@inproceedings{shelmanov-etal-2021-active,
title = "Active Learning for Sequence Tagging with Deep Pre-trained Models and {B}ayesian Uncertainty Estimates",
author = "Shelmanov, Artem and
Puzyrev, Dmitri and
Kupriyanova, Lyubov and
Belyakov, Denis and
Larionov, Daniil and
Khromov, Nikita and
Kozlova, Olga and
Artemova, Ekaterina and
Dylov, Dmitry V. and
Panchenko, Alexander",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.145",
doi = "10.18653/v1/2021.eacl-main.145",
pages = "1698--1712",
abstract = "Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We are the first to thoroughly investigate this powerful combination for the sequence tagging task. We conduct an extensive empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework and find the best combinations for different types of models. Besides, we also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance and reduces obstacles for applying deep active learning in practice.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shelmanov-etal-2021-active">
<titleInfo>
<title>Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitri</namePart>
<namePart type="family">Puzyrev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyubov</namePart>
<namePart type="family">Kupriyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Belyakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Larionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Khromov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kozlova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Dylov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We are the first to thoroughly investigate this powerful combination for the sequence tagging task. We conduct an extensive empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework and find the best combinations for different types of models. Besides, we also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance and reduces obstacles for applying deep active learning in practice.</abstract>
<identifier type="citekey">shelmanov-etal-2021-active</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.145</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.145</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1698</start>
<end>1712</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates
%A Shelmanov, Artem
%A Puzyrev, Dmitri
%A Kupriyanova, Lyubov
%A Belyakov, Denis
%A Larionov, Daniil
%A Khromov, Nikita
%A Kozlova, Olga
%A Artemova, Ekaterina
%A Dylov, Dmitry V.
%A Panchenko, Alexander
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F shelmanov-etal-2021-active
%X Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We are the first to thoroughly investigate this powerful combination for the sequence tagging task. We conduct an extensive empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework and find the best combinations for different types of models. Besides, we also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance and reduces obstacles for applying deep active learning in practice.
%R 10.18653/v1/2021.eacl-main.145
%U https://aclanthology.org/2021.eacl-main.145
%U https://doi.org/10.18653/v1/2021.eacl-main.145
%P 1698-1712
Markdown (Informal)
[Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates](https://aclanthology.org/2021.eacl-main.145) (Shelmanov et al., EACL 2021)
ACL
- Artem Shelmanov, Dmitri Puzyrev, Lyubov Kupriyanova, Denis Belyakov, Daniil Larionov, Nikita Khromov, Olga Kozlova, Ekaterina Artemova, Dmitry V. Dylov, and Alexander Panchenko. 2021. Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1698–1712, Online. Association for Computational Linguistics.