@inproceedings{wang-etal-2021-ji-yu-duo,
title = "基于多层次预训练策略和多任务学习的端到端蒙汉语音翻译(End-to-end {M}ongolian-{C}hinese Speech Translation Based on Multi-level Pre-training Strategies and Multi-task Learning)",
author = "Wang, Ningning and
Fei, Long and
Zhang, Hui",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.15",
pages = "156--165",
abstract = "端到端语音翻译将源语言语音直接翻译为目标语言文本,它需要{``}源语言语音-目标语言文本{''}作为训练数据,然而这类数据极其稀缺,本文提出了一种多层次预训练策略和多任务学习相结合的训练方法,首先分别对语音识别和机器翻译模型的各个模块进行多层次预训练,接着将语音识别和机器翻译模型连接起来构成语音翻译模型,然后使用迁移学习对预训练好的模型进行多步骤微调,在此过程中又运用多任务学习的方法,将语音识别作为语音翻译的一个辅助任务来组织训练,充分利用了已经存在的各种不同形式的数据来训练端到端模型,首次将端到端技术应用于资源受限条件下的蒙汉语音翻译,构建了首个翻译质量较高、实际可用的端到端蒙汉语音翻译系统。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-ji-yu-duo">
<titleInfo>
<title>基于多层次预训练策略和多任务学习的端到端蒙汉语音翻译(End-to-end Mongolian-Chinese Speech Translation Based on Multi-level Pre-training Strategies and Multi-task Learning)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ningning</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>端到端语音翻译将源语言语音直接翻译为目标语言文本,它需要“源语言语音-目标语言文本”作为训练数据,然而这类数据极其稀缺,本文提出了一种多层次预训练策略和多任务学习相结合的训练方法,首先分别对语音识别和机器翻译模型的各个模块进行多层次预训练,接着将语音识别和机器翻译模型连接起来构成语音翻译模型,然后使用迁移学习对预训练好的模型进行多步骤微调,在此过程中又运用多任务学习的方法,将语音识别作为语音翻译的一个辅助任务来组织训练,充分利用了已经存在的各种不同形式的数据来训练端到端模型,首次将端到端技术应用于资源受限条件下的蒙汉语音翻译,构建了首个翻译质量较高、实际可用的端到端蒙汉语音翻译系统。</abstract>
<identifier type="citekey">wang-etal-2021-ji-yu-duo</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.15</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>156</start>
<end>165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于多层次预训练策略和多任务学习的端到端蒙汉语音翻译(End-to-end Mongolian-Chinese Speech Translation Based on Multi-level Pre-training Strategies and Multi-task Learning)
%A Wang, Ningning
%A Fei, Long
%A Zhang, Hui
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G Chinese
%F wang-etal-2021-ji-yu-duo
%X 端到端语音翻译将源语言语音直接翻译为目标语言文本,它需要“源语言语音-目标语言文本”作为训练数据,然而这类数据极其稀缺,本文提出了一种多层次预训练策略和多任务学习相结合的训练方法,首先分别对语音识别和机器翻译模型的各个模块进行多层次预训练,接着将语音识别和机器翻译模型连接起来构成语音翻译模型,然后使用迁移学习对预训练好的模型进行多步骤微调,在此过程中又运用多任务学习的方法,将语音识别作为语音翻译的一个辅助任务来组织训练,充分利用了已经存在的各种不同形式的数据来训练端到端模型,首次将端到端技术应用于资源受限条件下的蒙汉语音翻译,构建了首个翻译质量较高、实际可用的端到端蒙汉语音翻译系统。
%U https://aclanthology.org/2021.ccl-1.15
%P 156-165
Markdown (Informal)
[基于多层次预训练策略和多任务学习的端到端蒙汉语音翻译(End-to-end Mongolian-Chinese Speech Translation Based on Multi-level Pre-training Strategies and Multi-task Learning)](https://aclanthology.org/2021.ccl-1.15) (Wang et al., CCL 2021)
ACL