@inproceedings{awasthy-etal-2020-predictive,
title = "Predictive Model Selection for Transfer Learning in Sequence Labeling Tasks",
author = "Awasthy, Parul and
Bhattacharjee, Bishwaranjan and
Kender, John and
Florian, Radu",
editor = "Moosavi, Nafise Sadat and
Fan, Angela and
Shwartz, Vered and
Glava{\v{s}}, Goran and
Joty, Shafiq and
Wang, Alex and
Wolf, Thomas",
booktitle = "Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sustainlp-1.15",
doi = "10.18653/v1/2020.sustainlp-1.15",
pages = "113--118",
abstract = "Transfer learning is a popular technique to learn a task using less training data and fewer compute resources. However, selecting the correct source model for transfer learning is a challenging task. We demonstrate a novel predictive method that determines which existing source model would minimize error for transfer learning to a given target. This technique does not require learning for prediction, and avoids computational costs of trail-and-error. We have evaluated this technique on nine datasets across diverse domains, including newswire, user forums, air flight booking, cybersecurity news, etc. We show that it per-forms better than existing techniques such as fine-tuning over vanilla BERT, or curriculum learning over the largest dataset on top of BERT, resulting in average F1 score gains in excess of 3{\%}. Moreover, our technique consistently selects the best model using fewer tries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="awasthy-etal-2020-predictive">
<titleInfo>
<title>Predictive Model Selection for Transfer Learning in Sequence Labeling Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parul</namePart>
<namePart type="family">Awasthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bishwaranjan</namePart>
<namePart type="family">Bhattacharjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Kender</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Florian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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 is a popular technique to learn a task using less training data and fewer compute resources. However, selecting the correct source model for transfer learning is a challenging task. We demonstrate a novel predictive method that determines which existing source model would minimize error for transfer learning to a given target. This technique does not require learning for prediction, and avoids computational costs of trail-and-error. We have evaluated this technique on nine datasets across diverse domains, including newswire, user forums, air flight booking, cybersecurity news, etc. We show that it per-forms better than existing techniques such as fine-tuning over vanilla BERT, or curriculum learning over the largest dataset on top of BERT, resulting in average F1 score gains in excess of 3%. Moreover, our technique consistently selects the best model using fewer tries.</abstract>
<identifier type="citekey">awasthy-etal-2020-predictive</identifier>
<identifier type="doi">10.18653/v1/2020.sustainlp-1.15</identifier>
<location>
<url>https://aclanthology.org/2020.sustainlp-1.15</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>113</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predictive Model Selection for Transfer Learning in Sequence Labeling Tasks
%A Awasthy, Parul
%A Bhattacharjee, Bishwaranjan
%A Kender, John
%A Florian, Radu
%Y Moosavi, Nafise Sadat
%Y Fan, Angela
%Y Shwartz, Vered
%Y Glavaš, Goran
%Y Joty, Shafiq
%Y Wang, Alex
%Y Wolf, Thomas
%S Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F awasthy-etal-2020-predictive
%X Transfer learning is a popular technique to learn a task using less training data and fewer compute resources. However, selecting the correct source model for transfer learning is a challenging task. We demonstrate a novel predictive method that determines which existing source model would minimize error for transfer learning to a given target. This technique does not require learning for prediction, and avoids computational costs of trail-and-error. We have evaluated this technique on nine datasets across diverse domains, including newswire, user forums, air flight booking, cybersecurity news, etc. We show that it per-forms better than existing techniques such as fine-tuning over vanilla BERT, or curriculum learning over the largest dataset on top of BERT, resulting in average F1 score gains in excess of 3%. Moreover, our technique consistently selects the best model using fewer tries.
%R 10.18653/v1/2020.sustainlp-1.15
%U https://aclanthology.org/2020.sustainlp-1.15
%U https://doi.org/10.18653/v1/2020.sustainlp-1.15
%P 113-118
Markdown (Informal)
[Predictive Model Selection for Transfer Learning in Sequence Labeling Tasks](https://aclanthology.org/2020.sustainlp-1.15) (Awasthy et al., sustainlp 2020)
ACL