@inproceedings{bond-etal-2008-sharing,
title = "Sharing User Dictionaries Across Multiple Systems with {UTX}-{S}",
author = "Bond, Francis and
Okura, Seiji and
Yamamoto, Yuji and
Murata, Toshiki and
Uchimoto, Kiyotaka and
Kato, Michael and
Shimazu, Miwako and
Suzuki, Tsugiyoshi",
booktitle = "Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Government and Commercial Uses of MT",
month = oct # " 21-25",
year = "2008",
address = "Waikiki, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2008.amta-govandcom.3/",
pages = "304--313",
abstract = "Careful tuning of user-created dictionaries is indispensable when using a machine translation system for computer aided translation. However, there is no widely used standard for user dictionaries in the Japanese/English machine translation market. To address this issue, AAMT (the Asia-Pacific Association for Machine Translation) has established a specification of sharable dictionaries (UTX-S: Universal Terminology eXchange -- Simple), which can be used across different machine translation systems, thus increasing the interoperability of language resources. UTX-S is simpler than existing specifications such as UPF and OLIF. It was explicitly designed to make it easy to (a) add new user dictionaries and (b) share existing user dictionaries. This facilitates rapid user dictionary production and avoids vendor tie in. In this study we describe the UTX-Simple (UTX-S) format, and show that it can be converted to the user dictionary formats for five commercial English-Japanese MT systems. We then present a case study where we (a) convert an on-line glossary to UTX-S, and (b) produce user dictionaries for five different systems, and then exchange them. The results show that the simplified format of UTX-S can be used to rapidly build dictionaries. Further, we confirm that customized user dictionaries are effective across systems, although with a slight loss in quality: on average, user dictionaries improved the translations for 44.8{\%} of translations with the systems they were built for and 37.3{\%} of translations for different systems. In ongoing work, AAMT is using UTX-S as the format in building up a user community for producing, sharing, and accumulating user dictionaries in a sustainable way."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bond-etal-2008-sharing">
<titleInfo>
<title>Sharing User Dictionaries Across Multiple Systems with UTX-S</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seiji</namePart>
<namePart type="family">Okura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiki</namePart>
<namePart type="family">Murata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyotaka</namePart>
<namePart type="family">Uchimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miwako</namePart>
<namePart type="family">Shimazu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsugiyoshi</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-oct 21-25</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Government and Commercial Uses of MT</title>
</titleInfo>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Waikiki, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Careful tuning of user-created dictionaries is indispensable when using a machine translation system for computer aided translation. However, there is no widely used standard for user dictionaries in the Japanese/English machine translation market. To address this issue, AAMT (the Asia-Pacific Association for Machine Translation) has established a specification of sharable dictionaries (UTX-S: Universal Terminology eXchange – Simple), which can be used across different machine translation systems, thus increasing the interoperability of language resources. UTX-S is simpler than existing specifications such as UPF and OLIF. It was explicitly designed to make it easy to (a) add new user dictionaries and (b) share existing user dictionaries. This facilitates rapid user dictionary production and avoids vendor tie in. In this study we describe the UTX-Simple (UTX-S) format, and show that it can be converted to the user dictionary formats for five commercial English-Japanese MT systems. We then present a case study where we (a) convert an on-line glossary to UTX-S, and (b) produce user dictionaries for five different systems, and then exchange them. The results show that the simplified format of UTX-S can be used to rapidly build dictionaries. Further, we confirm that customized user dictionaries are effective across systems, although with a slight loss in quality: on average, user dictionaries improved the translations for 44.8% of translations with the systems they were built for and 37.3% of translations for different systems. In ongoing work, AAMT is using UTX-S as the format in building up a user community for producing, sharing, and accumulating user dictionaries in a sustainable way.</abstract>
<identifier type="citekey">bond-etal-2008-sharing</identifier>
<location>
<url>https://aclanthology.org/2008.amta-govandcom.3/</url>
</location>
<part>
<date>2008-oct 21-25</date>
<extent unit="page">
<start>304</start>
<end>313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sharing User Dictionaries Across Multiple Systems with UTX-S
%A Bond, Francis
%A Okura, Seiji
%A Yamamoto, Yuji
%A Murata, Toshiki
%A Uchimoto, Kiyotaka
%A Kato, Michael
%A Shimazu, Miwako
%A Suzuki, Tsugiyoshi
%S Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Government and Commercial Uses of MT
%D 2008
%8 oct 21 25
%I Association for Machine Translation in the Americas
%C Waikiki, USA
%F bond-etal-2008-sharing
%X Careful tuning of user-created dictionaries is indispensable when using a machine translation system for computer aided translation. However, there is no widely used standard for user dictionaries in the Japanese/English machine translation market. To address this issue, AAMT (the Asia-Pacific Association for Machine Translation) has established a specification of sharable dictionaries (UTX-S: Universal Terminology eXchange – Simple), which can be used across different machine translation systems, thus increasing the interoperability of language resources. UTX-S is simpler than existing specifications such as UPF and OLIF. It was explicitly designed to make it easy to (a) add new user dictionaries and (b) share existing user dictionaries. This facilitates rapid user dictionary production and avoids vendor tie in. In this study we describe the UTX-Simple (UTX-S) format, and show that it can be converted to the user dictionary formats for five commercial English-Japanese MT systems. We then present a case study where we (a) convert an on-line glossary to UTX-S, and (b) produce user dictionaries for five different systems, and then exchange them. The results show that the simplified format of UTX-S can be used to rapidly build dictionaries. Further, we confirm that customized user dictionaries are effective across systems, although with a slight loss in quality: on average, user dictionaries improved the translations for 44.8% of translations with the systems they were built for and 37.3% of translations for different systems. In ongoing work, AAMT is using UTX-S as the format in building up a user community for producing, sharing, and accumulating user dictionaries in a sustainable way.
%U https://aclanthology.org/2008.amta-govandcom.3/
%P 304-313
Markdown (Informal)
[Sharing User Dictionaries Across Multiple Systems with UTX-S](https://aclanthology.org/2008.amta-govandcom.3/) (Bond et al., AMTA 2008)
ACL
- Francis Bond, Seiji Okura, Yuji Yamamoto, Toshiki Murata, Kiyotaka Uchimoto, Michael Kato, Miwako Shimazu, and Tsugiyoshi Suzuki. 2008. Sharing User Dictionaries Across Multiple Systems with UTX-S. In Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Government and Commercial Uses of MT, pages 304–313, Waikiki, USA. Association for Machine Translation in the Americas.