<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jehl-etal-2019-learning">
    <titleInfo>
        <title>Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Laura</namePart>
        <namePart type="family">Jehl</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carolin</namePart>
        <namePart type="family">Lawrence</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Riezler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>In many machine learning scenarios, supervision by gold labels is not available and conse quently neural models cannot be trained directly by maximum likelihood estimation. In a weak supervision scenario, metric-augmented objectives can be employed to assign feedback to model outputs, which can be used to extract a supervision signal for training. We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. We show that objectives should actively discourage negative outputs in addition to promoting a surrogate gold structure. This notion of bipolarity is naturally present in ramp loss objectives, which we adapt to neural models. We show that bipolar ramp loss objectives outperform other non-bipolar ramp loss objectives and minimum risk training on both weakly supervised tasks, as well as on a supervised machine translation task. Additionally, we introduce a novel token-level ramp loss objective, which is able to outperform even the best sequence-level ramp loss on both weakly supervised tasks.</abstract>
    <identifier type="citekey">jehl-etal-2019-learning</identifier>
    <identifier type="doi">10.1162/tacl_a_00265</identifier>
    <location>
        <url>https://aclanthology.org/Q19-1015</url>
    </location>
    <part>
        <date>2019</date>
        <detail type="volume"><number>7</number></detail>
        <extent unit="page">
            <start>233</start>
            <end>248</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss
%A Jehl, Laura
%A Lawrence, Carolin
%A Riezler, Stefan
%J Transactions of the Association for Computational Linguistics
%D 2019
%V 7
%I MIT Press
%C Cambridge, MA
%F jehl-etal-2019-learning
%X In many machine learning scenarios, supervision by gold labels is not available and conse quently neural models cannot be trained directly by maximum likelihood estimation. In a weak supervision scenario, metric-augmented objectives can be employed to assign feedback to model outputs, which can be used to extract a supervision signal for training. We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. We show that objectives should actively discourage negative outputs in addition to promoting a surrogate gold structure. This notion of bipolarity is naturally present in ramp loss objectives, which we adapt to neural models. We show that bipolar ramp loss objectives outperform other non-bipolar ramp loss objectives and minimum risk training on both weakly supervised tasks, as well as on a supervised machine translation task. Additionally, we introduce a novel token-level ramp loss objective, which is able to outperform even the best sequence-level ramp loss on both weakly supervised tasks.
%R 10.1162/tacl_a_00265
%U https://aclanthology.org/Q19-1015
%U https://doi.org/10.1162/tacl_a_00265
%P 233-248

Markdown (Informal)

[Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss](https://aclanthology.org/Q19-1015) (Jehl et al., TACL 2019)

• Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss (Jehl et al., TACL 2019)

ACL

• Laura Jehl, Carolin Lawrence, and Stefan Riezler. 2019. Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss. Transactions of the Association for Computational Linguistics, 7:233–248.