My main research community is natural language processing (NLP), which lies at the intersection of computational linguistics and AI. NLP research is organized through the Association for Computational Linguistics and sister organizations, and is mostly published in the ACL Anthology.
I study human language and computation. My research asks: How do people conceptually and linguistically organize meanings in their languages, and how does this organization manifest in usage data and AI models?
This includes work with LLMs; corpora; and analytical frameworks like CCG, CGELBank, UD (for syntax), and AMR, FrameNet, SNACS, UCCA (for semantics).
Recent research highlights (2024–2026):
- Linguistic interpretation of transformer language models
- Modeling nonnative sentence processing with L2 Language Models
- Construction identification and disambiguation using BERT: A case study of NPN
- Unpacking Let Alone: Human-scale models generalize to a rare construction in form but not meaning
- Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions
- Corpora and language learning
- Cross-linguistically consistent semantic and syntactic annotation of child-directed speech
- UD-English-CHILDES: A collected resource of gold and silver Universal Dependencies trees for child language Interactions
- CAIT: A Syntactic Parsing Toolkit for Child–Adult InTeractions
- ELQA: A corpus of metalinguistic questions and answers about English
- Crosslinguistic syntax/semantics
- Multilinguality in NLP systems
- Syntactic inductive bias in transformer language models: especially helpful for low-resource languages?
- Lost in translationese? Reducing translation effect using Abstract Meaning Representation
- To ask LLMs about English grammaticality, prompt them in a different language
- Speaking of Language: Reflections on Metalanguage Research in NLP
- Legal interpretation → LegIT Lab
- Unmasking textualism: Linguistic misunderstanding in the transit mask order case and beyond
- CuRIAM: Corpus Re Interpretation and Metalanguage in U.S. Supreme Court opinions
- Reading law with linguistics: The statutory interpretation of artifact nouns; Brief for Professors and Scholars of Linguistics and Law as Amici Curiae in Support of Petitioners, Garland v. VanDerStok (news writeup: How Georgetown Linguists, Legal Expert Scored a Win in Supreme Court ‘Ghost Guns’ Case)
- Large language models for legal interpretation? Don't take their word for it; Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis; Sense and Sensitivity: “Reasoning” Models are More Robust, but can Diverge from Human Consensus in a Legal Interpretation Task
An extended research overview covers highlights of my published research to May 2022. (There is a brief research overview from 2016.)
For further details, refer to my recent publications or reach out to students in my lab.