@inproceedings{mortensen-etal-2022-hmong,
title = "A {H}mong Corpus with Elaborate Expression Annotations",
author = "Mortensen, David R. and
Zhang, Xinyu and
Cui, Chenxuan and
Zhang, Katherine J.",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.533",
pages = "4992--5000",
abstract = "This paper describes the first publicly available corpus of Hmong, a minority language of China, Vietnam, Laos, Thailand, and various countries in Europe and the Americas. The corpus has been scraped from a long-running Usenet newsgroup called soc.culture.hmong and consists of approximately 12 million tokens. This corpus (called SCH) is also the first substantial corpus to be annotated for elaborate expressions, a kind of four-part coordinate construction that is common and important in the languages of mainland Southeast Asia. We show that word embeddings trained on SCH can benefit tasks in Hmong (solving analogies) and that a model trained on it can label previously unseen elaborate expressions, in context, with an F1 of 90.79 (precision: 87.36, recall: 94.52). [ISO 639-3: mww, hmj]",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mortensen-etal-2022-hmong">
<titleInfo>
<title>A Hmong Corpus with Elaborate Expression Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Mortensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxuan</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the first publicly available corpus of Hmong, a minority language of China, Vietnam, Laos, Thailand, and various countries in Europe and the Americas. The corpus has been scraped from a long-running Usenet newsgroup called soc.culture.hmong and consists of approximately 12 million tokens. This corpus (called SCH) is also the first substantial corpus to be annotated for elaborate expressions, a kind of four-part coordinate construction that is common and important in the languages of mainland Southeast Asia. We show that word embeddings trained on SCH can benefit tasks in Hmong (solving analogies) and that a model trained on it can label previously unseen elaborate expressions, in context, with an F1 of 90.79 (precision: 87.36, recall: 94.52). [ISO 639-3: mww, hmj]</abstract>
<identifier type="citekey">mortensen-etal-2022-hmong</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.533</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4992</start>
<end>5000</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Hmong Corpus with Elaborate Expression Annotations
%A Mortensen, David R.
%A Zhang, Xinyu
%A Cui, Chenxuan
%A Zhang, Katherine J.
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F mortensen-etal-2022-hmong
%X This paper describes the first publicly available corpus of Hmong, a minority language of China, Vietnam, Laos, Thailand, and various countries in Europe and the Americas. The corpus has been scraped from a long-running Usenet newsgroup called soc.culture.hmong and consists of approximately 12 million tokens. This corpus (called SCH) is also the first substantial corpus to be annotated for elaborate expressions, a kind of four-part coordinate construction that is common and important in the languages of mainland Southeast Asia. We show that word embeddings trained on SCH can benefit tasks in Hmong (solving analogies) and that a model trained on it can label previously unseen elaborate expressions, in context, with an F1 of 90.79 (precision: 87.36, recall: 94.52). [ISO 639-3: mww, hmj]
%U https://aclanthology.org/2022.lrec-1.533
%P 4992-5000
Markdown (Informal)
[A Hmong Corpus with Elaborate Expression Annotations](https://aclanthology.org/2022.lrec-1.533) (Mortensen et al., LREC 2022)
ACL
- David R. Mortensen, Xinyu Zhang, Chenxuan Cui, and Katherine J. Zhang. 2022. A Hmong Corpus with Elaborate Expression Annotations. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4992–5000, Marseille, France. European Language Resources Association.