@inproceedings{almeman-etal-2023-3d,
title = "3{D}-{EX}: A Unified Dataset of Definitions and Dictionary Examples",
author = "Almeman, Fatemah and
Sheikhi, Hadi and
Espinosa Anke, Luis",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.8",
pages = "69--79",
abstract = "Definitions are a fundamental building block in lexicography, linguistics and computational semantics. In NLP, they have been used for retrofitting word embeddings or augmenting contextual representations in language models. However, lexical resources containing definitions exhibit a wide range of properties, which has implications in the behaviour of models trained and evaluated on them. In this paper, we introduce 3D-EX, a dataset that aims to fill this gap by combining well-known English resources into one centralized knowledge repository in the form of {\textless}term, definition, example{\textgreater} triples. 3D-EX is a unified evaluation framework with carefully pre-computed train/validation/test splits to prevent memorization. We report experimental results that suggest that this dataset could be effectively leveraged in downstream NLP tasks. Code and data are available at https://github.com/F-Almeman/3D-EX.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almeman-etal-2023-3d">
<titleInfo>
<title>3D-EX: A Unified Dataset of Definitions and Dictionary Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatemah</namePart>
<namePart type="family">Almeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hadi</namePart>
<namePart type="family">Sheikhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Espinosa Anke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Definitions are a fundamental building block in lexicography, linguistics and computational semantics. In NLP, they have been used for retrofitting word embeddings or augmenting contextual representations in language models. However, lexical resources containing definitions exhibit a wide range of properties, which has implications in the behaviour of models trained and evaluated on them. In this paper, we introduce 3D-EX, a dataset that aims to fill this gap by combining well-known English resources into one centralized knowledge repository in the form of \textlessterm, definition, example\textgreater triples. 3D-EX is a unified evaluation framework with carefully pre-computed train/validation/test splits to prevent memorization. We report experimental results that suggest that this dataset could be effectively leveraged in downstream NLP tasks. Code and data are available at https://github.com/F-Almeman/3D-EX.</abstract>
<identifier type="citekey">almeman-etal-2023-3d</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.8</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>69</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 3D-EX: A Unified Dataset of Definitions and Dictionary Examples
%A Almeman, Fatemah
%A Sheikhi, Hadi
%A Espinosa Anke, Luis
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F almeman-etal-2023-3d
%X Definitions are a fundamental building block in lexicography, linguistics and computational semantics. In NLP, they have been used for retrofitting word embeddings or augmenting contextual representations in language models. However, lexical resources containing definitions exhibit a wide range of properties, which has implications in the behaviour of models trained and evaluated on them. In this paper, we introduce 3D-EX, a dataset that aims to fill this gap by combining well-known English resources into one centralized knowledge repository in the form of \textlessterm, definition, example\textgreater triples. 3D-EX is a unified evaluation framework with carefully pre-computed train/validation/test splits to prevent memorization. We report experimental results that suggest that this dataset could be effectively leveraged in downstream NLP tasks. Code and data are available at https://github.com/F-Almeman/3D-EX.
%U https://aclanthology.org/2023.ranlp-1.8
%P 69-79
Markdown (Informal)
[3D-EX: A Unified Dataset of Definitions and Dictionary Examples](https://aclanthology.org/2023.ranlp-1.8) (Almeman et al., RANLP 2023)
ACL