@inproceedings{siddhant-lipton-2018-deep,
title = "Deep {B}ayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study",
author = "Siddhant, Aditya and
Lipton, Zachary C.",
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/D18-1318",
doi = "10.18653/v1/D18-1318",
pages = "2904--2909",
abstract = "Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, we have no opportunity to compare models and acquisition functions. This paper provides a large-scale empirical study of deep active learning, addressing multiple tasks and, for each, multiple datasets, multiple models, and a full suite of acquisition functions. We find that across all settings, Bayesian active learning by disagreement, using uncertainty estimates provided either by Dropout or Bayes-by-Backprop significantly improves over i.i.d. baselines and usually outperforms classic uncertainty sampling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siddhant-lipton-2018-deep">
<titleInfo>
<title>Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Siddhant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Lipton</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>Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, we have no opportunity to compare models and acquisition functions. This paper provides a large-scale empirical study of deep active learning, addressing multiple tasks and, for each, multiple datasets, multiple models, and a full suite of acquisition functions. We find that across all settings, Bayesian active learning by disagreement, using uncertainty estimates provided either by Dropout or Bayes-by-Backprop significantly improves over i.i.d. baselines and usually outperforms classic uncertainty sampling.</abstract>
<identifier type="citekey">siddhant-lipton-2018-deep</identifier>
<identifier type="doi">10.18653/v1/D18-1318</identifier>
<location>
<url>https://aclanthology.org/D18-1318</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>2904</start>
<end>2909</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study
%A Siddhant, Aditya
%A Lipton, Zachary C.
%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 siddhant-lipton-2018-deep
%X Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each against a validation set before selecting a model, AL affords no such luxury. Over the course of one AL run, an agent annotates its dataset exhausting its labeling budget. Thus, given a new task, we have no opportunity to compare models and acquisition functions. This paper provides a large-scale empirical study of deep active learning, addressing multiple tasks and, for each, multiple datasets, multiple models, and a full suite of acquisition functions. We find that across all settings, Bayesian active learning by disagreement, using uncertainty estimates provided either by Dropout or Bayes-by-Backprop significantly improves over i.i.d. baselines and usually outperforms classic uncertainty sampling.
%R 10.18653/v1/D18-1318
%U https://aclanthology.org/D18-1318
%U https://doi.org/10.18653/v1/D18-1318
%P 2904-2909
Markdown (Informal)
[Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study](https://aclanthology.org/D18-1318) (Siddhant & Lipton, EMNLP 2018)
ACL