@inproceedings{wijnholds-moortgat-2021-sick,
title = "{SICK}-{NL}: A Dataset for {D}utch Natural Language Inference",
author = "Wijnholds, Gijs and
Moortgat, Michael",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.126/",
doi = "10.18653/v1/2021.eacl-main.126",
pages = "1474--1479",
abstract = "We present SICK-NL (read: signal), a dataset targeting Natural Language Inference in Dutch. SICK-NL is obtained by translating the SICK dataset of (Marelli et al., 2014) from English into Dutch. Having a parallel inference dataset allows us to compare both monolingual and multilingual NLP models for English and Dutch on the two tasks. In the paper, we motivate and detail the translation process, perform a baseline evaluation on both the original SICK dataset and its Dutch incarnation SICK-NL, taking inspiration from Dutch skipgram embeddings and contextualised embedding models. In addition, we encapsulate two phenomena encountered in the translation to formulate stress tests and verify how well the Dutch models capture syntactic restructurings that do not affect semantics. Our main finding is all models perform worse on SICK-NL than on SICK, indicating that the Dutch dataset is more challenging than the English original. Results on the stress tests show that models don`t fully capture word order freedom in Dutch, warranting future systematic studies."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wijnholds-moortgat-2021-sick">
<titleInfo>
<title>SICK-NL: A Dataset for Dutch Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gijs</namePart>
<namePart type="family">Wijnholds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Moortgat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>We present SICK-NL (read: signal), a dataset targeting Natural Language Inference in Dutch. SICK-NL is obtained by translating the SICK dataset of (Marelli et al., 2014) from English into Dutch. Having a parallel inference dataset allows us to compare both monolingual and multilingual NLP models for English and Dutch on the two tasks. In the paper, we motivate and detail the translation process, perform a baseline evaluation on both the original SICK dataset and its Dutch incarnation SICK-NL, taking inspiration from Dutch skipgram embeddings and contextualised embedding models. In addition, we encapsulate two phenomena encountered in the translation to formulate stress tests and verify how well the Dutch models capture syntactic restructurings that do not affect semantics. Our main finding is all models perform worse on SICK-NL than on SICK, indicating that the Dutch dataset is more challenging than the English original. Results on the stress tests show that models don‘t fully capture word order freedom in Dutch, warranting future systematic studies.</abstract>
<identifier type="citekey">wijnholds-moortgat-2021-sick</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.126</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.126/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1474</start>
<end>1479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SICK-NL: A Dataset for Dutch Natural Language Inference
%A Wijnholds, Gijs
%A Moortgat, Michael
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F wijnholds-moortgat-2021-sick
%X We present SICK-NL (read: signal), a dataset targeting Natural Language Inference in Dutch. SICK-NL is obtained by translating the SICK dataset of (Marelli et al., 2014) from English into Dutch. Having a parallel inference dataset allows us to compare both monolingual and multilingual NLP models for English and Dutch on the two tasks. In the paper, we motivate and detail the translation process, perform a baseline evaluation on both the original SICK dataset and its Dutch incarnation SICK-NL, taking inspiration from Dutch skipgram embeddings and contextualised embedding models. In addition, we encapsulate two phenomena encountered in the translation to formulate stress tests and verify how well the Dutch models capture syntactic restructurings that do not affect semantics. Our main finding is all models perform worse on SICK-NL than on SICK, indicating that the Dutch dataset is more challenging than the English original. Results on the stress tests show that models don‘t fully capture word order freedom in Dutch, warranting future systematic studies.
%R 10.18653/v1/2021.eacl-main.126
%U https://aclanthology.org/2021.eacl-main.126/
%U https://doi.org/10.18653/v1/2021.eacl-main.126
%P 1474-1479
Markdown (Informal)
[SICK-NL: A Dataset for Dutch Natural Language Inference](https://aclanthology.org/2021.eacl-main.126/) (Wijnholds & Moortgat, EACL 2021)
ACL
- Gijs Wijnholds and Michael Moortgat. 2021. SICK-NL: A Dataset for Dutch Natural Language Inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1474–1479, Online. Association for Computational Linguistics.