@inproceedings{zhang-etal-2022-task,
title = "Task Compass: Scaling Multi-task Pre-training with Task Prefix",
author = "Zhang, Zhuosheng and
Wang, Shuohang and
Xu, Yichong and
Fang, Yuwei and
Yu, Wenhao and
Liu, Yang and
Zhao, Hai and
Zhu, Chenguang and
Zeng, Michael",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.416",
doi = "10.18653/v1/2022.findings-emnlp.416",
pages = "5671--5685",
abstract = "Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-task">
<titleInfo>
<title>Task Compass: Scaling Multi-task Pre-training with Task Prefix</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuosheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuohang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuwei</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenguang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Zeng</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>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL.</abstract>
<identifier type="citekey">zhang-etal-2022-task</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.416</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.416</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5671</start>
<end>5685</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Task Compass: Scaling Multi-task Pre-training with Task Prefix
%A Zhang, Zhuosheng
%A Wang, Shuohang
%A Xu, Yichong
%A Fang, Yuwei
%A Yu, Wenhao
%A Liu, Yang
%A Zhao, Hai
%A Zhu, Chenguang
%A Zeng, Michael
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhang-etal-2022-task
%X Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL.
%R 10.18653/v1/2022.findings-emnlp.416
%U https://aclanthology.org/2022.findings-emnlp.416
%U https://doi.org/10.18653/v1/2022.findings-emnlp.416
%P 5671-5685
Markdown (Informal)
[Task Compass: Scaling Multi-task Pre-training with Task Prefix](https://aclanthology.org/2022.findings-emnlp.416) (Zhang et al., Findings 2022)
ACL
- Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, and Michael Zeng. 2022. Task Compass: Scaling Multi-task Pre-training with Task Prefix. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5671–5685, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.