@inproceedings{min-etal-2024-data,
title = "{DATA}-{CUBE}: Data Curriculum for Instruction-based Sentence Representation Learning",
author = "Min, Yingqian and
Zhou, Kun and
Gao, Dawei and
Zhao, Xin and
Hu, He and
Li, Yaliang",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.816",
pages = "13748--13761",
abstract = "Recently, multi-task instruction tuning has been utilized to improve sentence representation learning (SRL). It enables SRL models to generate task-specific representations with the guidance of task instruction, thus exhibiting strong generalization ability on unseen tasks. However, these methods mostly neglect the potential interference problems across different tasks and instances, which may affect the training of the model.To address this issue, we propose a data curriculum method, namely **Data-CUBE**, that arranges the order of all the multi-task data for training, to minimize the interference risks from two aspects.At the task level, we aim to find the optimal task order to minimize the total cross-task interference risk and formulate this problem as the traveling salesman problem, which is further solved by a specially designed simulated annealing algorithm. At the instance level, we propose a measurement method to quantify the difficulty of all instances per task, and then arrange instances in an easy-to-difficult order for training.Experimental results show that our approach can boost the performance of state-of-the-art methods. Our code and data will be publicly released.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="min-etal-2024-data">
<titleInfo>
<title>DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingqian</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, multi-task instruction tuning has been utilized to improve sentence representation learning (SRL). It enables SRL models to generate task-specific representations with the guidance of task instruction, thus exhibiting strong generalization ability on unseen tasks. However, these methods mostly neglect the potential interference problems across different tasks and instances, which may affect the training of the model.To address this issue, we propose a data curriculum method, namely **Data-CUBE**, that arranges the order of all the multi-task data for training, to minimize the interference risks from two aspects.At the task level, we aim to find the optimal task order to minimize the total cross-task interference risk and formulate this problem as the traveling salesman problem, which is further solved by a specially designed simulated annealing algorithm. At the instance level, we propose a measurement method to quantify the difficulty of all instances per task, and then arrange instances in an easy-to-difficult order for training.Experimental results show that our approach can boost the performance of state-of-the-art methods. Our code and data will be publicly released.</abstract>
<identifier type="citekey">min-etal-2024-data</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.816</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13748</start>
<end>13761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning
%A Min, Yingqian
%A Zhou, Kun
%A Gao, Dawei
%A Zhao, Xin
%A Hu, He
%A Li, Yaliang
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F min-etal-2024-data
%X Recently, multi-task instruction tuning has been utilized to improve sentence representation learning (SRL). It enables SRL models to generate task-specific representations with the guidance of task instruction, thus exhibiting strong generalization ability on unseen tasks. However, these methods mostly neglect the potential interference problems across different tasks and instances, which may affect the training of the model.To address this issue, we propose a data curriculum method, namely **Data-CUBE**, that arranges the order of all the multi-task data for training, to minimize the interference risks from two aspects.At the task level, we aim to find the optimal task order to minimize the total cross-task interference risk and formulate this problem as the traveling salesman problem, which is further solved by a specially designed simulated annealing algorithm. At the instance level, we propose a measurement method to quantify the difficulty of all instances per task, and then arrange instances in an easy-to-difficult order for training.Experimental results show that our approach can boost the performance of state-of-the-art methods. Our code and data will be publicly released.
%U https://aclanthology.org/2024.findings-acl.816
%P 13748-13761
Markdown (Informal)
[DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning](https://aclanthology.org/2024.findings-acl.816) (Min et al., Findings 2024)
ACL