<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kocher-etal-2019-alleviating">
    <titleInfo>
        <title>Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Noémien</namePart>
        <namePart type="family">Kocher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christian</namePart>
        <namePart type="family">Scuito</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lorenzo</namePart>
        <namePart type="family">Tarantino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandros</namePart>
        <namePart type="family">Lazaridis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">Fischer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Claudiu</namePart>
        <namePart type="family">Musat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In sequence modeling tasks the token order matters, but this information can be partially lost due to the discretization of the sequence into data points. In this paper, we study the imbalance between the way certain token pairs are included in data points and others are not. We denote this a token order imbalance (TOI) and we link the partial sequence information loss to a diminished performance of the system as a whole, both in text and speech processing tasks. We then provide a mechanism to leverage the full token order information—Alleviated TOI—by iteratively overlapping the token composition of data points. For recurrent networks, we use prime numbers for the batch size to avoid redundancies when building batches from overlapped data points. The proposed method achieved state of the art performance in both text and speech related tasks.</abstract>
    <identifier type="citekey">kocher-etal-2019-alleviating</identifier>
    <identifier type="doi">10.18653/v1/K19-1083</identifier>
    <location>
        <url>https://aclanthology.org/K19-1083</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>890</start>
            <end>899</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes
%A Kocher, Noémien
%A Scuito, Christian
%A Tarantino, Lorenzo
%A Lazaridis, Alexandros
%A Fischer, Andreas
%A Musat, Claudiu
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F kocher-etal-2019-alleviating
%X In sequence modeling tasks the token order matters, but this information can be partially lost due to the discretization of the sequence into data points. In this paper, we study the imbalance between the way certain token pairs are included in data points and others are not. We denote this a token order imbalance (TOI) and we link the partial sequence information loss to a diminished performance of the system as a whole, both in text and speech processing tasks. We then provide a mechanism to leverage the full token order information—Alleviated TOI—by iteratively overlapping the token composition of data points. For recurrent networks, we use prime numbers for the batch size to avoid redundancies when building batches from overlapped data points. The proposed method achieved state of the art performance in both text and speech related tasks.
%R 10.18653/v1/K19-1083
%U https://aclanthology.org/K19-1083
%U https://doi.org/10.18653/v1/K19-1083
%P 890-899

Markdown (Informal)

[Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes](https://aclanthology.org/K19-1083) (Kocher et al., CoNLL 2019)

• Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes (Kocher et al., CoNLL 2019)

ACL

• Noémien Kocher, Christian Scuito, Lorenzo Tarantino, Alexandros Lazaridis, Andreas Fischer, and Claudiu Musat. 2019. Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 890–899, Hong Kong, China. Association for Computational Linguistics.