<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paul-etal-2005-machine">
    <titleInfo>
        <title>A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Paul</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eiichiro</namePart>
        <namePart type="family">Sumita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seiichi</namePart>
        <namePart type="family">Yamamoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2005-sep 13-15</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Workshop on example-based machine translation</title>
        </titleInfo>
        <originInfo>
            <place>
                <placeTerm type="text">Phuket, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper proposes a method for integrating example-based and rule-based machine translation systems with statistical methods. It extends a greedy decoder for statistical machine translation (SMT), which searches for an optimal translation by using SMT models starting from a decoder seed, i.e., the source language input paired with an initial translation hypothesis. In order to reduce local optima problems inherent in the search, the outputs generated by multiple translation engines, such as rule-based (RBMT) and example-based (EBMT) systems, are utilized as the initial translation hypotheses. This method outperforms conventional greedy decoding approaches using initial translation hypotheses based on translation examples retrieved from a parallel text corpus. However, the decoding of multiple initial translation hypotheses is computationally expensive. This paper proposes a method to select a single initial translation hypothesis before decoding based on a machine learning approach that judges the appropriateness of multiple initial translation hypotheses and selects the most confident one for decoding. Our approach is evaluated for the translation of dialogues in the travel domain, and the results show that it drastically reduces computational costs without a loss in translation quality.</abstract>
    <identifier type="citekey">paul-etal-2005-machine</identifier>
    <location>
        <url>https://aclanthology.org/2005.mtsummit-ebmt.15</url>
    </location>
    <part>
        <date>2005-sep 13-15</date>
        <extent unit="page">
            <start>117</start>
            <end>124</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT
%A Paul, Michael
%A Sumita, Eiichiro
%A Yamamoto, Seiichi
%S Workshop on example-based machine translation
%D 2005
%8 sep 13 15
%C Phuket, Thailand
%F paul-etal-2005-machine
%X This paper proposes a method for integrating example-based and rule-based machine translation systems with statistical methods. It extends a greedy decoder for statistical machine translation (SMT), which searches for an optimal translation by using SMT models starting from a decoder seed, i.e., the source language input paired with an initial translation hypothesis. In order to reduce local optima problems inherent in the search, the outputs generated by multiple translation engines, such as rule-based (RBMT) and example-based (EBMT) systems, are utilized as the initial translation hypotheses. This method outperforms conventional greedy decoding approaches using initial translation hypotheses based on translation examples retrieved from a parallel text corpus. However, the decoding of multiple initial translation hypotheses is computationally expensive. This paper proposes a method to select a single initial translation hypothesis before decoding based on a machine learning approach that judges the appropriateness of multiple initial translation hypotheses and selects the most confident one for decoding. Our approach is evaluated for the translation of dialogues in the travel domain, and the results show that it drastically reduces computational costs without a loss in translation quality.
%U https://aclanthology.org/2005.mtsummit-ebmt.15
%P 117-124

Markdown (Informal)

[A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT](https://aclanthology.org/2005.mtsummit-ebmt.15) (Paul et al., MTSummit 2005)

• A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT (Paul et al., MTSummit 2005)

ACL

• Michael Paul, Eiichiro Sumita, and Seiichi Yamamoto. 2005. A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT. In Workshop on example-based machine translation, pages 117–124, Phuket, Thailand.