<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="szolnok-barta-lakatos-etal-2021-bme">
    <titleInfo>
        <title>BME Submission for SIGMORPHON 2021 Shared Task 0. A Three Step Training Approach with Data Augmentation for Morphological Inflection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gábor</namePart>
        <namePart type="family">Szolnok</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Botond</namePart>
        <namePart type="family">Barta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dorina</namePart>
        <namePart type="family">Lakatos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Judit</namePart>
        <namePart type="family">Ács</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Garrett</namePart>
            <namePart type="family">Nicolai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kyle</namePart>
            <namePart type="family">Gorman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ryan</namePart>
            <namePart type="family">Cotterell</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with three step training that is first trained on all languages, then fine-tuned on each language family and finally fine-tuned on individual languages. We use a different type of data augmentation technique in the first two steps. Our system outperformed the only other submission. Although it remains worse than the Transformer baseline released by the organizers, our model is simpler and our data augmentation techniques are easily applicable to new languages. We perform ablation studies and show that the augmentation techniques and the three training steps often help but sometimes have a negative effect. Our code is publicly available.</abstract>
    <identifier type="citekey">szolnok-barta-lakatos-etal-2021-bme</identifier>
    <identifier type="doi">10.18653/v1/2021.sigmorphon-1.27</identifier>
    <location>
        <url>https://aclanthology.org/2021.sigmorphon-1.27/</url>
    </location>
    <part>
        <date>2021-08</date>
        <extent unit="page">
            <start>268</start>
            <end>273</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BME Submission for SIGMORPHON 2021 Shared Task 0. A Three Step Training Approach with Data Augmentation for Morphological Inflection
%A Szolnok, Gábor
%A Barta, Botond
%A Lakatos, Dorina
%A Ács, Judit
%Y Nicolai, Garrett
%Y Gorman, Kyle
%Y Cotterell, Ryan
%S Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F szolnok-barta-lakatos-etal-2021-bme
%X We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with three step training that is first trained on all languages, then fine-tuned on each language family and finally fine-tuned on individual languages. We use a different type of data augmentation technique in the first two steps. Our system outperformed the only other submission. Although it remains worse than the Transformer baseline released by the organizers, our model is simpler and our data augmentation techniques are easily applicable to new languages. We perform ablation studies and show that the augmentation techniques and the three training steps often help but sometimes have a negative effect. Our code is publicly available.
%R 10.18653/v1/2021.sigmorphon-1.27
%U https://aclanthology.org/2021.sigmorphon-1.27/
%U https://doi.org/10.18653/v1/2021.sigmorphon-1.27
%P 268-273

Markdown (Informal)

[BME Submission for SIGMORPHON 2021 Shared Task 0. A Three Step Training Approach with Data Augmentation for Morphological Inflection](https://aclanthology.org/2021.sigmorphon-1.27/) (Szolnok et al., SIGMORPHON 2021)

• BME Submission for SIGMORPHON 2021 Shared Task 0. A Three Step Training Approach with Data Augmentation for Morphological Inflection (Szolnok et al., SIGMORPHON 2021)

ACL

• Gábor Szolnok, Botond Barta, Dorina Lakatos, and Judit Ács. 2021. BME Submission for SIGMORPHON 2021 Shared Task 0. A Three Step Training Approach with Data Augmentation for Morphological Inflection. In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 268–273, Online. Association for Computational Linguistics.