In this chapter of Advancing Natural Language Processing in Educational Assessment, Director of Research Polina Harik, PhD, Measurement Scientist Janet Mee, PhD, Senior Measurement Scientist Christopher Runyon, PhD and Distinguished Research Scientist Brian Clauser, PhD describe INCITE, a natural language processing (NLP)-based system for scoring free-text responses.

The system was developed by NBME to score responses produced as part of the USMLE^® Step 2 Clinical Skills Examination. The specifics of that application make our system unique in several ways because:

1. The INCITE was intended for use as part of physician licensure and must therefore function with a specialized medical vocabulary.
2. The scores for the written responses were based entirely on the content of the response, as well-structured and complete sentences are not required and spelling is secondary.
3. The scores from the examination were used to make high-stakes decisions, hence accuracy is critical.
4. The procedures used for scoring must be transparent so that it is possible to identify the specific scorable features of the text that the algorithm identified in each response