@inproceedings{fusco-antognini-2023-extracting,
title = "Extracting Text Representations for Terms and Phrases in Technical Domains",
author = "Fusco, Francesco and
Antognini, Diego",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.7",
doi = "10.18653/v1/2023.acl-industry.7",
pages = "61--70",
abstract = "Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple applications ranging from ranking results in search to summarization. Common approaches to create dense representations include training domain-specific embeddings with self-supervised setups or using sentence encoder models trained over similarity tasks. In contrast to static embeddings, sentence encoders do not suffer from the out-of-vocabulary (OOV) problem, but impose significant computational costs. In this paper, we propose a fully unsupervised approach to text encoding that consists of training small character-based models with the objective of reconstructing large pre-trained embedding matrices. Models trained with this approach can not only match the quality of sentence encoders in technical domains, but are 5 times smaller and up to 10 times faster, even on high-end GPUs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fusco-antognini-2023-extracting">
<titleInfo>
<title>Extracting Text Representations for Terms and Phrases in Technical Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Fusco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Antognini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple applications ranging from ranking results in search to summarization. Common approaches to create dense representations include training domain-specific embeddings with self-supervised setups or using sentence encoder models trained over similarity tasks. In contrast to static embeddings, sentence encoders do not suffer from the out-of-vocabulary (OOV) problem, but impose significant computational costs. In this paper, we propose a fully unsupervised approach to text encoding that consists of training small character-based models with the objective of reconstructing large pre-trained embedding matrices. Models trained with this approach can not only match the quality of sentence encoders in technical domains, but are 5 times smaller and up to 10 times faster, even on high-end GPUs.</abstract>
<identifier type="citekey">fusco-antognini-2023-extracting</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.7</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.7</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>61</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting Text Representations for Terms and Phrases in Technical Domains
%A Fusco, Francesco
%A Antognini, Diego
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F fusco-antognini-2023-extracting
%X Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple applications ranging from ranking results in search to summarization. Common approaches to create dense representations include training domain-specific embeddings with self-supervised setups or using sentence encoder models trained over similarity tasks. In contrast to static embeddings, sentence encoders do not suffer from the out-of-vocabulary (OOV) problem, but impose significant computational costs. In this paper, we propose a fully unsupervised approach to text encoding that consists of training small character-based models with the objective of reconstructing large pre-trained embedding matrices. Models trained with this approach can not only match the quality of sentence encoders in technical domains, but are 5 times smaller and up to 10 times faster, even on high-end GPUs.
%R 10.18653/v1/2023.acl-industry.7
%U https://aclanthology.org/2023.acl-industry.7
%U https://doi.org/10.18653/v1/2023.acl-industry.7
%P 61-70
Markdown (Informal)
[Extracting Text Representations for Terms and Phrases in Technical Domains](https://aclanthology.org/2023.acl-industry.7) (Fusco & Antognini, ACL 2023)
ACL