Prospective students
If you are a prospective PhD student hoping to work with me, instead of emailing me, directly apply to the INFO PhD program. A compelling application will include:
- a candidate statement that explains why we would be a good fit for each other, for example, because you have prior research related to my ongoing projects
- a curriculum vitae that demonstrates your research potential through publications in natural language processing workshops, conferences, or journals such as those on the ACL Anthology.
If you are an undergraduate or masters student interested in a one-semester directed research, I typically take on a small number of students each semester who:
- are already at the University of Arizona
- have achieved A grades in ISTA 457/INFO 557 (Neural Networks) and/or ISTA 439/INFO 539 (Statistical Natural Language Processing)
- are interested in working on one of my ongoing projects or one of the current SemEval tasks
If you meet all of the above criteria, please email me which project or task you would be interested in, along with your prior experience.
Current students
Graduated students
- Yiyun Zhao, Ph.D., Linguistics, University of Arizona, 2022
Thesis: How to probe linguistic knowledge and bias - Dongfang Xu, Ph.D., Information, University of Arizona, 2021
Thesis: Neural Network Algorithms for Ontology Informed Information Extraction - Vikas Yadav, Ph.D., Information, University of Arizona, 2020
Thesis: Evidence Retrieval for Explainable Question Answering - Farig Sadeque, Ph.D., Information, University of Arizona, 2019
Thesis: User behavior in social media: engagement, incivility, and depression - John Osborne, Ph.D., Computer and Information Sciences, University of Alabama at Birmingham, 2016
Thesis: Machine Learning of Composite Concepts and the Alleviation of The Content Completeness Problem in Text Mention Normalization - Upendra Sapkota, Ph.D., Computer and Information Sciences, University of Alabama at Birmingham, 2015
Thesis: Improving the performance of cross-domain authorship attribution