@inproceedings{karamcheti-etal-2017-tale,
title = "A Tale of Two {DRAGGN}s: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions",
author = "Karamcheti, Siddharth and
Williams, Edward Clem and
Arumugam, Dilip and
Rhee, Mina and
Gopalan, Nakul and
Wong, Lawson L.S. and
Tellex, Stefanie",
editor = "Bansal, Mohit and
Matuszek, Cynthia and
Andreas, Jacob and
Artzi, Yoav and
Bisk, Yonatan",
booktitle = "Proceedings of the First Workshop on Language Grounding for Robotics",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2809",
doi = "10.18653/v1/W17-2809",
pages = "67--75",
abstract = "Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands. These instructions often fall into one of two categories: those that specify a goal condition or target state, and those that specify explicit actions, or how to perform a given task. Recent approaches have used reward functions as a semantic representation of goal-based commands, which allows for the use of a state-of-the-art planner to find a policy for the given task. However, these reward functions cannot be directly used to represent action-oriented commands. We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes to unseen environments. Our robot-simulation results demonstrate that a system successfully interpreting both goal-oriented and action-oriented task specifications brings us closer to robust natural language understanding for human-robot interaction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karamcheti-etal-2017-tale">
<titleInfo>
<title>A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Karamcheti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="given">Clem</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilip</namePart>
<namePart type="family">Arumugam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mina</namePart>
<namePart type="family">Rhee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nakul</namePart>
<namePart type="family">Gopalan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawson</namePart>
<namePart type="given">L.S.</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefanie</namePart>
<namePart type="family">Tellex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Grounding for Robotics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="family">Matuszek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Andreas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Artzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Bisk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands. These instructions often fall into one of two categories: those that specify a goal condition or target state, and those that specify explicit actions, or how to perform a given task. Recent approaches have used reward functions as a semantic representation of goal-based commands, which allows for the use of a state-of-the-art planner to find a policy for the given task. However, these reward functions cannot be directly used to represent action-oriented commands. We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes to unseen environments. Our robot-simulation results demonstrate that a system successfully interpreting both goal-oriented and action-oriented task specifications brings us closer to robust natural language understanding for human-robot interaction.</abstract>
<identifier type="citekey">karamcheti-etal-2017-tale</identifier>
<identifier type="doi">10.18653/v1/W17-2809</identifier>
<location>
<url>https://aclanthology.org/W17-2809</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>67</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions
%A Karamcheti, Siddharth
%A Williams, Edward Clem
%A Arumugam, Dilip
%A Rhee, Mina
%A Gopalan, Nakul
%A Wong, Lawson L.S.
%A Tellex, Stefanie
%Y Bansal, Mohit
%Y Matuszek, Cynthia
%Y Andreas, Jacob
%Y Artzi, Yoav
%Y Bisk, Yonatan
%S Proceedings of the First Workshop on Language Grounding for Robotics
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F karamcheti-etal-2017-tale
%X Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands. These instructions often fall into one of two categories: those that specify a goal condition or target state, and those that specify explicit actions, or how to perform a given task. Recent approaches have used reward functions as a semantic representation of goal-based commands, which allows for the use of a state-of-the-art planner to find a policy for the given task. However, these reward functions cannot be directly used to represent action-oriented commands. We introduce a new hybrid approach, the Deep Recurrent Action-Goal Grounding Network (DRAGGN), for task grounding and execution that handles natural language from either category as input, and generalizes to unseen environments. Our robot-simulation results demonstrate that a system successfully interpreting both goal-oriented and action-oriented task specifications brings us closer to robust natural language understanding for human-robot interaction.
%R 10.18653/v1/W17-2809
%U https://aclanthology.org/W17-2809
%U https://doi.org/10.18653/v1/W17-2809
%P 67-75
Markdown (Informal)
[A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions](https://aclanthology.org/W17-2809) (Karamcheti et al., RoboNLP 2017)
ACL