Putting Humans in the Natural Language Processing Loop: A Survey

( * Authors contributed equally )
crown jewel figure
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 focusing on their tasks, goals, human interactions, and feedback learning methods.
Abstract
How can we design Natural Language Processing (NLP) systems that learn from human feedback? 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 focusing on their tasks, goals, human interactions, and feedback learning methods. Finally, we discuss future directions for integrating human feedback in the NLP development loop.
Citation
Putting Humans in the Natural Language Processing Loop: A Survey
PDF
Poster
(*Authors contributed equally)
@inproceedings{wangPuttingHumansNatural2021,
  title = {Putting {{Humans}} in the {{Natural Language Processing Loop}}: {{A Survey}}},
  shorttitle = {Putting {{Humans}} in the {{Natural Language Processing Loop}}},
  author = {Wang, Zijie J. and Choi, Dongjin and Xu, Shenyu and Yang, Diyi},
  year = {2021},
  month = mar,
  booktitle = "Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing",
  publisher = "Association for Computational Linguistics",
}