@inproceedings{lobov-etal-2022-applying,
title = "Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages",
author = "Lobov, Valeriy and
Ivoylova, Alexandra and
Sharoff, Serge",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.394",
pages = "4468--4480",
abstract = "Current practices in building new NLP models for low-resourced languages rely either on Machine Translation of training sets from better resourced languages or on cross-lingual transfer from them. Still we can see a considerable performance gap between the models originally trained within better resourced languages and the models transferred from them. In this study we test the possibility of (1) using natural annotation to build synthetic training sets from resources not initially designed for the target downstream task and (2) employing curriculum learning methods to select the most suitable examples from synthetic training sets. We test this hypothesis across seven Slavic languages and across three curriculum learning strategies on Named Entity Recognition as the downstream task. We also test the possibility of fine-tuning the synthetic resources to reflect linguistic properties, such as the grammatical case and gender, both of which are important for the Slavic languages. We demonstrate the possibility to achieve the mean F1 score of 0.78 across the three basic entities types for Belarusian starting from zero resources in comparison to the baseline of 0.63 using the zero-shot transfer from English. For comparison, the English model trained on the original set achieves the mean F1-score of 0.75. The experimental results are available from \url{https://github.com/ValeraLobov/SlavNER}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lobov-etal-2022-applying">
<titleInfo>
<title>Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valeriy</namePart>
<namePart type="family">Lobov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Ivoylova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</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>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current practices in building new NLP models for low-resourced languages rely either on Machine Translation of training sets from better resourced languages or on cross-lingual transfer from them. Still we can see a considerable performance gap between the models originally trained within better resourced languages and the models transferred from them. In this study we test the possibility of (1) using natural annotation to build synthetic training sets from resources not initially designed for the target downstream task and (2) employing curriculum learning methods to select the most suitable examples from synthetic training sets. We test this hypothesis across seven Slavic languages and across three curriculum learning strategies on Named Entity Recognition as the downstream task. We also test the possibility of fine-tuning the synthetic resources to reflect linguistic properties, such as the grammatical case and gender, both of which are important for the Slavic languages. We demonstrate the possibility to achieve the mean F1 score of 0.78 across the three basic entities types for Belarusian starting from zero resources in comparison to the baseline of 0.63 using the zero-shot transfer from English. For comparison, the English model trained on the original set achieves the mean F1-score of 0.75. The experimental results are available from https://github.com/ValeraLobov/SlavNER</abstract>
<identifier type="citekey">lobov-etal-2022-applying</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.394</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4468</start>
<end>4480</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages
%A Lobov, Valeriy
%A Ivoylova, Alexandra
%A Sharoff, Serge
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F lobov-etal-2022-applying
%X Current practices in building new NLP models for low-resourced languages rely either on Machine Translation of training sets from better resourced languages or on cross-lingual transfer from them. Still we can see a considerable performance gap between the models originally trained within better resourced languages and the models transferred from them. In this study we test the possibility of (1) using natural annotation to build synthetic training sets from resources not initially designed for the target downstream task and (2) employing curriculum learning methods to select the most suitable examples from synthetic training sets. We test this hypothesis across seven Slavic languages and across three curriculum learning strategies on Named Entity Recognition as the downstream task. We also test the possibility of fine-tuning the synthetic resources to reflect linguistic properties, such as the grammatical case and gender, both of which are important for the Slavic languages. We demonstrate the possibility to achieve the mean F1 score of 0.78 across the three basic entities types for Belarusian starting from zero resources in comparison to the baseline of 0.63 using the zero-shot transfer from English. For comparison, the English model trained on the original set achieves the mean F1-score of 0.75. The experimental results are available from https://github.com/ValeraLobov/SlavNER
%U https://aclanthology.org/2022.coling-1.394
%P 4468-4480
Markdown (Informal)
[Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages](https://aclanthology.org/2022.coling-1.394) (Lobov et al., COLING 2022)
ACL