An agent for learning new natural language commands

Teaching via natural language is an intuitive way for end users to add functionality to a virtual assistant, enabling them to personalize their assistant with new commands without requiring the intervention of the system developer, who cannot possibly anticipate all of an end user’s needs. In this p...

Full description

Saved in:
Bibliographic Details
Published in:Autonomous agents and multi-agent systems 2020-04, Vol.34 (1), Article 6
Main Authors: Azaria, Amos, Srivastava, Shashank, Krishnamurthy, Jayant, Labutov, Igor, Mitchell, Tom M.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Commands
Computer Science
Computer Systems Organization and Communication Networks
Datasets
Electronic mail
End users
Language
Learning
Natural language
Natural language (computers)
Semantics
Service introduction
Software Engineering/Programming and Operating Systems
User Interfaces and Human Computer Interaction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Teaching via natural language is an intuitive way for end users to add functionality to a virtual assistant, enabling them to personalize their assistant with new commands without requiring the intervention of the system developer, who cannot possibly anticipate all of an end user’s needs. In this paper we introduce our Learning by Instruction Agent (LIA), the first virtual assistant, for an email domain, that is capable of learning how to perform new commands taught by end users in natural language. LIA grounds the semantics of each command in terms of primitive executable procedures. When a user provides LIA with a command that it does not understand, it prompts the user to explain the command through a sequence of natural language steps. From this input, LIA learns the meaning of the new command and how to generalize the command to novel situations. For example, having been taught how to “forward an email to Alice”, it can correctly understand “forward this email to Bob”. We show that users that were assigned to interact with LIA completed the task quicker than users assigned to interact with a non-learning agent. These results demonstrate the potential of natural language teaching to improve the capabilities of intelligent personal assistants. We annotated 4759 natural language statements with their associated computer readable execution commands (logical forms) to form a dataset (which we publicize in this paper). We present the performance of several different parser methods on this dataset.
ISSN:1387-2532
1573-7454
DOI:10.1007/s10458-019-09425-x