<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruder-plank-2017-learning">
    <titleInfo>
        <title>Learning to select data for transfer learning with Bayesian Optimization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sebastian</namePart>
        <namePart type="family">Ruder</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Barbara</namePart>
        <namePart type="family">Plank</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Domain similarity measures can be used to gauge adaptability and select suitable data for transfer learning, but existing approaches define ad hoc measures that are deemed suitable for respective tasks. Inspired by work on curriculum learning, we propose to learn data selection measures using Bayesian Optimization and evaluate them across models, domains and tasks. Our learned measures outperform existing domain similarity measures significantly on three tasks: sentiment analysis, part-of-speech tagging, and parsing. We show the importance of complementing similarity with diversity, and that learned measures are–to some degree–transferable across models, domains, and even tasks.</abstract>
    <identifier type="citekey">ruder-plank-2017-learning</identifier>
    <identifier type="doi">10.18653/v1/D17-1038</identifier>
    <location>
        <url>https://aclanthology.org/D17-1038</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>372</start>
            <end>382</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to select data for transfer learning with Bayesian Optimization
%A Ruder, Sebastian
%A Plank, Barbara
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F ruder-plank-2017-learning
%X Domain similarity measures can be used to gauge adaptability and select suitable data for transfer learning, but existing approaches define ad hoc measures that are deemed suitable for respective tasks. Inspired by work on curriculum learning, we propose to learn data selection measures using Bayesian Optimization and evaluate them across models, domains and tasks. Our learned measures outperform existing domain similarity measures significantly on three tasks: sentiment analysis, part-of-speech tagging, and parsing. We show the importance of complementing similarity with diversity, and that learned measures are–to some degree–transferable across models, domains, and even tasks.
%R 10.18653/v1/D17-1038
%U https://aclanthology.org/D17-1038
%U https://doi.org/10.18653/v1/D17-1038
%P 372-382

Markdown (Informal)

[Learning to select data for transfer learning with Bayesian Optimization](https://aclanthology.org/D17-1038) (Ruder & Plank, EMNLP 2017)

• Learning to select data for transfer learning with Bayesian Optimization (Ruder & Plank, EMNLP 2017)

ACL

• Sebastian Ruder and Barbara Plank. 2017. Learning to select data for transfer learning with Bayesian Optimization. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 372–382, Copenhagen, Denmark. Association for Computational Linguistics.