We present Generate, a AI-human hybrid system to help education content creators interactively generate assessment content in an efficient and scalable manner. Our system integrates advanced natural language generation (NLG) approaches with subject matter expertise of assessment developers to efficiently generate a large number of highly customized and valid assessment items. We utilize the powerful Transformer architecture which is capable of leveraging substantive pretraining on several generic text corpora in order to produce sophisticated, context-dependent text as the basis for item creation. We present early results from experimental studies demonstrating the efficiency of our approach.

Citation Key: khan2021 <标题>: 生成：用于教育内容创作的自然语言生成系统