@inproceedings{shen-etal-2017-deep,
title = "Deep Active Learning for Named Entity Recognition",
author = "Shen, Yanyao and
Yun, Hyokun and
Lipton, Zachary and
Kronrod, Yakov and
Anandkumar, Animashree",
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/W17-2630",
doi = "10.18653/v1/W17-2630",
pages = "252--256",
abstract = "Deep neural networks have advanced the state of the art in named entity recognition. However, under typical training procedures, advantages over classical methods emerge only with large datasets. As a result, deep learning is employed only when large public datasets or a large budget for manually labeling data is available. In this work, we show otherwise: by combining deep learning with active learning, we can outperform classical methods even with a significantly smaller amount of training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2017-deep">
<titleInfo>
<title>Deep Active Learning for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanyao</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyokun</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Lipton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yakov</namePart>
<namePart type="family">Kronrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animashree</namePart>
<namePart type="family">Anandkumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep neural networks have advanced the state of the art in named entity recognition. However, under typical training procedures, advantages over classical methods emerge only with large datasets. As a result, deep learning is employed only when large public datasets or a large budget for manually labeling data is available. In this work, we show otherwise: by combining deep learning with active learning, we can outperform classical methods even with a significantly smaller amount of training data.</abstract>
<identifier type="citekey">shen-etal-2017-deep</identifier>
<identifier type="doi">10.18653/v1/W17-2630</identifier>
<location>
<url>https://aclanthology.org/W17-2630</url>
</location>
<part>
<date>2017-aug</date>
<extent unit="page">
<start>252</start>
<end>256</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Active Learning for Named Entity Recognition
%A Shen, Yanyao
%A Yun, Hyokun
%A Lipton, Zachary
%A Kronrod, Yakov
%A Anandkumar, Animashree
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 aug
%I Association for Computational Linguistics
%C Vancouver, Canada
%F shen-etal-2017-deep
%X Deep neural networks have advanced the state of the art in named entity recognition. However, under typical training procedures, advantages over classical methods emerge only with large datasets. As a result, deep learning is employed only when large public datasets or a large budget for manually labeling data is available. In this work, we show otherwise: by combining deep learning with active learning, we can outperform classical methods even with a significantly smaller amount of training data.
%R 10.18653/v1/W17-2630
%U https://aclanthology.org/W17-2630
%U https://doi.org/10.18653/v1/W17-2630
%P 252-256
Markdown (Informal)
[Deep Active Learning for Named Entity Recognition](https://aclanthology.org/W17-2630) (Shen et al., 2017)
ACL
- Yanyao Shen, Hyokun Yun, Zachary Lipton, Yakov Kronrod, and Animashree Anandkumar. 2017. Deep Active Learning for Named Entity Recognition. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 252–256, Vancouver, Canada. Association for Computational Linguistics.