<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="och-ney-2001-machine">
    <titleInfo>
        <title>What can machine translation learn from speech recognition?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Franz</namePart>
        <namePart type="given">Josef</namePart>
        <namePart type="family">Och</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hermann</namePart>
        <namePart type="family">Ney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2001-sep&quot; 18-22&quot;</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Workshop on MT2010: Towards a Road Map for MT</title>
        </titleInfo>
        <originInfo>
            <place>
                <placeTerm type="text">Santiago de Compostela, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The performance of machine translation technology after 50 years of development leaves much to be desired. There is a high demand for well performing and cheap MT systems for many language pairs and domains, which automatically adapt to rapidly changing terminology. We argue that for successful MT systems it will be crucial to apply data-driven methods, especially statistical machine translation. In addition, it will be very important to establish common test environments. This includes the availability of large parallel training corpora, well defined test corpora and standardized evaluation criteria. Thereby research results can be compared and this will open the possibility for more competition in MT research.</abstract>
    <identifier type="citekey">och-ney-2001-machine</identifier>
    <location>
        <url>https://aclanthology.org/2001.mtsummit-road.6</url>
    </location>
    <part>
        <date>2001-sep&quot; 18-22&quot;</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T What can machine translation learn from speech recognition?
%A Och, Franz Josef
%A Ney, Hermann
%S Workshop on MT2010: Towards a Road Map for MT
%D 2001
%8 sep" 18 22"
%C Santiago de Compostela, Spain
%F och-ney-2001-machine
%X The performance of machine translation technology after 50 years of development leaves much to be desired. There is a high demand for well performing and cheap MT systems for many language pairs and domains, which automatically adapt to rapidly changing terminology. We argue that for successful MT systems it will be crucial to apply data-driven methods, especially statistical machine translation. In addition, it will be very important to establish common test environments. This includes the availability of large parallel training corpora, well defined test corpora and standardized evaluation criteria. Thereby research results can be compared and this will open the possibility for more competition in MT research.
%U https://aclanthology.org/2001.mtsummit-road.6

Markdown (Informal)

[What can machine translation learn from speech recognition?](https://aclanthology.org/2001.mtsummit-road.6) (Och & Ney, MTSummit 2001)

• What can machine translation learn from speech recognition? (Och & Ney, MTSummit 2001)

ACL

• Franz Josef Och and Hermann Ney. 2001. What can machine translation learn from speech recognition?. In Workshop on MT2010: Towards a Road Map for MT, Santiago de Compostela, Spain.