@inproceedings{aiti-etal-2005-input,
title = "Input Normalization for an {E}nglish-to-{C}hinese {SMS} Translation System",
author = "AiTi, Aw and
Min, Zhang and
PohKhim, Yeo and
ZhenZhen, Fan and
Jian, Su",
booktitle = "Proceedings of Machine Translation Summit X: Posters",
month = sep # " 13-15",
year = "2005",
address = "Phuket, Thailand",
url = "https://aclanthology.org/2005.mtsummit-posters.18/",
pages = "445--450",
abstract = "This paper describes an approach to preprocess SMS text for Machine Translation. As SMS text behaves differently from normal written text and to reduce the tremendous effort required to customize or adapt the language model of the traditional translation system to handle SMS text style, normalization is performed to moderate the irregularities in English SMS text using a noisy channel model. A mapping model is used to model the three major problems in SMS text. They are (1) substitution of word using non-standard acronym, (2) insertion of flavour word, and (3) omission of auxiliary verb and subject pronoun. Experiment results show that with normalization before translation, the rejection rate of our English-to-Chinese SMS translation for broadcasting purpose is reduced by 15.5{\%}. We believe that the performance of normalization can be further improved with deeper linguistic processing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aiti-etal-2005-input">
<titleInfo>
<title>Input Normalization for an English-to-Chinese SMS Translation System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aw</namePart>
<namePart type="family">AiTi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeo</namePart>
<namePart type="family">PohKhim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">ZhenZhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="family">Jian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2005-sep 13-15</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit X: Posters</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Phuket, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an approach to preprocess SMS text for Machine Translation. As SMS text behaves differently from normal written text and to reduce the tremendous effort required to customize or adapt the language model of the traditional translation system to handle SMS text style, normalization is performed to moderate the irregularities in English SMS text using a noisy channel model. A mapping model is used to model the three major problems in SMS text. They are (1) substitution of word using non-standard acronym, (2) insertion of flavour word, and (3) omission of auxiliary verb and subject pronoun. Experiment results show that with normalization before translation, the rejection rate of our English-to-Chinese SMS translation for broadcasting purpose is reduced by 15.5%. We believe that the performance of normalization can be further improved with deeper linguistic processing.</abstract>
<identifier type="citekey">aiti-etal-2005-input</identifier>
<location>
<url>https://aclanthology.org/2005.mtsummit-posters.18/</url>
</location>
<part>
<date>2005-sep 13-15</date>
<extent unit="page">
<start>445</start>
<end>450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Input Normalization for an English-to-Chinese SMS Translation System
%A AiTi, Aw
%A Min, Zhang
%A PohKhim, Yeo
%A ZhenZhen, Fan
%A Jian, Su
%S Proceedings of Machine Translation Summit X: Posters
%D 2005
%8 sep 13 15
%C Phuket, Thailand
%F aiti-etal-2005-input
%X This paper describes an approach to preprocess SMS text for Machine Translation. As SMS text behaves differently from normal written text and to reduce the tremendous effort required to customize or adapt the language model of the traditional translation system to handle SMS text style, normalization is performed to moderate the irregularities in English SMS text using a noisy channel model. A mapping model is used to model the three major problems in SMS text. They are (1) substitution of word using non-standard acronym, (2) insertion of flavour word, and (3) omission of auxiliary verb and subject pronoun. Experiment results show that with normalization before translation, the rejection rate of our English-to-Chinese SMS translation for broadcasting purpose is reduced by 15.5%. We believe that the performance of normalization can be further improved with deeper linguistic processing.
%U https://aclanthology.org/2005.mtsummit-posters.18/
%P 445-450
Markdown (Informal)
[Input Normalization for an English-to-Chinese SMS Translation System](https://aclanthology.org/2005.mtsummit-posters.18/) (AiTi et al., MTSummit 2005)
ACL