@inproceedings{kim-etal-2021-translation,
title = "Translation Memory Retrieval Using Lucene",
author = "Kim, Kwang-hyok and
Cho, Myong-ho and
Ryang, Chol-ho and
Im, Ju-song and
Cho, Song-yong and
Han, Yong-jun",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.78",
pages = "684--691",
abstract = "Translation Memory (TM) system, a major component of computer-assisted translation (CAT), is widely used to improve human translators{'} productivity by making effective use of previously translated resource. We propose a method to achieve high-speed retrieval from a large translation memory by means of similarity evaluation based on vector model, and present the experimental result. Through our experiment using Lucene, an open source information retrieval search engine, we conclude that it is possible to achieve real-time retrieval speed of about tens of microseconds even for a large translation memory with 5 million segment pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2021-translation">
<titleInfo>
<title>Translation Memory Retrieval Using Lucene</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kwang-hyok</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myong-ho</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chol-ho</namePart>
<namePart type="family">Ryang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ju-song</namePart>
<namePart type="family">Im</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Song-yong</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong-jun</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translation Memory (TM) system, a major component of computer-assisted translation (CAT), is widely used to improve human translators’ productivity by making effective use of previously translated resource. We propose a method to achieve high-speed retrieval from a large translation memory by means of similarity evaluation based on vector model, and present the experimental result. Through our experiment using Lucene, an open source information retrieval search engine, we conclude that it is possible to achieve real-time retrieval speed of about tens of microseconds even for a large translation memory with 5 million segment pairs.</abstract>
<identifier type="citekey">kim-etal-2021-translation</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.78</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>684</start>
<end>691</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation Memory Retrieval Using Lucene
%A Kim, Kwang-hyok
%A Cho, Myong-ho
%A Ryang, Chol-ho
%A Im, Ju-song
%A Cho, Song-yong
%A Han, Yong-jun
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F kim-etal-2021-translation
%X Translation Memory (TM) system, a major component of computer-assisted translation (CAT), is widely used to improve human translators’ productivity by making effective use of previously translated resource. We propose a method to achieve high-speed retrieval from a large translation memory by means of similarity evaluation based on vector model, and present the experimental result. Through our experiment using Lucene, an open source information retrieval search engine, we conclude that it is possible to achieve real-time retrieval speed of about tens of microseconds even for a large translation memory with 5 million segment pairs.
%U https://aclanthology.org/2021.ranlp-1.78
%P 684-691
Markdown (Informal)
[Translation Memory Retrieval Using Lucene](https://aclanthology.org/2021.ranlp-1.78) (Kim et al., RANLP 2021)
ACL
- Kwang-hyok Kim, Myong-ho Cho, Chol-ho Ryang, Ju-song Im, Song-yong Cho, and Yong-jun Han. 2021. Translation Memory Retrieval Using Lucene. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 684–691, Held Online. INCOMA Ltd..