<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bei-zong-2017-towards">
    <titleInfo>
        <title>Towards better translation performance on spoken language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Bei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Zong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-dec 14-15</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 14th International Conference on Spoken Language Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sakriani</namePart>
            <namePart type="family">Sakti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Masao</namePart>
            <namePart type="family">Utiyama</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Workshop on Spoken Language Translation</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we describe GTCOM’s neural machine translation(NMT) systems for the International Workshop on Spoken Language Translation(IWSLT) 2017. We participated in the English-to-Chinese and Chinese-to-English tracks in the small data condition of the bilingual task and the zero-shot condition of the multilingual task. Our systems are based on the encoder-decoder architecture with attention mechanism. We build byte pair encoding (BPE) models in parallel data and back-translated monolingual training data provided in the small data condition. Other techniques we explored in our system include two deep architectures, layer nomalization, weight normalization and training models with annealing Adam, etc. The official scores of English-to-Chinese, Chinese-to-English are 28.13 and 21.35 on test set 2016 and 28.30 and 22.16 on test set 2017. The official scores on German-to-Dutch, Dutch-to-German, Italian-to-Romanian and Romanian-to-Italian are 19.59, 17.95, 18.62 and 20.39 respectively.</abstract>
    <identifier type="citekey">bei-zong-2017-towards</identifier>
    <location>
        <url>https://aclanthology.org/2017.iwslt-1.7</url>
    </location>
    <part>
        <date>2017-dec 14-15</date>
        <extent unit="page">
            <start>48</start>
            <end>54</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards better translation performance on spoken language
%A Bei, Chao
%A Zong, Hao
%Y Sakti, Sakriani
%Y Utiyama, Masao
%S Proceedings of the 14th International Conference on Spoken Language Translation
%D 2017
%8 dec 14 15
%I International Workshop on Spoken Language Translation
%C Tokyo, Japan
%F bei-zong-2017-towards
%X In this paper, we describe GTCOM’s neural machine translation(NMT) systems for the International Workshop on Spoken Language Translation(IWSLT) 2017. We participated in the English-to-Chinese and Chinese-to-English tracks in the small data condition of the bilingual task and the zero-shot condition of the multilingual task. Our systems are based on the encoder-decoder architecture with attention mechanism. We build byte pair encoding (BPE) models in parallel data and back-translated monolingual training data provided in the small data condition. Other techniques we explored in our system include two deep architectures, layer nomalization, weight normalization and training models with annealing Adam, etc. The official scores of English-to-Chinese, Chinese-to-English are 28.13 and 21.35 on test set 2016 and 28.30 and 22.16 on test set 2017. The official scores on German-to-Dutch, Dutch-to-German, Italian-to-Romanian and Romanian-to-Italian are 19.59, 17.95, 18.62 and 20.39 respectively.
%U https://aclanthology.org/2017.iwslt-1.7
%P 48-54

Markdown (Informal)

[Towards better translation performance on spoken language](https://aclanthology.org/2017.iwslt-1.7) (Bei & Zong, IWSLT 2017)

• Towards better translation performance on spoken language (Bei & Zong, IWSLT 2017)

ACL

• Chao Bei and Hao Zong. 2017. Towards better translation performance on spoken language. In Proceedings of the 14th International Conference on Spoken Language Translation, pages 48–54, Tokyo, Japan. International Workshop on Spoken Language Translation.