhingra, Dani Yogatama, Robin Jia, Willie Neiswanger
PDF Cite Dataset Project
IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that …
Ruohao Guo, Wei Xu, Alan Ritter
PDF Cite Code Dataset
Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
Improved Instruction Ordering in Recipe-Grounded Conversation
In this paper, we study the task of instructional dialogue and focus on the cooking domain. Analyzing the generated output of the GPT-J …
Duong Minh Le, Ruohao Guo, Wei Xu, Alan Ritter
PDF Cite Code Dataset
Improved Instruction Ordering in Recipe-Grounded Conversation
Constrained Labeled Data Generation for Low-Resource Named Entity Recognition
Named Entity Recognition (NER) in low-resource languages has been a long-standing challenge in NLP. Recent work has shown great …
Ruohao Guo, Dan Roth
PDF Cite Code DOI
Constrained Labeled Data Generation for Low-Resource Named Entity Recognition
See all publications

Experience

 
 
 
 
 
Research Assistant
University of Pennsylvania
Jun 2020 – Aug 2021
  • Compared different multilingual Named Entity Recognition models (eg. mBERT, XLM-R, Cogcomp) for 33 languages, and implemented an online demo with state-of-the-art performance.
  • Improved Named Entity Recognition for low-resource languages.
  • Participated in building a timeline summarization dataset.
 
 
 
 
 
Lead Course Assistant
University of Illinois at Urbana-Champaign
Aug 2019 – May 2021

Responsibilities include:

  • Running labs and office hours
  • Designing lecture notes
  • Maintaining course websites
  • Answering questions on Piazza

Projects

*
All Deep Learning
Open Source TensorFlow Visualization Tool
A TensorFlow visualization tool that helps monitor the real-time data in TensorFlow programs.
Open Source TensorFlow Visualization Tool