Katherine A. Keith
I am excited to announce I am joining Williams College as an Assistant Professor in Fall 2022. Starting in September, I will be in Seattle working with AI2 and their Semantic Scholar Team as a Young Investigator. I am grateful to have been supported by a Bloomberg Data Science PhD Fellowship 2019-2021.
My research is in the domain of social data science, answering questions about human behavior through quantitative analysis of large-scale data. I focus on methods and applications with text data because language is one of the richest and most salient expressions of human thought and behavior. This work is closely aligned to the fields of computational social science and text-as-data.My research expands methods in machine learning and natural language processing to social data science goals including: obtaining quantifiable social measurements from text data, aggregating said measurements in a statistically rigorous manner, and improving causal estimations from text. I also apply these methods to applications such as extracting macro-social measures from newspapers and studying the language of economic decision making.
- Spring 2020 — Instructor, CS335: Machine Learning, Mount Holyoke College
- Fall 2018 — Instructor, CS191: Ethical Issues Surrounding Artificial Intelligence Systems and Big Data, UMass Amherst
- Spring 2018 — Teaching Assistant, CS685: Advanced NLP, UMass Amherst
Uncertainty over Uncertainty: Investigating the Assumptions, Annotations, and Text Measurements of Economic Policy Uncertainty.
Katherine A. Keith, Christoph Teichmann, Brendan O'Connor, and Edgar Meij.
NLP+CSS Workshop at EMNLP, 2020.
Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates.
Katherine A. Keith , David Jensen, and Brendan O'Connor.
ACL, 2020. [video & slides]
Modeling financial analysts’ decision making via the pragmatics and semantics of earnings calls.
Katherine A. Keith and Amanda Stent.
ACL, 2019. [supplementary material] [poster] [bibtex]
Uncertainty-aware generative models for inferring document class prevalence.
Katherine A. Keith and Brendan O'Connor.
EMNLP, 2018. [code] [poster] [bibtex] [software]
Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses.
Katherine A. Keith, Su Lin Blodgett, and Brendan O'Connor.
NAACL, 2018. [code] [poster] [bibtex]
Identifying civilians killed by police with distantly supervised entity-event extraction.
Katherine A. Keith, Abram Handler, Michael Pinkham, Cara Magliozzi, Joshua McDuffie, and Brendan O’Connor.
EMNLP, 2017. [code & data] [slides] [bibtex] [press] [video]
- December 2020 — I was named an Outstanding Reviewer for EMNLP 2020.
- November 2020 — I am on the organizing committee for the 1st Workshop on Causal Inference & NLP which will be held at EMNLP 2021.
- April 2020 — Andy Halterman, Sheikh Sarwar, and I were awarded a $5,000 Kaggle Open Data Research Grant for "Semantic Role Annotations For Real-World Political Texts."
- Spring 2020 — I joined and am actively working with the REBLS (Research, Educator, Business Leaders, and Students) Network to increase access and opportunity for underrepresented students in computer science and engineering!
- January 1, 2020 — It has been my distinct pleasure to serve as Co-Chair of CSWomen, a group of graduate women in computer science here at UMass, for two semesters! Here is a recap of the events we organized last semester.
- December 6, 2019 — I passed portfolio (the equivalent of a PhD candidacy exam) with distinction.
- November 15, 2019 — I was the invited speaker at Williams College's Computer Science Colloquium.
- August 2019 — Honored to have received a Bloomberg Data Science PhD Fellowship. Here's a profile from UMass's Center for Data Science.
- July 2019 — Really enjoyed mentoring three undergrad researchers this summer. Check out a profile on their experience.
- September 24, 2018 — I was the invited speaker at Lewis & Clark College's Mathematical Sciences Colloquium.
- September 2018 — Su Lin Blodgett, Abe Handler, and I co-designed and co-taught Ethical Issues Surrounding Artificial Intelligence Systems and Big Data, a semester-long first-year computer science seminar at UMass.
- May 2018 — I am interning with Amanda Stent at Bloomberg L.P. in New York this summer.
- November 2017 — I helped design and organize our college's first Male Ally Workshop for graduate computer science students.
In the past, I really enjoyed studying Chinese. I lived for twelve months in Kinmen, Taiwan on a Fulbright English Teaching Assistantship, and I completed a language immersive study abroad program in Beijing, China during a semester in undergrad.
In my free time, I enjoy trail-running, sport climbing, triathlons, and backcountry and downhill skiing.
Amherst, Massachusetts, USA
kkeith (at) cs (dot) umass (dot) edu