Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language
Our goal is to build robots that can robustly interact with humans using natural language. This problem is extremely challenging because human language is filled with ambiguity, and furthermore, the robot's model of the environment might be much more limited than the human partner. When humans...
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Language: | en-US |
Published: |
2012
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/68651 |
_version_ | 1811088797062922240 |
---|---|
author | Tellex, Stefanie Thaker, Pratiksha Deits, Robin Simeonov, Dimitar Kollar, Thomas Roy, Nicholas |
author2 | Nick Roy |
author_facet | Nick Roy Tellex, Stefanie Thaker, Pratiksha Deits, Robin Simeonov, Dimitar Kollar, Thomas Roy, Nicholas |
author_sort | Tellex, Stefanie |
collection | MIT |
description | Our goal is to build robots that can robustly interact with humans using natural language. This problem is extremely challenging because human language is filled with ambiguity, and furthermore, the robot's model of the environment might be much more limited than the human partner. When humans encounter ambiguity in dialog with each other, a key strategy to resolve it is to ask clarifying questions about whatthey do not understand. This paper describes an approach for enabling robots to take the same approach: asking the human partner clarifying questions about ambiguous commands in order to infer better actions. The robot fuses information from the command, the question, and the answer by creating a joint probabilistic graphical model in the Generalized Grounding Graph framework. We demonstrate that by performing inference using information from the command, question and answer, the robot is able to infer object groundings and follow commands with higher accuracythan by using the command alone. |
first_indexed | 2024-09-23T14:07:42Z |
id | mit-1721.1/68651 |
institution | Massachusetts Institute of Technology |
language | en-US |
last_indexed | 2024-09-23T14:07:42Z |
publishDate | 2012 |
record_format | dspace |
spelling | mit-1721.1/686512019-04-12T15:20:47Z Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language Tellex, Stefanie Thaker, Pratiksha Deits, Robin Simeonov, Dimitar Kollar, Thomas Roy, Nicholas Nick Roy Robotics, Vision & Sensor Networks dialog, robotics, question-asking Our goal is to build robots that can robustly interact with humans using natural language. This problem is extremely challenging because human language is filled with ambiguity, and furthermore, the robot's model of the environment might be much more limited than the human partner. When humans encounter ambiguity in dialog with each other, a key strategy to resolve it is to ask clarifying questions about whatthey do not understand. This paper describes an approach for enabling robots to take the same approach: asking the human partner clarifying questions about ambiguous commands in order to infer better actions. The robot fuses information from the command, the question, and the answer by creating a joint probabilistic graphical model in the Generalized Grounding Graph framework. We demonstrate that by performing inference using information from the command, question and answer, the robot is able to infer object groundings and follow commands with higher accuracythan by using the command alone. 2012-01-24T22:30:02Z 2012-01-24T22:30:02Z 2012-01-23 http://hdl.handle.net/1721.1/68651 en-US MIT-CSAIL-TR-2012-002 2 p. application/pdf |
spellingShingle | dialog, robotics, question-asking Tellex, Stefanie Thaker, Pratiksha Deits, Robin Simeonov, Dimitar Kollar, Thomas Roy, Nicholas Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language |
title | Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language |
title_full | Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language |
title_fullStr | Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language |
title_full_unstemmed | Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language |
title_short | Toward a Probabilistic Approach to Acquiring Information from Human Partners Using Language |
title_sort | toward a probabilistic approach to acquiring information from human partners using language |
topic | dialog, robotics, question-asking |
url | http://hdl.handle.net/1721.1/68651 |
work_keys_str_mv | AT tellexstefanie towardaprobabilisticapproachtoacquiringinformationfromhumanpartnersusinglanguage AT thakerpratiksha towardaprobabilisticapproachtoacquiringinformationfromhumanpartnersusinglanguage AT deitsrobin towardaprobabilisticapproachtoacquiringinformationfromhumanpartnersusinglanguage AT simeonovdimitar towardaprobabilisticapproachtoacquiringinformationfromhumanpartnersusinglanguage AT kollarthomas towardaprobabilisticapproachtoacquiringinformationfromhumanpartnersusinglanguage AT roynicholas towardaprobabilisticapproachtoacquiringinformationfromhumanpartnersusinglanguage |