@inproceedings{johansen-socher-2017-learning,
title = "Learning when to skim and when to read",
author = "Johansen, Alexander and
Socher, Richard",
editor = "Blunsom, Phil and
Bordes, Antoine and
Cho, Kyunghyun and
Cohen, Shay and
Dyer, Chris and
Grefenstette, Edward and
Hermann, Karl Moritz and
Rimell, Laura and
Weston, Jason and
Yih, Scott",
booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2631",
doi = "10.18653/v1/W17-2631",
pages = "257--264",
abstract = "Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for every example in a dataset. We demonstrate two approaches to reducing unnecessary computation in cases where a fast but weak baseline classier and a stronger, slower model are both available. Applying an AUC-based metric to the task of sentiment classification, we find significant efficiency gains with both a probability-threshold method for reducing computational cost and one that uses a secondary decision network.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johansen-socher-2017-learning">
<titleInfo>
<title>Learning when to skim and when to read</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Johansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Socher</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 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bordes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="given">Moritz</namePart>
<namePart type="family">Hermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rimell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Weston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Yih</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>Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for every example in a dataset. We demonstrate two approaches to reducing unnecessary computation in cases where a fast but weak baseline classier and a stronger, slower model are both available. Applying an AUC-based metric to the task of sentiment classification, we find significant efficiency gains with both a probability-threshold method for reducing computational cost and one that uses a secondary decision network.</abstract>
<identifier type="citekey">johansen-socher-2017-learning</identifier>
<identifier type="doi">10.18653/v1/W17-2631</identifier>
<location>
<url>https://aclanthology.org/W17-2631</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>257</start>
<end>264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning when to skim and when to read
%A Johansen, Alexander
%A Socher, Richard
%Y Blunsom, Phil
%Y Bordes, Antoine
%Y Cho, Kyunghyun
%Y Cohen, Shay
%Y Dyer, Chris
%Y Grefenstette, Edward
%Y Hermann, Karl Moritz
%Y Rimell, Laura
%Y Weston, Jason
%Y Yih, Scott
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F johansen-socher-2017-learning
%X Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for every example in a dataset. We demonstrate two approaches to reducing unnecessary computation in cases where a fast but weak baseline classier and a stronger, slower model are both available. Applying an AUC-based metric to the task of sentiment classification, we find significant efficiency gains with both a probability-threshold method for reducing computational cost and one that uses a secondary decision network.
%R 10.18653/v1/W17-2631
%U https://aclanthology.org/W17-2631
%U https://doi.org/10.18653/v1/W17-2631
%P 257-264
Markdown (Informal)
[Learning when to skim and when to read](https://aclanthology.org/W17-2631) (Johansen & Socher, RepL4NLP 2017)
ACL
- Alexander Johansen and Richard Socher. 2017. Learning when to skim and when to read. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 257–264, Vancouver, Canada. Association for Computational Linguistics.