Learning Adaptive Language Interfaces through Decomposition

Siddharth Karamcheti, Dorsa Sadigh, Percy Liang


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.
Anthology ID:
2020.intexsempar-1.4
Volume:
Proceedings of the First Workshop on Interactive and Executable Semantic Parsing
Month:
November
Year:
2020
Address:
Online
Editors:
Ben Bogin, Srinivasan Iyer, Xi Victoria Lin, Dragomir Radev, Alane Suhr, Panupong, Caiming Xiong, Pengcheng Yin, Tao Yu, Rui Zhang, Victor Zhong
Venue:
intexsempar
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
23–33
Language:
URL:
https://aclanthology.org/2020.intexsempar-1.4
DOI:
10.18653/v1/2020.intexsempar-1.4
Bibkey:
Cite (ACL):
Siddharth Karamcheti, Dorsa Sadigh, and Percy Liang. 2020. Learning Adaptive Language Interfaces through Decomposition. In Proceedings of the First Workshop on Interactive and Executable Semantic Parsing, pages 23–33, Online. Association for Computational Linguistics.
Cite (Informal):
Learning Adaptive Language Interfaces through Decomposition (Karamcheti et al., intexsempar 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.intexsempar-1.4.pdf
Video:
 https://slideslive.com/38939456