@inproceedings{hu-etal-2020-ocnli,
title = "{OCNLI}: {O}riginal {C}hinese {N}atural {L}anguage {I}nference",
author = {Hu, Hai and
Richardson, Kyle and
Xu, Liang and
Li, Lu and
K{\"u}bler, Sandra and
Moss, Lawrence},
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.314",
doi = "10.18653/v1/2020.findings-emnlp.314",
pages = "3512--3526",
abstract = "Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g.,SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world{'}s languages. In this paper, we present the first large-scale NLI dataset (consisting of {\textasciitilde}56,000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI). Unlike recent attempts at extending NLI to other languages, our dataset does not rely on any automatic translation or non-expert annotation. Instead, we elicit annotations from native speakers specializing in linguistics. We follow closely the annotation protocol used for MNLI, but create new strategies for eliciting diverse hypotheses. We establish several baseline results on our dataset using state-of-the-art pre-trained models for Chinese, and find even the best performing models to be far outpaced by human performance ({\textasciitilde}12{\%} absolute performance gap), making it a challenging new resource that we hope will help to accelerate progress in Chinese NLU. To the best of our knowledge, this is the first human-elicited MNLI-style corpus for a non-English language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2020-ocnli">
<titleInfo>
<title>OCNLI: Original Chinese Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Moss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g.,SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world’s languages. In this paper, we present the first large-scale NLI dataset (consisting of ~56,000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI). Unlike recent attempts at extending NLI to other languages, our dataset does not rely on any automatic translation or non-expert annotation. Instead, we elicit annotations from native speakers specializing in linguistics. We follow closely the annotation protocol used for MNLI, but create new strategies for eliciting diverse hypotheses. We establish several baseline results on our dataset using state-of-the-art pre-trained models for Chinese, and find even the best performing models to be far outpaced by human performance (~12% absolute performance gap), making it a challenging new resource that we hope will help to accelerate progress in Chinese NLU. To the best of our knowledge, this is the first human-elicited MNLI-style corpus for a non-English language.</abstract>
<identifier type="citekey">hu-etal-2020-ocnli</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.314</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.314</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3512</start>
<end>3526</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OCNLI: Original Chinese Natural Language Inference
%A Hu, Hai
%A Richardson, Kyle
%A Xu, Liang
%A Li, Lu
%A Kübler, Sandra
%A Moss, Lawrence
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F hu-etal-2020-ocnli
%X Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g.,SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world’s languages. In this paper, we present the first large-scale NLI dataset (consisting of ~56,000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI). Unlike recent attempts at extending NLI to other languages, our dataset does not rely on any automatic translation or non-expert annotation. Instead, we elicit annotations from native speakers specializing in linguistics. We follow closely the annotation protocol used for MNLI, but create new strategies for eliciting diverse hypotheses. We establish several baseline results on our dataset using state-of-the-art pre-trained models for Chinese, and find even the best performing models to be far outpaced by human performance (~12% absolute performance gap), making it a challenging new resource that we hope will help to accelerate progress in Chinese NLU. To the best of our knowledge, this is the first human-elicited MNLI-style corpus for a non-English language.
%R 10.18653/v1/2020.findings-emnlp.314
%U https://aclanthology.org/2020.findings-emnlp.314
%U https://doi.org/10.18653/v1/2020.findings-emnlp.314
%P 3512-3526
Markdown (Informal)
[OCNLI: Original Chinese Natural Language Inference](https://aclanthology.org/2020.findings-emnlp.314) (Hu et al., Findings 2020)
ACL
- Hai Hu, Kyle Richardson, Liang Xu, Lu Li, Sandra Kübler, and Lawrence Moss. 2020. OCNLI: Original Chinese Natural Language Inference. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3512–3526, Online. Association for Computational Linguistics.