@inproceedings{tu-etal-2012-universal,
title = "A universal approach to translating numerical and time expressions",
author = "Tu, Mei and
Zhou, Yu and
Zong, Chengqing",
booktitle = "Proceedings of the 9th International Workshop on Spoken Language Translation: Papers",
month = dec # " 6-7",
year = "2012",
address = "Hong Kong, Table of contents",
url = "https://aclanthology.org/2012.iwslt-papers.9/",
pages = "209--216",
abstract = "Although statistical machine translation (SMT) has made great progress since it came into being, the translation of numerical and time expressions is still far from satisfactory. Generally speaking, numbers are likely to be out-of-vocabulary (OOV) words due to their non-exhaustive characteristics even when the size of training data is very large, so it is difficult to obtain accurate translation results for the infinite set of numbers only depending on traditional statistical methods. We propose a language-independent framework to recognize and translate numbers more precisely by using a rule-based method. Through designing operators, we succeed to make rules educible and totally separate from codes, thus, we can extend rules to various language-pairs without re-coding, which contributes a lot to the efficient development of an SMT system with good portability. We classify numbers and time expressions into seven types, which are Arabic number, cardinal numbers, ordinal numbers, date, time of day, day of week and figures. A greedy algorithm is developed to deal with rule conflicts. Experiments have shown that our approach can significantly improve the translation performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2012-universal">
<titleInfo>
<title>A universal approach to translating numerical and time expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-dec 6-7</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Spoken Language Translation: Papers</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Hong Kong, Table of contents</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although statistical machine translation (SMT) has made great progress since it came into being, the translation of numerical and time expressions is still far from satisfactory. Generally speaking, numbers are likely to be out-of-vocabulary (OOV) words due to their non-exhaustive characteristics even when the size of training data is very large, so it is difficult to obtain accurate translation results for the infinite set of numbers only depending on traditional statistical methods. We propose a language-independent framework to recognize and translate numbers more precisely by using a rule-based method. Through designing operators, we succeed to make rules educible and totally separate from codes, thus, we can extend rules to various language-pairs without re-coding, which contributes a lot to the efficient development of an SMT system with good portability. We classify numbers and time expressions into seven types, which are Arabic number, cardinal numbers, ordinal numbers, date, time of day, day of week and figures. A greedy algorithm is developed to deal with rule conflicts. Experiments have shown that our approach can significantly improve the translation performance.</abstract>
<identifier type="citekey">tu-etal-2012-universal</identifier>
<location>
<url>https://aclanthology.org/2012.iwslt-papers.9/</url>
</location>
<part>
<date>2012-dec 6-7</date>
<extent unit="page">
<start>209</start>
<end>216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A universal approach to translating numerical and time expressions
%A Tu, Mei
%A Zhou, Yu
%A Zong, Chengqing
%S Proceedings of the 9th International Workshop on Spoken Language Translation: Papers
%D 2012
%8 dec 6 7
%C Hong Kong, Table of contents
%F tu-etal-2012-universal
%X Although statistical machine translation (SMT) has made great progress since it came into being, the translation of numerical and time expressions is still far from satisfactory. Generally speaking, numbers are likely to be out-of-vocabulary (OOV) words due to their non-exhaustive characteristics even when the size of training data is very large, so it is difficult to obtain accurate translation results for the infinite set of numbers only depending on traditional statistical methods. We propose a language-independent framework to recognize and translate numbers more precisely by using a rule-based method. Through designing operators, we succeed to make rules educible and totally separate from codes, thus, we can extend rules to various language-pairs without re-coding, which contributes a lot to the efficient development of an SMT system with good portability. We classify numbers and time expressions into seven types, which are Arabic number, cardinal numbers, ordinal numbers, date, time of day, day of week and figures. A greedy algorithm is developed to deal with rule conflicts. Experiments have shown that our approach can significantly improve the translation performance.
%U https://aclanthology.org/2012.iwslt-papers.9/
%P 209-216
Markdown (Informal)
[A universal approach to translating numerical and time expressions](https://aclanthology.org/2012.iwslt-papers.9/) (Tu et al., IWSLT 2012)
ACL