@inproceedings{gee-etal-2022-fast,
title = "Fast Vocabulary Transfer for Language Model Compression",
author = "Gee, Leonidas and
Zugarini, Andrea and
Rigutini, Leonardo and
Torroni, Paolo",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.41",
doi = "10.18653/v1/2022.emnlp-industry.41",
pages = "409--416",
abstract = "Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gee-etal-2022-fast">
<titleInfo>
<title>Fast Vocabulary Transfer for Language Model Compression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonidas</namePart>
<namePart type="family">Gee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Zugarini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Rigutini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Torroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</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>Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.</abstract>
<identifier type="citekey">gee-etal-2022-fast</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.41</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.41</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>409</start>
<end>416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast Vocabulary Transfer for Language Model Compression
%A Gee, Leonidas
%A Zugarini, Andrea
%A Rigutini, Leonardo
%A Torroni, Paolo
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F gee-etal-2022-fast
%X Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.
%R 10.18653/v1/2022.emnlp-industry.41
%U https://aclanthology.org/2022.emnlp-industry.41
%U https://doi.org/10.18653/v1/2022.emnlp-industry.41
%P 409-416
Markdown (Informal)
[Fast Vocabulary Transfer for Language Model Compression](https://aclanthology.org/2022.emnlp-industry.41) (Gee et al., EMNLP 2022)
ACL
- Leonidas Gee, Andrea Zugarini, Leonardo Rigutini, and Paolo Torroni. 2022. Fast Vocabulary Transfer for Language Model Compression. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 409–416, Abu Dhabi, UAE. Association for Computational Linguistics.