[2010.05190] Learning Adaptive Language Interfaces through Decompositionopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

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

3 mentions: @siddkaramcheti@DorsaSadigh
Date: 2020/10/17 23:21

Referring Tweets

@DorsaSadigh Beginning of many future exciting RoboNLP work. Learning adaptive language interfaces through interaction: t.co/c9CkE4MAsI w/ @siddkaramcheti and Percy Liang
@siddkaramcheti How do we build adaptive language interfaces that learn through interaction with real human users? New work w/ my amazing advisors @DorsaSadigh and @percyliang, to be presented at the @intexsempar2020 workshop at #emnlp2020. Link: t.co/2VqAPhtks3 A thread 🧵(1 / N). t.co/174Ju39VQj

Related Entries

Read more Notes on the Limitations of the Empirical Fisher Approximation
1 users, 3 mentions 2019/06/06 14:23
Read more [1906.02940] Selfie: Self-supervised Pretraining for Image Embedding
1 users, 5 mentions 2019/06/10 02:18
Read more Learn how to make BERT smaller and faster
0 users, 8 mentions 2019/08/08 14:56
Read more A Connectome of the Adult Drosophila Central Brain | bioRxiv
0 users, 11 mentions 2020/01/31 03:51
Read more Kubeflow 1.0: Cloud-Native ML for Everyone - kubeflow - Medium
0 users, 6 mentions 2020/03/02 17:44