Dongjin Choi
How can we design Natural Language Process- ing (NLP) systems that learn from human feed- back? There is a growing research body of Human-in-the-loop (HITL) NLP frameworks that continuously integrate human feedback to improve the model itself. HITL NLP research is nascent but multifarious—solving various NLP problems, collecting diverse feedback from different people, and applying different methods to learn from collected feedback. We present a survey of HITL NLP work from both Machine Learning (ML) and Human- Computer Interaction (HCI) communities that highlights its short yet inspiring history, and thoroughly summarize recent frameworks fo- cusing on their tasks, goals, human interac- tions, and feedback learning methods. Finally, we discuss future directions for integrating hu- man feedback in the NLP development loop.