<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aghaebrahimian-cieliebak-2019-towards">
    <titleInfo>
        <title>Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ahmad</namePart>
        <namePart type="family">Aghaebrahimian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Cieliebak</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 report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical hypothesis testing method is used to extract the most informative words for each given class. These words are used as a class description for more label-aware text classification. Intuition is to help the model to concentrate on more informative words rather than more frequent ones. The model leverages the use of label descriptions in addition to the input text to enhance text classification performance. Our method is entirely data-driven, has no dependency on other sources of information than the training data, and is adaptable to different classification problems by providing appropriate training data without major hyper-parameter tuning. We trained and tested our system on several publicly available datasets, where we managed to improve the state-of-the-art on one set with a high margin and to obtain competitive results on all other ones.</abstract>
    <identifier type="citekey">aghaebrahimian-cieliebak-2019-towards</identifier>
    <identifier type="doi">10.18653/v1/P19-1557</identifier>
    <location>
        <url>https://aclanthology.org/P19-1557</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>5551</start>
            <end>5557</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks
%A Aghaebrahimian, Ahmad
%A Cieliebak, Mark
%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 aghaebrahimian-cieliebak-2019-towards
%X We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical hypothesis testing method is used to extract the most informative words for each given class. These words are used as a class description for more label-aware text classification. Intuition is to help the model to concentrate on more informative words rather than more frequent ones. The model leverages the use of label descriptions in addition to the input text to enhance text classification performance. Our method is entirely data-driven, has no dependency on other sources of information than the training data, and is adaptable to different classification problems by providing appropriate training data without major hyper-parameter tuning. We trained and tested our system on several publicly available datasets, where we managed to improve the state-of-the-art on one set with a high margin and to obtain competitive results on all other ones.
%R 10.18653/v1/P19-1557
%U https://aclanthology.org/P19-1557
%U https://doi.org/10.18653/v1/P19-1557
%P 5551-5557

Markdown (Informal)

[Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks](https://aclanthology.org/P19-1557) (Aghaebrahimian & Cieliebak, ACL 2019)

• Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks (Aghaebrahimian & Cieliebak, ACL 2019)

ACL

• Ahmad Aghaebrahimian and Mark Cieliebak. 2019. Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5551–5557, Florence, Italy. Association for Computational Linguistics.