Second Workshop on Interactive Learning for Natural Language Processing


For virtual attendees (change to your local timezone)


Opening Remarks


Invited talk
Karthik Narasimhan A desirable feature of interactive NLP systems is the ability to receive feedback from humans and personalize to new users. Existing paradigms encounter challenges in acquiring new concepts due to the use of discrete labels and scalar rewards. As one solution to alleviate this problem, I will present our work on Semantic Supervision (SemSUP), which trains models to predict over multiple natural language descriptions of classes (or even structured ones like JSON). SemSUP can seamlessly replace any standard supervised learning setup without sacrificing any in-distribution accuracy, while providing generalization to unseen concepts and scalability to large label spaces.


Invited talk
John Langford (invited talk)


Coffee Break


Contributed Talk
Is Reinforcement Learning (Not) for Natural Language Processing? Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization Rajkumar Ramamurthy and Prithviraj Ammanabrolu


Contributed Talk
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents Shunyu Yao


Invited talk
Dan Weld (invited talk)


Invited talk
Qian Yang (invited talk)


Lunch Break


Poster Sessions


Contributed Talk
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions Bodhisattwa Prasad


Contributed Talk
Error Detection for Interactive Text-to-SQL Semantic Parsing Shijie Chen


Invited Talk
Anca Dragan: Learning human preferences from language In classic instruction following, language like "I'd like the JetBlue flight" maps to actions (e.g., selecting that flight). However, language also conveys information about a user's underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. In this talk, I'll share a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences.


Coffee Break


Invited Talk
Aida Nematzadeh There has been an increased interest in developing general-purpose pretrained models across different domains, such as language, vision, and multimodal. This approach is appealing because we can pretrain models on large datasets once, and then adapt them to various tasks using a smaller supervised dataset. Moreover, these models achieve impressive results on a range of benchmarks, often performing better than task-specific models. Finally, this pretraining approach processes the data passively and does not rely on actively interacting with humans. In this talk, I will first discuss what aspects of language children can learn passively and to what extent interacting with others might require developing theory of mind. Next, I discuss the need for better evaluation pipelines to better understand the shortcomings and strengths of pretrained models. In particular, I will talk about: (1) the necessity of directly measuring real-world performance (as opposed to relying on benchmark performance), (2) the importance of strong baselines, and (3) how to design probing dataset to measure certain capabilities of our models. I will focus on commonsense reasoning, verb understanding, and theory of mind as challenging domains for our existing pretrained models.


Panel Discussion
tbd (panelists: tbd)


Closing Remarks