@inproceedings{vacareanu-etal-2024-active,
title = "Active Learning Design Choices for {NER} with Transformers",
author = "Vacareanu, Robert and
Noriega-Atala, Enrique and
Hahn-Powell, Gus and
Valenzuela-Escarcega, Marco A. and
Surdeanu, Mihai",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.30/",
pages = "321--334",
abstract = "We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vacareanu-etal-2024-active">
<titleInfo>
<title>Active Learning Design Choices for NER with Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Vacareanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gus</namePart>
<namePart type="family">Hahn-Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Valenzuela-Escarcega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly.</abstract>
<identifier type="citekey">vacareanu-etal-2024-active</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.30/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>321</start>
<end>334</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Active Learning Design Choices for NER with Transformers
%A Vacareanu, Robert
%A Noriega-Atala, Enrique
%A Hahn-Powell, Gus
%A Valenzuela-Escarcega, Marco A.
%A Surdeanu, Mihai
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F vacareanu-etal-2024-active
%X We explore multiple important choices that have not been analyzed in conjunction regarding active learning for token classification using transformer networks. These choices are: (i) how to select what to annotate, (ii) decide whether to annotate entire sentences or smaller sentence fragments, (iii) how to train with incomplete annotations at token-level, and (iv) how to select the initial seed dataset. We explore whether annotating at sub-sentence level can translate to an improved downstream performance by considering two different sub-sentence annotation strategies: (i) entity-level, and (ii) token-level. These approaches result in some sentences being only partially annotated. To address this issue, we introduce and evaluate multiple strategies to deal with partially-annotated sentences during the training process. We show that annotating at the sub-sentence level achieves comparable or better performance than sentence-level annotations with a smaller number of annotated tokens. We then explore the extent to which the performance gap remains once accounting for the annotation time and found that both annotation schemes perform similarly.
%U https://aclanthology.org/2024.lrec-main.30/
%P 321-334
Markdown (Informal)
[Active Learning Design Choices for NER with Transformers](https://aclanthology.org/2024.lrec-main.30/) (Vacareanu et al., LREC-COLING 2024)
ACL
- Robert Vacareanu, Enrique Noriega-Atala, Gus Hahn-Powell, Marco A. Valenzuela-Escarcega, and Mihai Surdeanu. 2024. Active Learning Design Choices for NER with Transformers. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 321–334, Torino, Italia. ELRA and ICCL.