@inproceedings{kober-etal-2021-data,
title = "Data Augmentation for Hypernymy Detection",
author = "Kober, Thomas and
Weeds, Julie and
Bertolini, Lorenzo and
Weir, David",
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.89",
doi = "10.18653/v1/2021.eacl-main.89",
pages = "1034--1048",
abstract = "The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability of high quality training data. We have developed two novel data augmentation techniques which generate new training examples from existing ones. First, we combine the linguistic principles of hypernym transitivity and intersective modifier-noun composition to generate additional pairs of vectors, such as {``}small dog - dog{''} or {``}small dog - animal{''}, for which a hypernymy relationship can be assumed. Second, we use generative adversarial networks (GANs) to generate pairs of vectors for which the hypernymy relation can also be assumed. We furthermore present two complementary strategies for extending an existing dataset by leveraging linguistic resources such as WordNet. Using an evaluation across 3 different datasets for hypernymy detection and 2 different vector spaces, we demonstrate that both of the proposed automatic data augmentation and dataset extension strategies substantially improve classifier performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kober-etal-2021-data">
<titleInfo>
<title>Data Augmentation for Hypernymy Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Kober</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Weeds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Bertolini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Weir</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>The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability of high quality training data. We have developed two novel data augmentation techniques which generate new training examples from existing ones. First, we combine the linguistic principles of hypernym transitivity and intersective modifier-noun composition to generate additional pairs of vectors, such as “small dog - dog” or “small dog - animal”, for which a hypernymy relationship can be assumed. Second, we use generative adversarial networks (GANs) to generate pairs of vectors for which the hypernymy relation can also be assumed. We furthermore present two complementary strategies for extending an existing dataset by leveraging linguistic resources such as WordNet. Using an evaluation across 3 different datasets for hypernymy detection and 2 different vector spaces, we demonstrate that both of the proposed automatic data augmentation and dataset extension strategies substantially improve classifier performance.</abstract>
<identifier type="citekey">kober-etal-2021-data</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.89</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.89</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1034</start>
<end>1048</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Hypernymy Detection
%A Kober, Thomas
%A Weeds, Julie
%A Bertolini, Lorenzo
%A Weir, David
%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 kober-etal-2021-data
%X The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability of high quality training data. We have developed two novel data augmentation techniques which generate new training examples from existing ones. First, we combine the linguistic principles of hypernym transitivity and intersective modifier-noun composition to generate additional pairs of vectors, such as “small dog - dog” or “small dog - animal”, for which a hypernymy relationship can be assumed. Second, we use generative adversarial networks (GANs) to generate pairs of vectors for which the hypernymy relation can also be assumed. We furthermore present two complementary strategies for extending an existing dataset by leveraging linguistic resources such as WordNet. Using an evaluation across 3 different datasets for hypernymy detection and 2 different vector spaces, we demonstrate that both of the proposed automatic data augmentation and dataset extension strategies substantially improve classifier performance.
%R 10.18653/v1/2021.eacl-main.89
%U https://aclanthology.org/2021.eacl-main.89
%U https://doi.org/10.18653/v1/2021.eacl-main.89
%P 1034-1048
Markdown (Informal)
[Data Augmentation for Hypernymy Detection](https://aclanthology.org/2021.eacl-main.89) (Kober et al., EACL 2021)
ACL
- Thomas Kober, Julie Weeds, Lorenzo Bertolini, and David Weir. 2021. Data Augmentation for Hypernymy Detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1034–1048, Online. Association for Computational Linguistics.