@inproceedings{zhang-etal-2023-friend,
title = "Friend-training: Learning from Models of Different but Related Tasks",
author = "Zhang, Mian and
Jin, Lifeng and
Song, Linfeng and
Mi, Haitao and
Zhou, Xiabing and
Yu, Dong",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.18",
doi = "10.18653/v1/2023.eacl-main.18",
pages = "232--247",
abstract = "Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes. However, many tasks in natural language processing are about different but related aspects of language, and models trained for one task can be great teachers for other related tasks. In this work, we propose friend-training, a cross-task self-training framework, where models trained to do different tasks are used in an iterative training, pseudo-labeling, and retraining process to help each other for better selection of pseudo-labels. With two dialogue understanding tasks, conversational semantic role labeling and dialogue rewriting, chosen for a case study, we show that the models trained with the friend-training framework achieve the best performance compared to strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-friend">
<titleInfo>
<title>Friend-training: Learning from Models of Different but Related Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linfeng</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Mi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiabing</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes. However, many tasks in natural language processing are about different but related aspects of language, and models trained for one task can be great teachers for other related tasks. In this work, we propose friend-training, a cross-task self-training framework, where models trained to do different tasks are used in an iterative training, pseudo-labeling, and retraining process to help each other for better selection of pseudo-labels. With two dialogue understanding tasks, conversational semantic role labeling and dialogue rewriting, chosen for a case study, we show that the models trained with the friend-training framework achieve the best performance compared to strong baselines.</abstract>
<identifier type="citekey">zhang-etal-2023-friend</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.18</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.18</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>232</start>
<end>247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Friend-training: Learning from Models of Different but Related Tasks
%A Zhang, Mian
%A Jin, Lifeng
%A Song, Linfeng
%A Mi, Haitao
%A Zhou, Xiabing
%A Yu, Dong
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F zhang-etal-2023-friend
%X Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes. However, many tasks in natural language processing are about different but related aspects of language, and models trained for one task can be great teachers for other related tasks. In this work, we propose friend-training, a cross-task self-training framework, where models trained to do different tasks are used in an iterative training, pseudo-labeling, and retraining process to help each other for better selection of pseudo-labels. With two dialogue understanding tasks, conversational semantic role labeling and dialogue rewriting, chosen for a case study, we show that the models trained with the friend-training framework achieve the best performance compared to strong baselines.
%R 10.18653/v1/2023.eacl-main.18
%U https://aclanthology.org/2023.eacl-main.18
%U https://doi.org/10.18653/v1/2023.eacl-main.18
%P 232-247
Markdown (Informal)
[Friend-training: Learning from Models of Different but Related Tasks](https://aclanthology.org/2023.eacl-main.18) (Zhang et al., EACL 2023)
ACL
- Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Xiabing Zhou, and Dong Yu. 2023. Friend-training: Learning from Models of Different but Related Tasks. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 232–247, Dubrovnik, Croatia. Association for Computational Linguistics.