Learning Adaptive Language Interfaces through Decomposition
arXiv:2010.05190
Abstract
Our goal is to create an interactive natural language interface that efficiently and reliably learns from users to complete tasks in simulated robotics settings. We introduce a neural semantic parsing system that learns new high-level abstractions through decomposition: users interactively teach the system by breaking down high-level utterances describing novel behavior into low-level steps that it can understand. Unfortunately, existing methods either rely on grammars which parse sentences with limited flexibility, or neural sequence-to-sequence models that do not learn efficiently or reliably from individual examples. Our approach bridges this gap, demonstrating the flexibility of modern neural systems, as well as the one-shot reliable generalization of grammar-based methods. Our crowdsourced interactive experiments suggest that over time, users complete complex tasks more efficiently while using our system by leveraging what they just taught. At the same time, getting users to trust the system enough to be incentivized to teach high-level utterances is still an ongoing challenge. We end with a discussion of some of the obstacles we need to overcome to fully realize the potential of the interactive paradigm.
arXiv commentAccepted at the 1st Workshop for Interactive and Executable Semantic Parsing (IntEx-SemPar) @ EMNLP 2020. 11 pages, 5 figures
References in corpus (6)
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Grounded Language Learning in a Simulated 3D World
- CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
- CraftAssist: A Framework for Dialogue-enabled Interactive Agents