<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lakumarapu-etal-2020-end">
    <titleInfo>
        <title>End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nikhil</namePart>
        <namePart type="given">Kumar</namePart>
        <namePart type="family">Lakumarapu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Beomseok</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sathish</namePart>
        <namePart type="given">Reddy</namePart>
        <namePart type="family">Indurthi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hou</namePart>
        <namePart type="given">Jeung</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohd</namePart>
        <namePart type="given">Abbas</namePart>
        <namePart type="family">Zaidi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sangha</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Conference on Spoken Language Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we describe the system submitted to the IWSLT 2020 Offline Speech Translation Task. We adopt the Transformer architecture coupled with the meta-learning approach to build our end-to-end Speech-to-Text Translation (ST) system. Our meta-learning approach tackles the data scarcity of the ST task by leveraging the data available from Automatic Speech Recognition (ASR) and Machine Translation (MT) tasks. The meta-learning approach combined with synthetic data augmentation techniques improves the model performance significantly and achieves BLEU scores of 24.58, 27.51, and 27.61 on IWSLT test 2015, MuST-C test, and Europarl-ST test sets respectively.</abstract>
    <identifier type="citekey">lakumarapu-etal-2020-end</identifier>
    <identifier type="doi">10.18653/v1/2020.iwslt-1.7</identifier>
    <location>
        <url>https://aclanthology.org/2020.iwslt-1.7</url>
    </location>
    <part>
        <date>2020-jul</date>
        <extent unit="page">
            <start>73</start>
            <end>79</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning
%A Lakumarapu, Nikhil Kumar
%A Lee, Beomseok
%A Indurthi, Sathish Reddy
%A Han, Hou Jeung
%A Zaidi, Mohd Abbas
%A Kim, Sangha
%S Proceedings of the 17th International Conference on Spoken Language Translation
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F lakumarapu-etal-2020-end
%X In this paper, we describe the system submitted to the IWSLT 2020 Offline Speech Translation Task. We adopt the Transformer architecture coupled with the meta-learning approach to build our end-to-end Speech-to-Text Translation (ST) system. Our meta-learning approach tackles the data scarcity of the ST task by leveraging the data available from Automatic Speech Recognition (ASR) and Machine Translation (MT) tasks. The meta-learning approach combined with synthetic data augmentation techniques improves the model performance significantly and achieves BLEU scores of 24.58, 27.51, and 27.61 on IWSLT test 2015, MuST-C test, and Europarl-ST test sets respectively.
%R 10.18653/v1/2020.iwslt-1.7
%U https://aclanthology.org/2020.iwslt-1.7
%U https://doi.org/10.18653/v1/2020.iwslt-1.7
%P 73-79

Markdown (Informal)

[End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning](https://aclanthology.org/2020.iwslt-1.7) (Lakumarapu et al., IWSLT 2020)

• End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning (Lakumarapu et al., IWSLT 2020)

ACL

• Nikhil Kumar Lakumarapu, Beomseok Lee, Sathish Reddy Indurthi, Hou Jeung Han, Mohd Abbas Zaidi, and Sangha Kim. 2020. End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 73–79, Online. Association for Computational Linguistics.