@inproceedings{alomari-etal-2017-natural,
title = "Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands",
author = "Alomari, Muhannad and
Duckworth, Paul and
Hawasly, Majd and
Hogg, David C. and
Cohn, Anthony G.",
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/W17-2805",
doi = "10.18653/v1/W17-2805",
pages = "35--43",
abstract = "We present a cognitively plausible system capable of acquiring knowledge in language and vision from pairs of short video clips and linguistic descriptions. The aim of this work is to teach a robot manipulator how to execute natural language commands by demonstration. This is achieved by first learning a set of visual {`}concepts{'} that abstract the visual feature spaces into concepts that have human-level meaning. Second, learning the mapping/grounding between words and the extracted visual concepts. Third, inducing grammar rules via a semantic representation known as Robot Control Language (RCL). We evaluate our approach against state-of-the-art supervised and unsupervised grounding and grammar induction systems, and show that a robot can learn to execute never seen-before commands from pairs of unlabelled linguistic and visual inputs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alomari-etal-2017-natural">
<titleInfo>
<title>Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhannad</namePart>
<namePart type="family">Alomari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Duckworth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majd</namePart>
<namePart type="family">Hawasly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Hogg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Cohn</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>We present a cognitively plausible system capable of acquiring knowledge in language and vision from pairs of short video clips and linguistic descriptions. The aim of this work is to teach a robot manipulator how to execute natural language commands by demonstration. This is achieved by first learning a set of visual ‘concepts’ that abstract the visual feature spaces into concepts that have human-level meaning. Second, learning the mapping/grounding between words and the extracted visual concepts. Third, inducing grammar rules via a semantic representation known as Robot Control Language (RCL). We evaluate our approach against state-of-the-art supervised and unsupervised grounding and grammar induction systems, and show that a robot can learn to execute never seen-before commands from pairs of unlabelled linguistic and visual inputs.</abstract>
<identifier type="citekey">alomari-etal-2017-natural</identifier>
<identifier type="doi">10.18653/v1/W17-2805</identifier>
<location>
<url>https://aclanthology.org/W17-2805</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>35</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands
%A Alomari, Muhannad
%A Duckworth, Paul
%A Hawasly, Majd
%A Hogg, David C.
%A Cohn, Anthony G.
%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 alomari-etal-2017-natural
%X We present a cognitively plausible system capable of acquiring knowledge in language and vision from pairs of short video clips and linguistic descriptions. The aim of this work is to teach a robot manipulator how to execute natural language commands by demonstration. This is achieved by first learning a set of visual ‘concepts’ that abstract the visual feature spaces into concepts that have human-level meaning. Second, learning the mapping/grounding between words and the extracted visual concepts. Third, inducing grammar rules via a semantic representation known as Robot Control Language (RCL). We evaluate our approach against state-of-the-art supervised and unsupervised grounding and grammar induction systems, and show that a robot can learn to execute never seen-before commands from pairs of unlabelled linguistic and visual inputs.
%R 10.18653/v1/W17-2805
%U https://aclanthology.org/W17-2805
%U https://doi.org/10.18653/v1/W17-2805
%P 35-43
Markdown (Informal)
[Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands](https://aclanthology.org/W17-2805) (Alomari et al., RoboNLP 2017)
ACL