@inproceedings{huynh-etal-2022-vinli,
title = "{V}i{NLI}: A {V}ietnamese Corpus for Studies on Open-Domain Natural Language Inference",
author = "Huynh, Tin Van and
Nguyen, Kiet Van and
Nguyen, Ngan Luu-Thuy",
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-1.339",
pages = "3858--3872",
abstract = "Over a decade, the research field of computational linguistics has witnessed the growth of corpora and models for natural language inference (NLI) for rich-resource languages such as English and Chinese. A large-scale and high-quality corpus is necessary for studies on NLI for Vietnamese, which can be considered a low-resource language. In this paper, we introduce ViNLI (Vietnamese Natural Language Inference), an open-domain and high-quality corpus for evaluating Vietnamese NLI models, which is created and evaluated with a strict process of quality control. ViNLI comprises over 30,000 human-annotated premise-hypothesis sentence pairs extracted from more than 800 online news articles on 13 distinct topics. In this paper, we introduce the guidelines for corpus creation which take the specific characteristics of the Vietnamese language in expressing entailment and contradiction into account. To evaluate the challenging level of our corpus, we conduct experiments with state-of-the-art deep neural networks and pre-trained models on our dataset. The best system performance is still far from human performance (a 14.20{\%} gap in accuracy). The ViNLI corpus is a challenging corpus to accelerate progress in Vietnamese computational linguistics. Our corpus is available publicly for research purposes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huynh-etal-2022-vinli">
<titleInfo>
<title>ViNLI: A Vietnamese Corpus for Studies on Open-Domain Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tin</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Huynh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiet</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngan</namePart>
<namePart type="given">Luu-Thuy</namePart>
<namePart type="family">Nguyen</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>Over a decade, the research field of computational linguistics has witnessed the growth of corpora and models for natural language inference (NLI) for rich-resource languages such as English and Chinese. A large-scale and high-quality corpus is necessary for studies on NLI for Vietnamese, which can be considered a low-resource language. In this paper, we introduce ViNLI (Vietnamese Natural Language Inference), an open-domain and high-quality corpus for evaluating Vietnamese NLI models, which is created and evaluated with a strict process of quality control. ViNLI comprises over 30,000 human-annotated premise-hypothesis sentence pairs extracted from more than 800 online news articles on 13 distinct topics. In this paper, we introduce the guidelines for corpus creation which take the specific characteristics of the Vietnamese language in expressing entailment and contradiction into account. To evaluate the challenging level of our corpus, we conduct experiments with state-of-the-art deep neural networks and pre-trained models on our dataset. The best system performance is still far from human performance (a 14.20% gap in accuracy). The ViNLI corpus is a challenging corpus to accelerate progress in Vietnamese computational linguistics. Our corpus is available publicly for research purposes.</abstract>
<identifier type="citekey">huynh-etal-2022-vinli</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.339</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3858</start>
<end>3872</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ViNLI: A Vietnamese Corpus for Studies on Open-Domain Natural Language Inference
%A Huynh, Tin Van
%A Nguyen, Kiet Van
%A Nguyen, Ngan Luu-Thuy
%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 huynh-etal-2022-vinli
%X Over a decade, the research field of computational linguistics has witnessed the growth of corpora and models for natural language inference (NLI) for rich-resource languages such as English and Chinese. A large-scale and high-quality corpus is necessary for studies on NLI for Vietnamese, which can be considered a low-resource language. In this paper, we introduce ViNLI (Vietnamese Natural Language Inference), an open-domain and high-quality corpus for evaluating Vietnamese NLI models, which is created and evaluated with a strict process of quality control. ViNLI comprises over 30,000 human-annotated premise-hypothesis sentence pairs extracted from more than 800 online news articles on 13 distinct topics. In this paper, we introduce the guidelines for corpus creation which take the specific characteristics of the Vietnamese language in expressing entailment and contradiction into account. To evaluate the challenging level of our corpus, we conduct experiments with state-of-the-art deep neural networks and pre-trained models on our dataset. The best system performance is still far from human performance (a 14.20% gap in accuracy). The ViNLI corpus is a challenging corpus to accelerate progress in Vietnamese computational linguistics. Our corpus is available publicly for research purposes.
%U https://aclanthology.org/2022.coling-1.339
%P 3858-3872
Markdown (Informal)
[ViNLI: A Vietnamese Corpus for Studies on Open-Domain Natural Language Inference](https://aclanthology.org/2022.coling-1.339) (Huynh et al., COLING 2022)
ACL