1st Edition
Machine Translation and Transliteration involving Related, Low-resource Languages
Machine Translation and Transliteration involving Related, Low-resource Languages discusses an important aspect of natural language processing that has received lesser attention: translation and transliteration involving related languages in a low-resource setting. This is a very relevant real-world scenario for people living in neighbouring states/provinces/countries who speak similar languages and need to communicate with each other, but training data to build supporting MT systems is limited. The book discusses different characteristics of related languages with rich examples and draws connections between two problems: translation for related languages and transliteration. It shows how linguistic similarities can be utilized to learn MT systems for related languages with limited data. It comprehensively discusses the use of subword-level models and multilinguality to utilize these linguistic similarities. The second part of the book explores methods for machine transliteration involving related languages based on multilingual and unsupervised approaches. Through extensive experiments over a wide variety of languages, the efficacy of these methods is established.
Features
- Novel methods for machine translation and transliteration between related languages, supported with experiments on a wide variety of languages.
- An overview of past literature on machine translation for related languages.
- A case study about machine translation for related languages between 10 major languages from India, which is one of the most linguistically diverse country in the world.
The book presents important concepts and methods for machine translation involving related languages. In general, it serves as a good reference to NLP for related languages. It is intended for students, researchers and professionals interested in Machine Translation, Translation Studies, Multilingual Computing Machine and Natural Language Processing. It can be used as reference reading for courses in NLP and machine translation.
Anoop Kunchukuttan is a Senior Applied Researcher at Microsoft India. His research spans various areas on multilingual and low-resource NLP. Pushpak Bhattacharyya is a Professor at the Department of Computer Science, IIT Bombay. His research areas are Natural Language Processing, Machine Learning and AI (NLP-ML-AI). Prof. Bhattacharyya has published more than 350 research papers in various areas of NLP.
Preface. Introduction. Need for Machine Translation and Transliteration. Need for Machine Translation involving Related Languages. Language Relatedness: Origins and Key Properties. Do we need SMT approaches customized for Related Languages? Translation, Transliteration and Related Languages: The Connection. What does the monograph contain? Past Work on MT for Related Languages. Translation between Related Languages. Translation involving Related Languages and a Lingua franca. Neural Machine Translation and Related Languages. Rule-based MT Systems involving Related Languages. Summary. I Machine Translation. Utilizing Lexical Similarity by using Subword Translation Units. Motivation. Related Work. Translation Units for Related Languages. Training Subword-level Translation Models. Experimental Setup. Results and Discussion. Why are Subword Units better than other Translation Units? Summary and Future Work. Improving Subword-level Translation Quality. Effect of Resource Availability. Investigation of Design Choices and Hyperparameters. Improving Decoding Speed. Summary. Subword-level Pivot-based SMT. Motivation. Pivotbased SMT for Related Languages. Related Work. Experimental Setup. Results and Analysis. Using Multiple, Related Pivot Languages. Choice of Pivot Language and Language Relatedness. Summary and Future Directions. A Case Study on Indic Language Translation. A Primer on Indian Languages. Relatedness among Indian Languages. Dataset used for Study. Lexical Similarity between Indian Languages. Translation between Indian Languages. Translation from English to Indian Languages. II Machine Transliteration. Utilizing Orthographic Similarity for Unsupervised Transliteration. Motivation. Related Work. Unsupervised Substring-based Transliteration. Character-based Unsupervised Transliteration. Bootstrapping Substring-based models. Experimental Setup. Results and Discussion. Summary and Future Work. Multilingual Neural Transliteration. Motivation. Related Work. Multilingual Transliteration Learning. Experimental Setup. Results and Discussion. Zeroshot Transliteration. Incorporating Phonetic Information. Summary and Future Work. Conclusion and Future Directions. Conclusions. Future Work and Directions. Appendices. A Extended ITRANS Romanization Scheme. B Software and Data Resources. C Conferences/Workshops for Translation between Related Languages. Bibliography.
Biography
Dr. Anoop Kunchukuttan is a Senior Applied Researcher in the machine translation team at Microsoft India, Hyderabad. He received his Ph.D from the Indian Institute of Technology Bombay. He is broadly interested in natural language processing and machine learning. His research interests include multilingual learning, language relatedness, machine translation, machine transliteration and distributional semantics. He has also explored problems in information extraction, automated grammar correction, multiword expressions and crowdsourcing for NLP. These works have been published in top-tier Natural Language Processing (NLP) conferences and journals. He is passionate about building software and resources for NLP in Indian languages. He actively develops and maintains the Indic NLP Library and the Indic NLP Catalog, and has contributed to the development of resources like the AI4Bharat Indic NLP Suite and the IIT Bombay parallel corpus. He is a co-organizer of the Workshop on Asian Translation and a co-founder of the AI4Bharat NLP Initiative.
Dr. Pushpak Bhattacharyya is Professor of Computer Science and Engineering Department IIT Bombay. His research areas are Natural Language Processing, Machine Learning and AI (NLP-ML-AI). Prof. Bhattacharyya has published more than 350 research papers in various areas of NLP. His textbook ‘Machine Translation’ sheds light on all paradigms of machine translation with abundant examples from Indian Languages. Two recent monographs co-authored by him called 'Investigations in Computational Sarcasm' and 'Cognitively Inspired Natural Language Processing- An Investigation Based on Eye Tracking' describe cutting edge research in NLP and ML. Prof. Bhattacharyya is Fellow of Indian National Academy of Engineering (FNAE) and Abdul Kalam National Fellow. For sustained contribution to technology he received the Manthan Award of the Ministry of IT, P.K. Patwardhan Award of IIT Bombay and VNMM Award of IIT Roorkey. He is also a Distinguished Alumnus of IIT Kharagpur and past President of Association of Computational Linguistics.
