<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pentyala-etal-2019-multi">
    <titleInfo>
        <title>Multi-Task Networks with Universe, Group, and Task Feature Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shiva</namePart>
        <namePart type="family">Pentyala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mengwen</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Markus</namePart>
        <namePart type="family">Dreyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information at the inter-task level and can be encoded into the model. We investigate two variants of neural network architectures that accomplish this, learning different feature spaces at the levels of individual tasks, task groups, as well as the universe of all tasks: (1) parallel architectures encode each input simultaneously into feature spaces at different levels; (2) serial architectures encode each input successively into feature spaces at different levels in the task hierarchy. We demonstrate the methods on natural language understanding (NLU) tasks, where a grouping of tasks into different task domains leads to improved performance on ATIS, Snips, and a large in-house dataset.</abstract>
    <identifier type="citekey">pentyala-etal-2019-multi</identifier>
    <identifier type="doi">10.18653/v1/P19-1079</identifier>
    <location>
        <url>https://aclanthology.org/P19-1079</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>820</start>
            <end>830</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Task Networks with Universe, Group, and Task Feature Learning
%A Pentyala, Shiva
%A Liu, Mengwen
%A Dreyer, Markus
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F pentyala-etal-2019-multi
%X We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information at the inter-task level and can be encoded into the model. We investigate two variants of neural network architectures that accomplish this, learning different feature spaces at the levels of individual tasks, task groups, as well as the universe of all tasks: (1) parallel architectures encode each input simultaneously into feature spaces at different levels; (2) serial architectures encode each input successively into feature spaces at different levels in the task hierarchy. We demonstrate the methods on natural language understanding (NLU) tasks, where a grouping of tasks into different task domains leads to improved performance on ATIS, Snips, and a large in-house dataset.
%R 10.18653/v1/P19-1079
%U https://aclanthology.org/P19-1079
%U https://doi.org/10.18653/v1/P19-1079
%P 820-830

Markdown (Informal)

[Multi-Task Networks with Universe, Group, and Task Feature Learning](https://aclanthology.org/P19-1079) (Pentyala et al., ACL 2019)

• Multi-Task Networks with Universe, Group, and Task Feature Learning (Pentyala et al., ACL 2019)

ACL

• Shiva Pentyala, Mengwen Liu, and Markus Dreyer. 2019. Multi-Task Networks with Universe, Group, and Task Feature Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 820–830, Florence, Italy. Association for Computational Linguistics.