Chinese-Vietnamese neural machine translation model incorporating entity translation

doi:10.11772/j.issn.1001-9081.2023121880

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (1): 69-74.DOI: 10.11772/j.issn.1001-9081.2023121880

• Artificial intelligence • Previous Articles Next Articles

Chinese-Vietnamese neural machine translation model incorporating entity translation

Shengxiang GAO¹^,²(), Zhe HOU¹^,², Zhengtao YU¹^,², Hua LAI¹^,²

^1.Faculty of Information Engineering and Automation，Kunming University of Science and Technology，Kunming Yunnan 650504，China
^2.Key Laboratory of Artificial Intelligence in Yunnan Province （Kunming University of Science and Technology），Kunming Yunnan 650504，China

Received:2024-01-11 Revised:2024-04-07 Accepted:2024-04-10 Online:2024-05-07 Published:2025-01-10
Contact: Shengxiang GAO
About author:HOU Zhe， born in 1997， M. S. candidate. His research interests include natural language processing， machine translation.
YU Zhengtao， born in 1970， Ph. D.， professor. His research interests include natural language processing， machine translation， information retrieval， network security.
LAI Hua， born in 1966， M. S.， associate professor. His research interests include intelligent information processing， complex process control.
Supported by:
National Natural Science Foundation of China(62376111);Yunnan High-Tech Industry Development Project(201606);Yunnan Provincial Key Research and Development Program(202303AP140008);Yunnan Provincial Basic Research Program(202001AS070014);Yunnan Provincial Science and Technology Talent and Platform Program(202105AC160018)

融入实体翻译的汉越神经机器翻译模型

高盛祥¹^,²(), 侯哲¹^,², 余正涛¹^,², 赖华¹^,²

^1.昆明理工大学信息工程与自动化学院，昆明 650504
^2.云南省人工智能重点实验室（昆明理工大学），昆明 650504

通讯作者: 高盛祥
作者简介:侯哲（1997—），男，山西大同人，硕士研究生，主要研究方向：自然语言处理、机器翻译；
余正涛（1970—），男，云南曲靖人，教授，博士，CCF会员，主要研究方向：自然语言处理、机器翻译、信息检索、网络安全；
赖华（1966—），男，云南昆明人，副教授，硕士，主要研究方向：智能信息处理、复杂过程控制。
基金资助:
国家自然科学基金资助项目(62376111);云南高新技术产业发展项目(201606);云南省重大科技专项计划项目(202303AP140008);云南省基础研究计划项目(202001AS070014);云南省科技人才与平台计划项目(202105AC160018)

Abstract

Abstract:

In low-resource Chinese-Vietnamese translation tasks， translating entity words in sentences accurately is a significant challenge. In order to solve the problems such as the low frequency of entity words in training corpus and the inability of the model to construct the mapping relationship between bilingual entity words， a Chinese-Vietnamese neural machine translation model that incorporates entity translation was constructed. Firstly， the translation results of entity words in the source sentence were obtained through a Chinese-Vietnamese bilingual entity dictionary. Then， these results were concatenated at the end of the source sentence as input to the model， and the “constraint prompt information” was introduced at the encoding end to enhance representation. Finally， a pointer network mechanism was integrated at the decoding end to ensure that the model was able to replicate the vocabulary of the source sentence. Experimental results show that this model achieves increases of 1.37 and 0.21 points in BiLingual Evaluation Understudy （BLEU） for Chinese-Vietnamese translation and Vietnamese-Chinese translation compared to the cross-lingual language model — XLM-R （Cross-lingual Language Model-RoBERTa） and shortens training time by 3.19% and 3.50% compared to Transformer for Chinese-Vietnamese translation and Vietnamese-Chinese translation， enhancing the comprehensive performance of entity word translation in sentences effectively.

Key words: Chinese-Vietnamese neural machine translation, entity translation, bilingual dictionary, pointer network, low-resource

摘要：

在汉越低资源翻译任务中，句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低，模型无法构建双语实体词之间的映射关系等问题，构建一种融入实体翻译的汉越神经机器翻译模型。首先，通过汉越实体双语词典预先获取源句中实体词的翻译结果；其次，将结果拼接在源句末端作为模型的输入，同时在编码端引入“约束提示信息”增强表征；最后，在解码端融入指针网络机制，以确保模型能复制输出源端句的词汇。实验结果表明，该模型相较于跨语言模型XLM-R （Cross-lingual Language Model-RoBERTa）的双语评估替补（BLEU）值在汉越方向提升了1.37，越汉方向提升了0.21，时间性能上相较于Transformer该模型在汉越方向和越汉方向分别缩短3.19%和3.50%，可有效地提升句子中实体词翻译的综合性能。

关键词: 汉越神经机器翻译, 实体翻译, 双语词典, 指针网络, 低资源

CLC Number:

TP391.21

Shengxiang GAO, Zhe HOU, Zhengtao YU, Hua LAI. Chinese-Vietnamese neural machine translation model incorporating entity translation[J]. Journal of Computer Applications, 2025, 45(1): 69-74.

高盛祥, 侯哲, 余正涛, 赖华. 融入实体翻译的汉越神经机器翻译模型[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 69-74.

Figures/Tables 8

References 17

1	RANATHUNGA S， LEE E S A， PRIFTI SKENDULI M P， et al. Neural machine translation for low-resource languages： a survey ［J］. ACM Computing Surveys， 2023， 55（11）： No.229.
2	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
3	LI B， HOU Y， CHE W. Data augmentation approaches in natural language processing： a survey ［J］. AI Open， 2022， 3： 71-90.
4	DEVLIN J， CHANG M W， LEE K， et al. BERT： pre-training of deep bidirectional transformers for language understanding ［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1（Long and Short Papers）. Stroudsburg： ACL， 2019： 4171-4186.
5	CHEN G， CHEN Y， WANG Y， et al. Lexical-constraint-aware neural machine translation via data augmentation ［C］// Proceedings of the 29th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2021： 3587-3593.
6	ZHANG J， LUAN H， SUN M， et al. Neural machine translation with explicit phrase alignment ［J］. IEEE/ACM Transactions on Audio， Speech， and Language Processing， 2021， 29： 1001-1010.
7	WU Y， SCHUSTER M， CHEN Z， et al. Google’s neural machine translation system： bridging the gap between human and machine translation ［EB/OL］. ［2023-05-10］. .
8	SAUNDERS D， STAHLBERG F， DE GISPERT A， et al. Multi-representation ensembles and delayed SGD updates improve syntax-based NMT ［C］// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics （Volume 2： Short Papers）. Stroudsburg： ACL， 2018： 319-325.
9	SONG K， ZHANG Y， YU H， et al. Code-switching for enhancing NMT with pre-specified translation ［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1（Long and Short Papers）. Stroudsburg： ACL， 2019： 449-459.
10	DINU G， MATHUR P， FEDERICO M， et al. Training neural machine translation to apply terminology constraints ［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 3063-3068.
11	HOKAMP C， LIU Q. Lexically constrained decoding for sequence generation using grid beam search ［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2017： 1535-1546.
12	POST M， VILAR D. Fast lexically constrained decoding with dynamic beam allocation for neural machine translation ［C］// Proceedings of the 2018 North American Chapter of the Association for Computational Linguistics， Volume 1 （Long Papers）. Stroudsburg： ACL， 2018： 1314-1324.
13	张乐乐，郭军军，王繁.基于预训练跨语言模型及交互注意力的平行句对抽取方法［J］.通信技术， 2022， 55（4）： 443-452.
	ZHANG L L， GUO J J， WANG F. Parallel sentence pair extraction method based on pre-training cross-language model and interactive attention ［J］. Communications Technology， 2022， 55（4）： 443-452.
14	HU Y， LIU Y， LV S， et al. DCCRN： deep complex convolution recurrent network for phase-aware speech enhancement ［C］// Proceedings of the INTERSPEECH 2020. ［S.l.］： International Speech Communication Association， 2020： 2472-2476.
15	FERNANDES P， YIN K， LIU E， et al. When does translation require context？ a data-driven， multilingual exploration ［C］// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg： ACL， 2023： 606-626.
16	NGUYEN X P， JOTY S， HOI S C H， et al. Tree-structured attention with hierarchical accumulation ［EB/OL］. ［2023-05-10］. .
17	BUGLIARELLO E， OKAZAKI N. Enhancing machine translation with dependency-aware self-attention ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020： 1618-1627.

约束类别	模型	BLEU
约束类别	模型	汉语→越语方向	越语→汉语方向
硬约束	GBS	23.67	22.19
	DBA	23.69	22.23
	POINTER	23.59	22.21
软约束	占位符法	22.38	21.07
	LeCA	22.75	21.43
	LeCA+Ptr	23.37	21.94
本文约束	本文模型	23.78	22.36

约束类别	模型	BLEU
约束类别	模型	汉语→越语方向	越语→汉语方向
硬约束	GBS	23.67	22.19
	DBA	23.69	22.23
	POINTER	23.59	22.21
软约束	占位符法	22.38	21.07
	LeCA	22.75	21.43
	LeCA+Ptr	23.37	21.94
本文约束	本文模型	23.78	22.36

模型	BLEU
模型	汉语→越语方向	越语→汉语方向
Transformer	20.94	19.83
ConvS2S^［15］	18.36	17.84
DATNMT^［16］	21.26	19.86
HySAN^［17］	21.88	20.59
XLM	22.36	22.09
XLM-R	22.41	22.15
本文模型	23.78	22.36

模型	BLEU
模型	汉语→越语方向	越语→汉语方向
Transformer	20.94	19.83
ConvS2S^［15］	18.36	17.84
DATNMT^［16］	21.26	19.86
HySAN^［17］	21.88	20.59
XLM	22.36	22.09
XLM-R	22.41	22.15
本文模型	23.78	22.36

模型	时间
模型	汉语→越语方向	越语→汉语方向
Transformer	65.9	62.8
ConvS2S^［15］	68.3	66.8
DATNMT^［16］	71.2	69.8
HySAN^［17］	71.8	70.5
XLM	74.3	73.9
XLM-R	73.3	72.1
本文模型	63.8	60.6

Chinese-Vietnamese neural machine translation model incorporating entity translation

融入实体翻译的汉越神经机器翻译模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 17

Related Articles 4

Recommended Articles

Metrics

汉语例句	模型	越南语
我们在乎的是我们如何赚取利润。	参考译文	Chúng tôi（我们） quan tâm（在乎） là（在句中表语气组词） chúng tôi（我们） làm ra（赚取） lợi nhuận（利润） như thế nào（如何）.
	Transformer	Chúng tôi（我们） quan tâm（在乎） chúng tôi（我们） làm ra（赚取） lợi nhuận（利润） như thế nào（如何）.
	本文模型	Chúng tôi（我们） quan tâm（在乎） là（在句中表语气组词） chúng tôi（我们） làm ra（赚取） lợi nhuận（利润） như thế nào（如何）.

汉语例句	模型	越南语
越南水运主要港口位于河内。	参考译文	Cảng（港口） chính của giao thông đường thủy Việt Nam（越南） được đặt tại Hà Nội（河内）.
	Transformer	đảo cảng（港岛） chính của giao thông đường thủy Việt Nam được đặt tại Hà Lan（荷兰）
	本文模型	Cảng chính của giao thông đường thủy Việt Nam được đặt tại Hà Nội.

[1]	Bin LI, Min LIN, Siriguleng, Yingjie GAO, Yurong WANG, Shujun ZHANG. Joint entity-relation extraction method for ancient Chinese books based on prompt learning and global pointer network [J]. Journal of Computer Applications, 2025, 45(1): 75-81.
[2]	Yu XU, Yunyou ZHU, Xiao LIU, Yuting DENG, Yong LIAO. Multi-objective routing optimization of electric power material distribution based on deep reinforcement learning [J]. Journal of Computer Applications, 2022, 42(10): 3252-3258.
[3]	JIA Chengxun, LAI Hua, YU Zhengtao, WEN Yonghua, YU Zhiqiang. Chinese-Vietnamese pseudo-parallel corpus generation based on monolingual language model [J]. Journal of Computer Applications, 2021, 41(6): 1652-1658.
[4]	QIN Chuxiong, ZHANG Lianhai. Acoustic modeling approach of multi-stream feature incorporated convolutional neural network for low-resource speech recognition [J]. Journal of Computer Applications, 2016, 36(9): 2609-2615.

模型	BLEU
模型	汉语→越语方向	越语→汉语方向
Transformer	19.94	18.83
本文模型-约束提示	22.37	20.94
本文模型-指针网络	20.23	19.18
本文模型	22.78	21.36

模型	BLEU
模型	汉语→越语方向	越语→汉语方向
Transformer	19.94	18.83
本文模型-约束提示	22.37	20.94
本文模型-指针网络	20.23	19.18
本文模型	22.78	21.36