@article{kojima-etal-2021-continual,
title = "Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior",
author = "Kojima, Noriyuki and
Suhr, Alane and
Artzi, Yoav",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "9",
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.tacl-1.77",
doi = "10.1162/tacl_a_00428",
pages = "1303--1319",
abstract = "We study continual learning for natural language instruction generation, by observing human users{'} instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural language. We compare user execution of generated instructions to the original system intent as an indication to the system{'}s success communicating its intent. We show how to use this signal to improve the system{'}s ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kojima-etal-2021-continual">
<titleInfo>
<title>Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noriyuki</namePart>
<namePart type="family">Kojima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alane</namePart>
<namePart type="family">Suhr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Artzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We study continual learning for natural language instruction generation, by observing human users’ instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural language. We compare user execution of generated instructions to the original system intent as an indication to the system’s success communicating its intent. We show how to use this signal to improve the system’s ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.</abstract>
<identifier type="citekey">kojima-etal-2021-continual</identifier>
<identifier type="doi">10.1162/tacl_a_00428</identifier>
<location>
<url>https://aclanthology.org/2021.tacl-1.77</url>
</location>
<part>
<date>2021</date>
<detail type="volume"><number>9</number></detail>
<extent unit="page">
<start>1303</start>
<end>1319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior
%A Kojima, Noriyuki
%A Suhr, Alane
%A Artzi, Yoav
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F kojima-etal-2021-continual
%X We study continual learning for natural language instruction generation, by observing human users’ instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural language. We compare user execution of generated instructions to the original system intent as an indication to the system’s success communicating its intent. We show how to use this signal to improve the system’s ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.
%R 10.1162/tacl_a_00428
%U https://aclanthology.org/2021.tacl-1.77
%U https://doi.org/10.1162/tacl_a_00428
%P 1303-1319
Markdown (Informal)
[Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior](https://aclanthology.org/2021.tacl-1.77) (Kojima et al., TACL 2021)
ACL