no code implementations • NAACL (CLPsych) 2022 • John Culnan, Damian Romero Diaz, Steven Bethard
This paper presents transformer-based models created for the CLPsych 2022 shared task.
no code implementations • EACL (WASSA) 2021 • John Culnan, SeongJin Park, Meghavarshini Krishnaswamy, Rebecca Sharp
In deployment, systems that use speech as input must make use of automated transcriptions.
no code implementations • NAACL (DADC) 2022 • Damian Y. Romero Diaz, Magdalena Anioł, John Culnan
We present our experience as annotators in the creation of high-quality, adversarial machine-reading-comprehension data for extractive QA for Task 1 of the First Workshop on Dynamic Adversarial Data Collection (DADC).
no code implementations • LREC 2020 • Hannah Smith, Zeyu Zhang, John Culnan, Peter Jansen
Named entity recognition identifies common classes of entities in text, but these entity labels are generally sparse, limiting utility to downstream tasks.