@inproceedings{padmakumar-etal-2018-learning,
title = "Learning a Policy for Opportunistic Active Learning",
author = "Padmakumar, Aishwarya and
Stone, Peter and
Mooney, Raymond",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1165",
doi = "10.18653/v1/D18-1165",
pages = "1347--1357",
abstract = "Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="padmakumar-etal-2018-learning">
<titleInfo>
<title>Learning a Policy for Opportunistic Active Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Stone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="family">Mooney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.</abstract>
<identifier type="citekey">padmakumar-etal-2018-learning</identifier>
<identifier type="doi">10.18653/v1/D18-1165</identifier>
<location>
<url>https://aclanthology.org/D18-1165</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>1347</start>
<end>1357</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning a Policy for Opportunistic Active Learning
%A Padmakumar, Aishwarya
%A Stone, Peter
%A Mooney, Raymond
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F padmakumar-etal-2018-learning
%X Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.
%R 10.18653/v1/D18-1165
%U https://aclanthology.org/D18-1165
%U https://doi.org/10.18653/v1/D18-1165
%P 1347-1357
Markdown (Informal)
[Learning a Policy for Opportunistic Active Learning](https://aclanthology.org/D18-1165) (Padmakumar et al., EMNLP 2018)
ACL
- Aishwarya Padmakumar, Peter Stone, and Raymond Mooney. 2018. Learning a Policy for Opportunistic Active Learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1347–1357, Brussels, Belgium. Association for Computational Linguistics.