Katherine A. Keith
kak5 (at) williams (dot) edu
curriculum vitae (CV)
Home
Research
Teaching
Working Papers
Codebook LLMs: Adapting Political Science Codebooks for LLM Use and Adapting LLMs to Follow Codebooks
Andrew Halterman and
Katherine A. Keith
.
Publications
Proximal Causal Inference With Text Data
Jacob M. Chen, Rohit Bhattacharya, and
Katherine A. Keith
.
Forthcoming, NeurIPS 2024. [
poster-acic-2024
]
"Let Me Just Interrupt You": Estimating Gender Effects in Supreme Court Oral Arguments.
Erica Cai, Ankita Gupta,
Katherine Keith
, Brendan O'Connor, and Douglas R. Rice.
Forthcoming, Journal of Law and Courts. [
press
] [
press-podcast
] [
poster-tada-2022
] [
slides
] [
code & data
]
Democratizing Machine Learning for Interdisciplinary Scholars: Reflections on the NLP+CSS Tutorial Series.
Katherine A. Keith
and Ian Stewart.
Teaching4NLP Workshop, 2023.
[website]
[YouTube channel]
RCT Rejection Sampling for Causal Estimation Evaluation.
Katherine A. Keith
, Sergey Feldman, David Jurgens, Jonathan Bragg, and Rohit Bhattacharya.
TMLR, November 2023.
[code & data]
[open reviews]
[slides-JSM]
Literary Intertextual Semantic Change Detection: Application and Motivation for Evaluating Models on Small Corpora
Jackson Ehrenworth and
Katherine A. Keith
.
LChange Workshop at EMNLP, 2023.
[code & data]
Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies.
Raymond Z. Zhang, Neha Nayak Kennard, Daniel Scott Smith, Daniel A. McFarland, Andrew McCallum, and
Katherine A. Keith
.
Findings of ACL, 2023.
[overview slide]
[code & data]
Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications.
Li Lucy, Jesse Dodge, David Bamman, and
Katherine A. Keith
.
Findings of ACL, 2023.
[blog post]
[code & data]
Paying Attention to the Algorithm Behind the Curtain: Bringing Transparency to YouTube’s Demonetization Algorithms.
Arun Dunna,
Katherine A. Keith
, Ethan Zuckerman, Narseo Vallina-Rodriguez, Brendan O'Connor, Rishab Nithyanand.
CSCW, 2022.
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond.
Amir Feder,
Katherine A. Keith
, (and many others).
TACL, 2022.
[github page]
Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects.
Katherine A. Keith
, Douglas Rice, and Brendan O'Connor.
CI+NLP Workshop at EMNLP, 2021.
[poster]
[slides]
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence.
Andrew Halterman*,
Katherine A. Keith
*, Sheikh Muhammad Sarwar*, and Brendan O'Connor. (*joint first-authors)
Findings of ACL, 2021.
[data & code]
[poster]
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.
[video & slides]
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]
PhD dissertation
Social Measurement and Causal Inference with Text
.
Katherine A. Keith
.
PhD Dissertation, University of Massachusetts Amherst, 2021.
[slides]
[video]