Kevin Stowe

At ETS, I am working on generating content for testing and educational applications. We're striving to build high-quality, bias-free solutions for education, and it's an exciting team to be a part of!

I work to ensure responsible AI practices, including assessing fairness and bias in generated content, dealing with misinformation, and supporting ethical and responsible use of large language models.
In my most recent work, I developed and evaluated a series of systems to ensure LLM-generated content follows fairness, bias, and accessibility constraints specific to certain tests. For more, see our BEA 2024 publication.

I've also worked on various aspects of controlled content generation: building sentences for testing that contain the right vocabulary. For more, see our Industry Track at EMNLP 2022 Publication

I'm fascinated by creative language generation: exploring possibilities for generating all sorts of novel language (humor, metaphor, etc) using deep learning. Are end-to-end models sufficient, and if not, how can we improve them to handle this difficult area of language?

We built a system to generate conceptual metaphors based on BART, Frame Semantics, and other tools: see our ACL paper Metaphoric Generation with Conceptual Mappings
Relatedly, we built a dataset of idiomatic and metaphoric paraphrases to explore natural language inference capabilities on figurative language:IMPLI: Investigating NLI Models' Performance on Figurative Language

Crisis informatics: how can we provide concrete benefits and relief to those impacted by natural disasters using NLP technology?
- I collaborated on a project attempting automatically adapt to rapidly changing language during crises, presented at the Findings of EMNLP 2022
- Our group explored social media collection and analysis for crises events, supporting citizen science efforts to annotate the never-ending stream of data that can contribute to our situational awareness, including the COVID-19 crisis. Our goal is to build a system for quick and efficient data collection and annotation to improve responses to natural hazards. Our collection uses the helpful Nasty Scraper for collection as well as the powerful INCEpTION tool for annotation. Presented at EACL 2023.
- Check out my and my students' work on a social good data collection pipeline, presented at the AAAI Fall Symposium on Social Good

Doctoral dissertation on syntactically motivated approaches to metaphors, with the CLEAR group under Profs. Martha Palmer and Jim Martin. I studied how syntax can influence metaphoric properties, and this can be leveraged to improve deep-learning metaphor detection.
Supported lexical resources at the University of Colorado, including VerbNet and SemLink.
Worked for the Project Epic lab with Profs. Leysia Palen and Kenneth M. Anderson. We collaborated with NCAR to analyze responses to hurricanes, and build improved computaitonal methods for data analysis and exploration in order to assist researchers understanding the effects of natural disasters.