@inproceedings{almeman-espinosa-anke-2025-gear,
title = "{GEAR}: A Simple {GENERATE}, {EMBED}, {AVERAGE} {AND} {RANK} Approach for Unsupervised Reverse Dictionary",
author = "Almeman, Fatemah Yousef and
Espinosa Anke, Luis",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.549/",
pages = "8242--8254",
abstract = "Reverse Dictionary (RD) is the task of obtaining the most relevant word or set of words given a textual description or dictionary definition. Effective RD methods have applications in accessibility, translation or writing support systems. Moreover, in NLP research we find RD to be used to benchmark text encoders at various granularities, as it often requires word, definition and sentence embeddings. In this paper, we propose a simple approach to RD that leverages LLMs in combination with embedding models. Despite its simplicity, this approach outperforms supervised baselines in well studied RD datasets, while also showing less overfitting. We also conduct a number of experiments on different dictionaries and analyze how different styles, registers and target audiences impact the quality of RD systems. We conclude that, on average, untuned embeddings alone fare way below an LLM-only baseline (although they are competitive in highly technical dictionaries), but are crucial for boosting performance in combined methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almeman-espinosa-anke-2025-gear">
<titleInfo>
<title>GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatemah</namePart>
<namePart type="given">Yousef</namePart>
<namePart type="family">Almeman</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>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reverse Dictionary (RD) is the task of obtaining the most relevant word or set of words given a textual description or dictionary definition. Effective RD methods have applications in accessibility, translation or writing support systems. Moreover, in NLP research we find RD to be used to benchmark text encoders at various granularities, as it often requires word, definition and sentence embeddings. In this paper, we propose a simple approach to RD that leverages LLMs in combination with embedding models. Despite its simplicity, this approach outperforms supervised baselines in well studied RD datasets, while also showing less overfitting. We also conduct a number of experiments on different dictionaries and analyze how different styles, registers and target audiences impact the quality of RD systems. We conclude that, on average, untuned embeddings alone fare way below an LLM-only baseline (although they are competitive in highly technical dictionaries), but are crucial for boosting performance in combined methods.</abstract>
<identifier type="citekey">almeman-espinosa-anke-2025-gear</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.549/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8242</start>
<end>8254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary
%A Almeman, Fatemah Yousef
%A Espinosa Anke, Luis
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F almeman-espinosa-anke-2025-gear
%X Reverse Dictionary (RD) is the task of obtaining the most relevant word or set of words given a textual description or dictionary definition. Effective RD methods have applications in accessibility, translation or writing support systems. Moreover, in NLP research we find RD to be used to benchmark text encoders at various granularities, as it often requires word, definition and sentence embeddings. In this paper, we propose a simple approach to RD that leverages LLMs in combination with embedding models. Despite its simplicity, this approach outperforms supervised baselines in well studied RD datasets, while also showing less overfitting. We also conduct a number of experiments on different dictionaries and analyze how different styles, registers and target audiences impact the quality of RD systems. We conclude that, on average, untuned embeddings alone fare way below an LLM-only baseline (although they are competitive in highly technical dictionaries), but are crucial for boosting performance in combined methods.
%U https://aclanthology.org/2025.coling-main.549/
%P 8242-8254
Markdown (Informal)
[GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary](https://aclanthology.org/2025.coling-main.549/) (Almeman & Espinosa Anke, COLING 2025)
ACL