@inproceedings{gajbhiye-etal-2024-amended,
title = "{AM}en{D}e{D}: Modelling Concepts by Aligning Mentions, Definitions and Decontextualised Embeddings",
author = "Gajbhiye, Amit and
Bouraoui, Zied and
Espinosa Anke, Luis and
Schockaert, Steven",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.72",
pages = "801--811",
abstract = "Contextualised Language Models (LM) improve on traditional word embeddings by encoding the meaning of words in context. However, such models have also made it possible to learn high-quality decontextualised concept embeddings. Three main strategies for learning such embeddings have thus far been considered: (i) fine-tuning the LM to directly predict concept embeddings from the name of the concept itself, (ii) averaging contextualised representations of mentions of the concept in a corpus, and (iii) encoding definitions of the concept. As these strategies have complementary strengths and weaknesses, we propose to learn a unified embedding space in which all three types of representations can be integrated. We show that this allows us to outperform existing approaches in tasks such as ontology completion, which heavily depends on access to high-quality concept embeddings. We furthermore find that mentions and definitions are well-aligned in the resulting space, enabling tasks such as target sense verification, even without the need for any fine-tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gajbhiye-etal-2024-amended">
<titleInfo>
<title>AMenDeD: Modelling Concepts by Aligning Mentions, Definitions and Decontextualised Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Gajbhiye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zied</namePart>
<namePart type="family">Bouraoui</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>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Contextualised Language Models (LM) improve on traditional word embeddings by encoding the meaning of words in context. However, such models have also made it possible to learn high-quality decontextualised concept embeddings. Three main strategies for learning such embeddings have thus far been considered: (i) fine-tuning the LM to directly predict concept embeddings from the name of the concept itself, (ii) averaging contextualised representations of mentions of the concept in a corpus, and (iii) encoding definitions of the concept. As these strategies have complementary strengths and weaknesses, we propose to learn a unified embedding space in which all three types of representations can be integrated. We show that this allows us to outperform existing approaches in tasks such as ontology completion, which heavily depends on access to high-quality concept embeddings. We furthermore find that mentions and definitions are well-aligned in the resulting space, enabling tasks such as target sense verification, even without the need for any fine-tuning.</abstract>
<identifier type="citekey">gajbhiye-etal-2024-amended</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.72</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>801</start>
<end>811</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AMenDeD: Modelling Concepts by Aligning Mentions, Definitions and Decontextualised Embeddings
%A Gajbhiye, Amit
%A Bouraoui, Zied
%A Espinosa Anke, Luis
%A Schockaert, Steven
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F gajbhiye-etal-2024-amended
%X Contextualised Language Models (LM) improve on traditional word embeddings by encoding the meaning of words in context. However, such models have also made it possible to learn high-quality decontextualised concept embeddings. Three main strategies for learning such embeddings have thus far been considered: (i) fine-tuning the LM to directly predict concept embeddings from the name of the concept itself, (ii) averaging contextualised representations of mentions of the concept in a corpus, and (iii) encoding definitions of the concept. As these strategies have complementary strengths and weaknesses, we propose to learn a unified embedding space in which all three types of representations can be integrated. We show that this allows us to outperform existing approaches in tasks such as ontology completion, which heavily depends on access to high-quality concept embeddings. We furthermore find that mentions and definitions are well-aligned in the resulting space, enabling tasks such as target sense verification, even without the need for any fine-tuning.
%U https://aclanthology.org/2024.lrec-main.72
%P 801-811
Markdown (Informal)
[AMenDeD: Modelling Concepts by Aligning Mentions, Definitions and Decontextualised Embeddings](https://aclanthology.org/2024.lrec-main.72) (Gajbhiye et al., LREC-COLING 2024)
ACL