We introduce a method for transliteration generation that can produce transliterations in every language. Where previous results are only as multilingual as Wikipedia, we show how to use training data from Wikipedia as surrogate training for any language. Thus, the problem becomes one of ranking Wikipedia languages in order of suitability with respect to a target language. We introduce several task-specific methods for ranking languages, and show that our approach is comparable to the oracle ceiling, and even outperforms it in some cases.
Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP
Nilekani Centre at AI4Bharat(AI4Bharat的Nilekani中心);Indian Institute of Technology Madras(印度理工学院马德拉斯分校);Indian Institute of Engineering, Science and Technology(印度工程、科学与技术学院)
ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration
University of Arizona(亚利桑那大学);Bangladesh University of Engineering and Technology(孟加拉工程与技术大学);University of Rochester(罗切斯特大学);Chittagong University of Engineering and Technology(丘比特工程与技术大学)
Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment
Technical University of Munich(慕尼黑工业大学);Center for Information and Language Processing, LMU Munich(慕尼黑大学信息与语言处理中心);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心)
Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages
Minzu University of China(中国民族大学);National Language Resource Monitoring & Research Center Minority Languages Branch(国家语言资源监测与研究中心少数民族语言分部);Institute of National Security, Minzu University of China(中国民族大学国家安全学院)
A Comparison of Different Machine Transliteration Models
National Institute of Information and Communications Technology (NICT)(国立信息与通信技术研究所(NICT));Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院(KAIST))
Context based Roman-Urdu to Urdu Script Transliteration System
Comsats University of Information Technology Islamabad, Pakistan (Abbottabad Campus)(巴基斯坦伊斯兰堡 COMSATS 信息技术大学(阿伯塔巴德校区));University of Science and Technology of China (USTC), Hefei, People Republic of China(中国科学技术大学(合肥));Near East University Cyprus KKTC(塞浦路斯近东大学(北塞浦路斯土耳其共和国))
How Transliterations Improve Crosslingual Alignment
Center for Information and Language Processing, LMU Munich(慕尼黑大学信息与语言处理中心);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Bosch Center for Artificial Intelligence(博世人工智能中心);Technical University of Munich(慕尼黑工业大学);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);ISIR(智能与机器人系统研究所)
Exploring Cross-Lingual Knowledge Transfer via Transliteration-Based MLM Fine-Tuning for Critically Low-resource Chakma Language
IIT, University of Dhaka(达卡大学理工学院);Toronto Metropolitan University(多伦多 Metropolitan 大学);Stony Brook University(石溪大学);State University of New York at Old Westbury(纽约州立大学奥尔巴尼分校)
A Systematic Benchmark of Machine Transliteration Models for the Tajik-Farsi Language Pair: A Comparative Study from Rule-Based to Transformer Architectures
Institute of Computational Mathematics and Information Technologies(计算数学与信息科技学院);Kazan Federal University(卡兹安联邦大学)
Happiness is Sharing a Vocabulary: A Study of Transliteration Methods
University of British Columbia, Canada(不列颠哥伦比亚大学,加拿大);Sungkyunkwan University, Republic of Korea(成均馆大学,韩国);Seoul National University, Republic of Korea(首尔国立大学,韩国);Electronics and Telecommunications Research Institute, Republic of Korea(电子通信研究院,韩国);Carnegie Mellon University, USA(卡内基梅隆大学,美国)
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration
LMU Munich(慕尼黑大学);Munich Center for Machine Learning(慕尼黑机器学习中心);University of Texas at Austin(德克萨斯大学奥斯汀分校);Carnegie Mellon University(卡内基梅隆大学);University of California, Berkeley(加州大学伯克利分校);Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration
Department of EECS, Embry-Riddle Aeronautical University, Daytona Beach, FL, USA(电子工程与科学系,埃姆布里-里德尔航空大学,日落海滩,佛罗里达州,美国);NLP Engineering Team, Hishab Singapore Pte. Ltd, Singapore(自然语言处理工程团队,Hishab新加坡私人有限公司,新加坡);Department of Computer Information Systems, Texas A&M University - Central Texas, Texas, USA(计算机信息系统系,德克萨斯A&M大学-中央德克萨斯分校,德克萨斯州,美国)
Towards Zero-Shot Code-Switched Speech Recognition
Carnegie Mellon University(卡内基梅隆大学);Johns Hopkins University(约翰斯·霍普金斯大学);University of Edinburgh(爱丁堡大学);Indian Institute of Technology Bombay(印度理工学院孟买分校)
UniGlyph: A Seven-Segment Script for Universal Language Representation
St. Xavier's Catholic College of Engineering(圣泽维尔天主教工程学院);Loyola College(洛约拉学院);University of Madras(马德拉斯大学);Bell Matriculation Higher Secondary School(贝尔预科高中);St. Xavier’s College(圣泽维尔学院);Manonmaniyam Sundaranar University(马农马尼亚姆·孙达拉纳尔大学)
SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors
Department of Computer Science and Technology, Tsinghua(清华大学计算机科学与技术系);Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua(清华大学交叉信息研究院)