@inproceedings{gu-etal-2024-nlopt,
title = "{NL}o{PT}: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption",
author = "Gu, Hao and
Yi, Jiangyan and
Lian, Zheng and
Tao, Jianhua and
Yan, Xinrui",
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.1072/",
pages = "12259--12270",
abstract = "Pre-trained Language Models (PLMs) like BERT have achieved superior performance on different downstream tasks, even when such a model is trained on a general domain. Moreover, recent studies have shown that continued pre-training on task-specific data, known as task adaptive pre-training (TAPT), can further improve downstream task performance. However, conventional TAPT adjusts all the parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLMs weights, and it is expensive to store a whole model copy for each downstream task. In this paper, we propose NLoPT, a two-step n-gram enhanced low-rank task adaptive pre-training method, to effectively and efficiently customize a PLM to the downstream task. Specifically, we first apply low-rank adaption (LoRA), a prevalent parameter-efficient technique, for efficient TAPT. We further explicitly incorporate the task-specific multi-granularity n-gram information via the cross-attention mechanism. Experimental results on six datasets from four domains illustrate the effectiveness of NLoPT, demonstrating the superiority of LoRA based TAPT and the necessity of incorporating task-specific n-gram information."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2024-nlopt">
<titleInfo>
<title>NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangyan</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianhua</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinrui</namePart>
<namePart type="family">Yan</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>Pre-trained Language Models (PLMs) like BERT have achieved superior performance on different downstream tasks, even when such a model is trained on a general domain. Moreover, recent studies have shown that continued pre-training on task-specific data, known as task adaptive pre-training (TAPT), can further improve downstream task performance. However, conventional TAPT adjusts all the parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLMs weights, and it is expensive to store a whole model copy for each downstream task. In this paper, we propose NLoPT, a two-step n-gram enhanced low-rank task adaptive pre-training method, to effectively and efficiently customize a PLM to the downstream task. Specifically, we first apply low-rank adaption (LoRA), a prevalent parameter-efficient technique, for efficient TAPT. We further explicitly incorporate the task-specific multi-granularity n-gram information via the cross-attention mechanism. Experimental results on six datasets from four domains illustrate the effectiveness of NLoPT, demonstrating the superiority of LoRA based TAPT and the necessity of incorporating task-specific n-gram information.</abstract>
<identifier type="citekey">gu-etal-2024-nlopt</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1072/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12259</start>
<end>12270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption
%A Gu, Hao
%A Yi, Jiangyan
%A Lian, Zheng
%A Tao, Jianhua
%A Yan, Xinrui
%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 gu-etal-2024-nlopt
%X Pre-trained Language Models (PLMs) like BERT have achieved superior performance on different downstream tasks, even when such a model is trained on a general domain. Moreover, recent studies have shown that continued pre-training on task-specific data, known as task adaptive pre-training (TAPT), can further improve downstream task performance. However, conventional TAPT adjusts all the parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLMs weights, and it is expensive to store a whole model copy for each downstream task. In this paper, we propose NLoPT, a two-step n-gram enhanced low-rank task adaptive pre-training method, to effectively and efficiently customize a PLM to the downstream task. Specifically, we first apply low-rank adaption (LoRA), a prevalent parameter-efficient technique, for efficient TAPT. We further explicitly incorporate the task-specific multi-granularity n-gram information via the cross-attention mechanism. Experimental results on six datasets from four domains illustrate the effectiveness of NLoPT, demonstrating the superiority of LoRA based TAPT and the necessity of incorporating task-specific n-gram information.
%U https://aclanthology.org/2024.lrec-main.1072/
%P 12259-12270
Markdown (Informal)
[NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption](https://aclanthology.org/2024.lrec-main.1072/) (Gu et al., LREC-COLING 2024)
ACL