@inproceedings{wenjuan-etal-2024-ji,
title = "基于隐性句逗号识别的汉语长句机器翻译(Machine translation of {C}hinese long sentences based on recognition of implicit period and comma)",
author = "Wenjuan, Zhang and
Manjia, Li and
Wenhe, Feng",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.14/",
pages = "197--205",
language = "zho",
abstract = "{\textquotedblleft}长句翻译一直是机器翻译的难题。本文根据汉语中相当数量的逗号(句内标点)和句号(句间标点)可相互转化的特点,提出{\textquotedblright}隐性句号{\textquotedblright}(可转化为句号的逗号)和{\textquotedblright}隐性逗号{\textquotedblright}(可转化为逗号的句号)概念,并实现其自动识别,以将汉语长句变为短句用于汉英机器翻译。为此,首先通过人工与半监督学习结合方法构建了一个隐性句逗数据集,实现了基于预训练模型的隐性句逗识别方法,其中性能最好的HierarchicalBERT作为后续应用模型。进而,实现了基于隐性句逗识别的汉英机器翻译方法。在WMT2018(新闻)和WMT2023(文学)测试语料上基于预训练机器翻译模型的实验表明,对于汉语长句的英译,本文方法相比基准翻译的BLEU值整体有所提高,而且在相对稳健机器翻译模型上,呈现为句子越长本文方法效果越明显。{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wenjuan-etal-2024-ji">
<titleInfo>
<title>基于隐性句逗号识别的汉语长句机器翻译(Machine translation of Chinese long sentences based on recognition of implicit period and comma)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Wenjuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Manjia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Wenhe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“长句翻译一直是机器翻译的难题。本文根据汉语中相当数量的逗号(句内标点)和句号(句间标点)可相互转化的特点,提出”隐性句号”(可转化为句号的逗号)和”隐性逗号”(可转化为逗号的句号)概念,并实现其自动识别,以将汉语长句变为短句用于汉英机器翻译。为此,首先通过人工与半监督学习结合方法构建了一个隐性句逗数据集,实现了基于预训练模型的隐性句逗识别方法,其中性能最好的HierarchicalBERT作为后续应用模型。进而,实现了基于隐性句逗识别的汉英机器翻译方法。在WMT2018(新闻)和WMT2023(文学)测试语料上基于预训练机器翻译模型的实验表明,对于汉语长句的英译,本文方法相比基准翻译的BLEU值整体有所提高,而且在相对稳健机器翻译模型上,呈现为句子越长本文方法效果越明显。”</abstract>
<identifier type="citekey">wenjuan-etal-2024-ji</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.14/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>197</start>
<end>205</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于隐性句逗号识别的汉语长句机器翻译(Machine translation of Chinese long sentences based on recognition of implicit period and comma)
%A Wenjuan, Zhang
%A Manjia, Li
%A Wenhe, Feng
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G zho
%F wenjuan-etal-2024-ji
%X “长句翻译一直是机器翻译的难题。本文根据汉语中相当数量的逗号(句内标点)和句号(句间标点)可相互转化的特点,提出”隐性句号”(可转化为句号的逗号)和”隐性逗号”(可转化为逗号的句号)概念,并实现其自动识别,以将汉语长句变为短句用于汉英机器翻译。为此,首先通过人工与半监督学习结合方法构建了一个隐性句逗数据集,实现了基于预训练模型的隐性句逗识别方法,其中性能最好的HierarchicalBERT作为后续应用模型。进而,实现了基于隐性句逗识别的汉英机器翻译方法。在WMT2018(新闻)和WMT2023(文学)测试语料上基于预训练机器翻译模型的实验表明,对于汉语长句的英译,本文方法相比基准翻译的BLEU值整体有所提高,而且在相对稳健机器翻译模型上,呈现为句子越长本文方法效果越明显。”
%U https://aclanthology.org/2024.ccl-1.14/
%P 197-205
Markdown (Informal)
[基于隐性句逗号识别的汉语长句机器翻译(Machine translation of Chinese long sentences based on recognition of implicit period and comma)](https://aclanthology.org/2024.ccl-1.14/) (Wenjuan et al., CCL 2024)
ACL