Extracting Bilingual Multi-word Expressions for Low-resource Statistical Machine Translation

被引：0

作者：

Wei, Linyu ^{[1
,2
]}

Li, Miao ^{[2
]}

Chen, Lei ^{[2
]}

Yang, Zhenxin ^{[1
,2
]}

Sun, Kai ^{[1
,2
]}

Yuan, Man ^{[3
]}

机构：

[1] Univ Sci & Technol China, Dept Automat, Hefei, Peoples R China

[2] Chinese Acad Sci, IIM, Inst Intelligent Machines, Hefei, Peoples R China

[3] Hefei Univ Technol, HFUT, Hefei, Peoples R China

来源：

PROCEEDINGS OF 2015 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING | 2015年

关键词：

Statistical machine translation; Multi-word expression extraction; Low-resource language pair;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Improving the performance of statistical machine translation is often a significant problem, especially in low language resource scenarios such as Chinese-Mongolian SMT. In this paper, we propose a method to improve the performance of Chinese-Mongolian SMT system using multi-word expressions, which is also a pilot study for this language pair. We extract MWEs from the phrase-table then integrate the MWEs into SMT system by various strategies. Experimental results indicate our method outperforms a baseline model by 0.81 BLEU points on Test-All and 1.54 BLEU points on Test-MWE.

引用

页码：21 / 24

页数：4

共 50 条

[1] Identifying bilingual Multi-Word Expressions for Statistical Machine Translation
Bouamor, Dhouha
Semmar, Nasredine
Zweigenbaum, Pierre
LREC 2012 - EIGHTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2012, : 674 - 679
[2] Utilization of Multi-word Expressions to Improve Statistical Machine Translation of Statutory Sentences
Sakamoto, Satomi
Ogawa, Yasuhiro
Nakamura, Makoto
Ohno, Tomohiro
Toyama, Katsuhiko
NEW FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2017, 10091 : 249 - 264
[3] Machine translation and human translation of multi-word expressions: peeling this pineapple
Rebechi, Rozane Rodrigues
Marcon, Nathalia Oliva
Faller, Guilherme de Almeida
REVISTA VIRTUAL DE ESTUDOS DA LINGUAGEM-REVEL, 2025, 23 (44): : 346 - 380
[4] Multi-word Expressions in English-Latvian Machine Translation
Skadina, Inguna
BALTIC JOURNAL OF MODERN COMPUTING, 2016, 4 (04): : 811 - 825
[5] Framework for Handling Rare Word Problems in Neural Machine Translation System Using Multi-Word Expressions
Garg, Kamal Deep
Shekhar, Shashi
Kumar, Ajit
Goyal, Vishal
Sharma, Bhisham
Chengoden, Rajeswari
Srivastava, Gautam
APPLIED SCIENCES-BASEL, 2022, 12 (21):
[6] A Content Word Augmentation Method for Low-Resource Neural Machine Translation
Li, Fuxue
Zhao, Zhongchao
Chi, Chuncheng
Yan, Hong
Zhang, Zhen
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, ICIC 2023, PT IV, 2023, 14089 : 720 - 731
[7] A Bilingual Templates Data Augmentation Method for Low-Resource Neural Machine Translation
Li, Fuxue
Liu, Beibei
Yan, Hong
Shao, Mingzhi
Xie, Peijun
Li, Jiarui
Chi, Chuncheng
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT III, ICIC 2024, 2024, 14877 : 40 - 51
[8] Regressing Word and Sentence Embeddings for Low-Resource Neural Machine Translation
Unanue I.J.
Borzeshi E.Z.
Piccardi M.
IEEE Transactions on Artificial Intelligence, 2023, 4 (03): : 450 - 463
[9] Augmenting Training Data for Low-Resource Neural Machine Translation via Bilingual Word Embeddings and BERT Language Modelling
Ramesh, Akshai
Uhana, Haque Usuf
Parthasarathy, Venkatesh Balavadhani
Haque, Rejwanul
Way, Andy
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
[10] Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages
Duh, Kevin
McNamee, Paul
Post, Matt
Thompson, Brian
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), 2020, : 2667 - 2675

← 1 2 3 4 5 →