DeepAI AI Chat
Log In Sign Up

Neural Semantic Parsing with Anonymization for Command Understanding in General-Purpose Service Robots

by   Nick Walker, et al.
University of Washington

Service robots are envisioned to undertake a wide range of tasks at the request of users. Semantic parsing is one way to convert natural language commands given to these robots into executable representations. Methods for creating semantic parsers, however, rely either on large amounts of data or on engineered lexical features and parsing rules, which has limited their application in robotics. To address this challenge, we propose an approach that leverages neural semantic parsing methods in combination with contextual word embeddings to enable the training of a semantic parser with little data and without domain specific parser engineering. Key to our approach is the use of an anonymized target representation which is more easily learned by the parser. In most cases, this simplified representation can trivially be transformed into an executable format, and in others the parse can be completed through further interaction with the user. We evaluate this approach in the context of the RoboCup@Home General Purpose Service Robot task, where we have collected a corpus of paraphrased versions of commands from the standardized command generator. Our results show that neural semantic parsers can predict the logical form of unseen commands with 89 details of our models to encourage further development from the RoboCup and service robotics communities.


page 1

page 2

page 3

page 4


Desiderata for Planning Systems in General-Purpose Service Robots

General-purpose service robots are expected to undertake a broad range o...

Robust Incremental Neural Semantic Graph Parsing

Parsing sentences to linguistically-expressive semantic representations ...

Transition-based Abstract Meaning Representation Parsing with Contextual Embeddings

The ability to understand and generate languages sets human cognition ap...

Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing

Nearly all general-purpose neural semantic parsers generate logical form...

GRILLBot: An Assistant for Real-World Tasks with Neural Semantic Parsing and Graph-Based Representations

GRILLBot is the winning system in the 2022 Alexa Prize TaskBot Challenge...

A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers

We present a phenomenon-oriented comparative analysis of the two dominan...

Underwater Robotics Semantic Parser Assistant

Semantic parsing is a means of taking natural language and putting it in...