Guy Divita


pdf bib
Development of Natural Language Processing Tools to Support Determination of Federal Disability Benefits in the U.S.
Bart Desmet | Julia Porcino | Ayah Zirikly | Denis Newman-Griffis | Guy Divita | Elizabeth Rasch
Proceedings of the 1st Workshop on Language Technologies for Government and Public Administration (LT4Gov)

The disability benefits programs administered by the US Social Security Administration (SSA) receive between 2 and 3 million new applications each year. Adjudicators manually review hundreds of evidence pages per case to determine eligibility based on financial, medical, and functional criteria. Natural Language Processing (NLP) technology is uniquely suited to support this adjudication work and is a critical component of an ongoing inter-agency collaboration between SSA and the National Institutes of Health. This NLP work provides resources and models for document ranking, named entity recognition, and terminology extraction in order to automatically identify documents and reports pertinent to a case, and to allow adjudicators to search for and locate desired information quickly. In this paper, we describe our vision for how NLP can impact SSA’s adjudication process, present the resources and models that have been developed, and discuss some of the benefits and challenges in working with large-scale government data, and its specific properties in the functional domain.


pdf bib
Classifying the reported ability in clinical mobility descriptions
Denis Newman-Griffis | Ayah Zirikly | Guy Divita | Bart Desmet
Proceedings of the 18th BioNLP Workshop and Shared Task

Assessing how individuals perform different activities is key information for modeling health states of individuals and populations. Descriptions of activity performance in clinical free text are complex, including syntactic negation and similarities to textual entailment tasks. We explore a variety of methods for the novel task of classifying four types of assertions about activity performance: Able, Unable, Unclear, and None (no information). We find that ensembling an SVM trained with lexical features and a CNN achieves 77.9% macro F1 score on our task, and yields nearly 80% recall on the rare Unclear and Unable samples. Finally, we highlight several challenges in classifying performance assertions, including capturing information about sources of assistance, incorporating syntactic structure and negation scope, and handling new modalities at test time. Our findings establish a strong baseline for this novel task, and identify intriguing areas for further research.