@inproceedings{parvez-chang-2021-evaluating,
title = "Evaluating the Values of Sources in Transfer Learning",
author = "Parvez, Md Rizwan and
Chang, Kai-Wei",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.402",
doi = "10.18653/v1/2021.naacl-main.402",
pages = "5084--5116",
abstract = "Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop , an efficient source valuation framework for quantifying the usefulness of the sources (e.g., ) in transfer learning based on the Shapley value method. Experiments and comprehensive analyses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parvez-chang-2021-evaluating">
<titleInfo>
<title>Evaluating the Values of Sources in Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rizwan</namePart>
<namePart type="family">Parvez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop , an efficient source valuation framework for quantifying the usefulness of the sources (e.g., ) in transfer learning based on the Shapley value method. Experiments and comprehensive analyses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.</abstract>
<identifier type="citekey">parvez-chang-2021-evaluating</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.402</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.402</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>5084</start>
<end>5116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Values of Sources in Transfer Learning
%A Parvez, Md Rizwan
%A Chang, Kai-Wei
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F parvez-chang-2021-evaluating
%X Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop , an efficient source valuation framework for quantifying the usefulness of the sources (e.g., ) in transfer learning based on the Shapley value method. Experiments and comprehensive analyses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.
%R 10.18653/v1/2021.naacl-main.402
%U https://aclanthology.org/2021.naacl-main.402
%U https://doi.org/10.18653/v1/2021.naacl-main.402
%P 5084-5116
Markdown (Informal)
[Evaluating the Values of Sources in Transfer Learning](https://aclanthology.org/2021.naacl-main.402) (Parvez & Chang, NAACL 2021)
ACL
- Md Rizwan Parvez and Kai-Wei Chang. 2021. Evaluating the Values of Sources in Transfer Learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5084–5116, Online. Association for Computational Linguistics.