Survey of Low-Resource Machine Translation

被引：22

作者：

Haddow, Barry ^{[1
]}

Bawden, Rachel ^{[2
]}

Barone, Antonio Valerio Miceli ^{[1
]}

Helcl, Jindrich ^{[1
]}

Birch, Alexandra ^{[1
]}

机构：

[1] Univ Edinburgh, Sch Informat, Edinburgh, Scotland

[2] Inria, Paris, France

来源：

COMPUTATIONAL LINGUISTICS | 2022年 / 48卷 / 03期

基金：

英国工程与自然科学研究理事会;

关键词：

D O I：

10.1162/coli_a_00446

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a survey covering the state of the art in low-resource machine translation (MT) research. There are currently around 7,000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a summary of this topical research field and provide a description of the techniques evaluated by researchers in several recent shared tasks in low-resource MT.

引用

页码：673 / 732

页数：60

共 50 条

[1] A Survey on Low-Resource Neural Machine Translation
Wang, Rui
Tan, Xu
Luo, Renqian
Qin, Tao
Liu, Tie-Yan
[J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4636 - 4643
[2] A Survey on Low-resource Neural Machine Translation
Li, Hong-Zheng
Feng, Chong
Huang, He-Yan
[J]. Zidonghua Xuebao/Acta Automatica Sinica, 2021, 47 (06): : 1217 - 1231
[3] Neural Machine Translation for Low-resource Languages: A Survey
Ranathunga, Surangika
Lee, En-Shiun Annie
Skenduli, Marjana Prifti
Shekhar, Ravi
Alam, Mehreen
Kaur, Rishemjit
[J]. ACM COMPUTING SURVEYS, 2023, 55 (11)
[4] Translation Memories as Baselines for Low-Resource Machine Translation
Knowles, Rebecca
Littell, Patrick
[J]. LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 6759 - 6767
[5] Machine Translation into Low-resource Language Varieties
Kumar, Sachin
Anastasopoulos, Antonios
Wintner, Shuly
Tsvetkov, Yulia
[J]. ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 110 - 121
[6] Transformers for Low-resource Neural Machine Translation
Gezmu, Andargachew Mekonnen
Nuernberger, Andreas
[J]. ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 1, 2022, : 459 - 466
[7] The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
Ahia, Orevaoghene
Kreutzer, Julia
Hooker, Sara
[J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 3316 - 3333
[8] OCR Improves Machine Translation for Low-Resource Languages
Ignat, Oana
Maillard, Jean
Chaudhary, Vishrav
Guzman, Francisco
[J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), 2022, : 1164 - 1174
[9] Decoding Strategies for Improving Low-Resource Machine Translation
Park, Chanjun
Yang, Yeongwook
Park, Kinam
Lim, Heuiseok
[J]. ELECTRONICS, 2020, 9 (10) : 1 - 15
[10] Low-resource Neural Machine Translation: Methods and Trends
Shi, Shumin
Wu, Xing
Su, Rihai
Huang, Heyan
[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2022, 21 (05)

← 1 2 3 4 5 →