InterNLP 2022 will be co-located with NeurIPS 2022

Workshop proposal accepted


Interactive Learning for NLP means training, fine-tuning or otherwise adapting an NLP model to inputs from a human user or teacher. Relevant approaches range from active learning with a human in the loop, to training with implicit user feedback (e.g., clicks), dialogue systems that adapt to user utterances, and training with new forms of human input. Interactive learning is the converse of learning from datasets collected offline with no human input during the training process.

A key aspect of human learning is the ability to learn continuously from various sources of feedback. In contrast, much of the recent success of deep learning for NLP relies on large datasets and extensive compute resources to train and fine-tune models, which then remain fixed. This leaves a research gap for systems that adapt to the changing needs of individual users or allow users to continually correct errors as they emerge. Learning from user interaction is crucial for tasks that require a high grade of personalization and for rapidly changing or complex, multi-step tasks where collecting and annotating large datasets is not feasible, but an informed user can provide guidance.

After a successful launch of InterNLP 2021 at ACL 2021, the second workshop of interactive learning for NLP will be co-located with NeurIPS 2022. We will again feature several invited talks from well-known researchers in the field, a panel discussion, and – of course – talks and posters from all accepted papers! A call for papers will be published soon at this year's workshop website. We are looking forward to your submissions and participation!

Organizers: Yoav Artzi (Cornell University), Kianté Brantley (Cornell University), Soham Dan (University of Pennsylvania), Ji-Ung Lee (UKP, Technical University of Darmstadt), Khanh Nguyen (University of Maryland-College Park), Edwin Simpson (University of Bristol), Alane Suhr (Cornell University)