@inproceedings{feiyu-etal-2021-incorporating,
title = "Incorporating translation quality estimation into {C}hinese-{K}orean neural machine translation",
author = "Feiyu, Li and
Yahui, Zhao and
Feiyang, Yang and
Rongyi, Cui",
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-1.81",
pages = "906--915",
abstract = "Exposure bias and poor translation diversity are two common problems in neural machine trans-lation (NMT) which are caused by the general of the teacher forcing strategy for training inthe NMT models. Moreover the NMT models usually require the large-scale and high-quality parallel corpus. However Korean is a low resource language and there is no large-scale parallel corpus between Chinese and Korean which is a challenging for the researchers. Therefore wepropose a method which is to incorporate translation quality estimation into the translation processand adopt reinforcement learning. The evaluation mechanism is used to guide the training of the model so that the prediction cannot converge completely to the ground truth word. When the model predicts a sequence different from the ground truth word the evaluation mechanism cangive an appropriate evaluation and reward to the model. In addition we alleviated the lack of Korean corpus resources by adding training data. In our experiment we introduce a monolingual corpus of a certain scale to construct pseudo-parallel data. At the same time we also preprocessed the Korean corpus with different granularities to overcome the data sparsity. Experimental results show that our work is superior to the baselines in Chinese-Korean and Korean-Chinese translation tasks which fully certificates the effectiveness of our method.",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feiyu-etal-2021-incorporating">
<titleInfo>
<title>Incorporating translation quality estimation into Chinese-Korean neural machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Feiyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Yahui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feiyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cui</namePart>
<namePart type="family">Rongyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</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>Exposure bias and poor translation diversity are two common problems in neural machine trans-lation (NMT) which are caused by the general of the teacher forcing strategy for training inthe NMT models. Moreover the NMT models usually require the large-scale and high-quality parallel corpus. However Korean is a low resource language and there is no large-scale parallel corpus between Chinese and Korean which is a challenging for the researchers. Therefore wepropose a method which is to incorporate translation quality estimation into the translation processand adopt reinforcement learning. The evaluation mechanism is used to guide the training of the model so that the prediction cannot converge completely to the ground truth word. When the model predicts a sequence different from the ground truth word the evaluation mechanism cangive an appropriate evaluation and reward to the model. In addition we alleviated the lack of Korean corpus resources by adding training data. In our experiment we introduce a monolingual corpus of a certain scale to construct pseudo-parallel data. At the same time we also preprocessed the Korean corpus with different granularities to overcome the data sparsity. Experimental results show that our work is superior to the baselines in Chinese-Korean and Korean-Chinese translation tasks which fully certificates the effectiveness of our method.</abstract>
<identifier type="citekey">feiyu-etal-2021-incorporating</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.81</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>906</start>
<end>915</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating translation quality estimation into Chinese-Korean neural machine translation
%A Feiyu, Li
%A Yahui, Zhao
%A Feiyang, Yang
%A Rongyi, Cui
%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 English
%F feiyu-etal-2021-incorporating
%X Exposure bias and poor translation diversity are two common problems in neural machine trans-lation (NMT) which are caused by the general of the teacher forcing strategy for training inthe NMT models. Moreover the NMT models usually require the large-scale and high-quality parallel corpus. However Korean is a low resource language and there is no large-scale parallel corpus between Chinese and Korean which is a challenging for the researchers. Therefore wepropose a method which is to incorporate translation quality estimation into the translation processand adopt reinforcement learning. The evaluation mechanism is used to guide the training of the model so that the prediction cannot converge completely to the ground truth word. When the model predicts a sequence different from the ground truth word the evaluation mechanism cangive an appropriate evaluation and reward to the model. In addition we alleviated the lack of Korean corpus resources by adding training data. In our experiment we introduce a monolingual corpus of a certain scale to construct pseudo-parallel data. At the same time we also preprocessed the Korean corpus with different granularities to overcome the data sparsity. Experimental results show that our work is superior to the baselines in Chinese-Korean and Korean-Chinese translation tasks which fully certificates the effectiveness of our method.
%U https://aclanthology.org/2021.ccl-1.81
%P 906-915
Markdown (Informal)
[Incorporating translation quality estimation into Chinese-Korean neural machine translation](https://aclanthology.org/2021.ccl-1.81) (Feiyu et al., CCL 2021)
ACL