Abstract: Methods, apparatuses, and systems for more efficiently assessing the performance of a person on a test or at completing a task. The disclosure is directed to systems, apparatuses, and methods for training a model to jointly predict (a) test item annotations (e.g., a domain or subject-matter expert's assessment of the difficulty level of a test item) and (b) test-taker responses. The disclosed approach may be used to estimate item parameters used in tests for evaluating the proficiency of a test taker, and more specifically, as part of a language proficiency test or examination.

Abstract: System and methods for improving automated test personalization are disclosed. The server system communicates a plurality of assessment questions to a client system for presentation to a user through a user interface. The system receives a user response for each transmitted assessment question and then compares the received user responses to reference data stored in an answer database at the server system to generate an estimated proficiency score for the user. Based on the generated estimated proficiency score, the server system automatically selects an interview prompt from a plurality of possible interview prompts. The server then communicates, to the client system, the selected interview prompt and instructions to cause the client system to record a live video of the user responding to the selected interview prompt. The server system then receives and stores a recorded live video of the user responding to the selected interview prompt.