@inproceedings{taylor-white-1998-predicting,
title = "Predicting what {MT} is good for: user judgments and task performance",
author = "Taylor, Kathryn and
White, John",
editor = "Farwell, David and
Gerber, Laurie and
Hovy, Eduard",
booktitle = "Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 28-31",
year = "1998",
address = "Langhorne, PA, USA",
publisher = "Springer",
url = "https://aclanthology.org/1998.amta-papers.32/",
pages = "364--373",
abstract = "As part of the Machine Translation (MT) Proficiency Scale project at the US Federal Intelligent Document Understanding Laboratory (FIDUL), Litton PRC is developing a method to measure MT systems in terms of the tasks for which their output may be successfully used. This paper describes the development of a task inventory, i.e., a comprehensive list of the tasks analysts perform with translated material and details the capture of subjective user judgments and insights about MT samples. Also described are the user exercises conducted using machine and human translation samples and the assessment of task performance. By analyzing translation errors, user judgments about errors that interfere with task performance, and user task performance results, we isolate source language patterns which produce output problems. These patterns can then be captured in a single diagnostic test set, to be easily applied to any new Japanese-English system to predict the utility of its output."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="taylor-white-1998-predicting">
<titleInfo>
<title>Predicting what MT is good for: user judgments and task performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathryn</namePart>
<namePart type="family">Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">White</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>1998-oct 28-31</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Farwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Gerber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Langhorne, PA, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As part of the Machine Translation (MT) Proficiency Scale project at the US Federal Intelligent Document Understanding Laboratory (FIDUL), Litton PRC is developing a method to measure MT systems in terms of the tasks for which their output may be successfully used. This paper describes the development of a task inventory, i.e., a comprehensive list of the tasks analysts perform with translated material and details the capture of subjective user judgments and insights about MT samples. Also described are the user exercises conducted using machine and human translation samples and the assessment of task performance. By analyzing translation errors, user judgments about errors that interfere with task performance, and user task performance results, we isolate source language patterns which produce output problems. These patterns can then be captured in a single diagnostic test set, to be easily applied to any new Japanese-English system to predict the utility of its output.</abstract>
<identifier type="citekey">taylor-white-1998-predicting</identifier>
<location>
<url>https://aclanthology.org/1998.amta-papers.32/</url>
</location>
<part>
<date>1998-oct 28-31</date>
<extent unit="page">
<start>364</start>
<end>373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting what MT is good for: user judgments and task performance
%A Taylor, Kathryn
%A White, John
%Y Farwell, David
%Y Gerber, Laurie
%Y Hovy, Eduard
%S Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 1998
%8 oct 28 31
%I Springer
%C Langhorne, PA, USA
%F taylor-white-1998-predicting
%X As part of the Machine Translation (MT) Proficiency Scale project at the US Federal Intelligent Document Understanding Laboratory (FIDUL), Litton PRC is developing a method to measure MT systems in terms of the tasks for which their output may be successfully used. This paper describes the development of a task inventory, i.e., a comprehensive list of the tasks analysts perform with translated material and details the capture of subjective user judgments and insights about MT samples. Also described are the user exercises conducted using machine and human translation samples and the assessment of task performance. By analyzing translation errors, user judgments about errors that interfere with task performance, and user task performance results, we isolate source language patterns which produce output problems. These patterns can then be captured in a single diagnostic test set, to be easily applied to any new Japanese-English system to predict the utility of its output.
%U https://aclanthology.org/1998.amta-papers.32/
%P 364-373
Markdown (Informal)
[Predicting what MT is good for: user judgments and task performance](https://aclanthology.org/1998.amta-papers.32/) (Taylor & White, AMTA 1998)
ACL