@inproceedings{kim-etal-2021-analysis,
title = "Analysis of Zero-Shot Crosslingual Learning between {E}nglish and {K}orean for Named Entity Recognition",
author = "Kim, Jongin and
Choi, Nayoung and
Lim, Seunghyun and
Kim, Jungwhan and
Chung, Soojin and
Woo, Hyunsoo and
Song, Min and
Choi, Jinho D.",
editor = "Ataman, Duygu and
Birch, Alexandra and
Conneau, Alexis and
Firat, Orhan and
Ruder, Sebastian and
Sahin, Gozde Gul",
booktitle = "Proceedings of the 1st Workshop on Multilingual Representation Learning",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrl-1.19",
doi = "10.18653/v1/2021.mrl-1.19",
pages = "224--237",
abstract = "This paper presents a English-Korean parallel dataset that collects 381K news articles where 1,400 of them, comprising 10K sentences, are manually labeled for crosslingual named entity recognition (NER). The annotation guidelines for the two languages are developed in parallel, that yield the inter-annotator agreement scores of 91 and 88{\%} for English and Korean respectively, indicating sublime quality annotation in our dataset. Three types of crosslingual learning approaches, direct model transfer, embedding projection, and annotation projection, are used to develop zero-shot Korean NER models. Our best model gives the F1-score of 51{\%} that is very encouraging, considering the extremely distinct natures of these two languages. This is pioneering work that explores zero-shot cross-lingual learning between English and Korean and provides rich parallel annotation for a core NLP task such as named entity recognition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2021-analysis">
<titleInfo>
<title>Analysis of Zero-Shot Crosslingual Learning between English and Korean for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jongin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nayoung</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seunghyun</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungwhan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soojin</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunsoo</namePart>
<namePart type="family">Woo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multilingual Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orhan</namePart>
<namePart type="family">Firat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gozde</namePart>
<namePart type="given">Gul</namePart>
<namePart type="family">Sahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a English-Korean parallel dataset that collects 381K news articles where 1,400 of them, comprising 10K sentences, are manually labeled for crosslingual named entity recognition (NER). The annotation guidelines for the two languages are developed in parallel, that yield the inter-annotator agreement scores of 91 and 88% for English and Korean respectively, indicating sublime quality annotation in our dataset. Three types of crosslingual learning approaches, direct model transfer, embedding projection, and annotation projection, are used to develop zero-shot Korean NER models. Our best model gives the F1-score of 51% that is very encouraging, considering the extremely distinct natures of these two languages. This is pioneering work that explores zero-shot cross-lingual learning between English and Korean and provides rich parallel annotation for a core NLP task such as named entity recognition.</abstract>
<identifier type="citekey">kim-etal-2021-analysis</identifier>
<identifier type="doi">10.18653/v1/2021.mrl-1.19</identifier>
<location>
<url>https://aclanthology.org/2021.mrl-1.19</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>224</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analysis of Zero-Shot Crosslingual Learning between English and Korean for Named Entity Recognition
%A Kim, Jongin
%A Choi, Nayoung
%A Lim, Seunghyun
%A Kim, Jungwhan
%A Chung, Soojin
%A Woo, Hyunsoo
%A Song, Min
%A Choi, Jinho D.
%Y Ataman, Duygu
%Y Birch, Alexandra
%Y Conneau, Alexis
%Y Firat, Orhan
%Y Ruder, Sebastian
%Y Sahin, Gozde Gul
%S Proceedings of the 1st Workshop on Multilingual Representation Learning
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F kim-etal-2021-analysis
%X This paper presents a English-Korean parallel dataset that collects 381K news articles where 1,400 of them, comprising 10K sentences, are manually labeled for crosslingual named entity recognition (NER). The annotation guidelines for the two languages are developed in parallel, that yield the inter-annotator agreement scores of 91 and 88% for English and Korean respectively, indicating sublime quality annotation in our dataset. Three types of crosslingual learning approaches, direct model transfer, embedding projection, and annotation projection, are used to develop zero-shot Korean NER models. Our best model gives the F1-score of 51% that is very encouraging, considering the extremely distinct natures of these two languages. This is pioneering work that explores zero-shot cross-lingual learning between English and Korean and provides rich parallel annotation for a core NLP task such as named entity recognition.
%R 10.18653/v1/2021.mrl-1.19
%U https://aclanthology.org/2021.mrl-1.19
%U https://doi.org/10.18653/v1/2021.mrl-1.19
%P 224-237
Markdown (Informal)
[Analysis of Zero-Shot Crosslingual Learning between English and Korean for Named Entity Recognition](https://aclanthology.org/2021.mrl-1.19) (Kim et al., MRL 2021)
ACL
- Jongin Kim, Nayoung Choi, Seunghyun Lim, Jungwhan Kim, Soojin Chung, Hyunsoo Woo, Min Song, and Jinho D. Choi. 2021. Analysis of Zero-Shot Crosslingual Learning between English and Korean for Named Entity Recognition. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 224–237, Punta Cana, Dominican Republic. Association for Computational Linguistics.