Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP

2026-04-20

AI Summary

This study addresses the “script barrier” in cross-lingual natural language processing (NLP), which arises from divergent writing systems and hinders effective transfer learning. The work proposes the first systematic taxonomic framework for transliteration techniques in NLP, introducing an analytical perspective grounded in motivation and input integration to comprehensively map their evolutionary trajectory and application contexts. It reveals transliteration’s unique advantages in handling code-mixed text, leveraging linguistic relatedness, and enhancing inference efficiency. The research delineates the effective boundaries of various transliteration strategies under differing resource availability and task constraints, offering a practical selection guide for cross-lingual applications in the era of large language models and thereby advancing the practical deployment of cross-lingual NLP systems.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Multiagent Systems: Agent Communication

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Cross-lingual transfer in NLP is often hindered by the ``script barrier'' where differences in writing systems inhibit transfer learning between languages. Transliteration, the process of converting the script, has emerged as a powerful technique to bridge this gap by increasing lexical overlap. This paper provides a comprehensive survey of the application of transliteration in cross-lingual NLP. We present a taxonomy of key motivations to utilize transliterations in language models, and provide an overview of different approaches of incorporating transliterations as input. We analyze the evolution and effectiveness of these methods, discussing the critical trade-offs involved, and contextualize their need in modern LLMs. The review explores various settings that show how transliteration is beneficial, including handling code-mixed text, leveraging language family relatedness, and pragmatic gains in inference efficiency. Based on this analysis, we provide concrete recommendations for researchers on selecting and implementing the most appropriate transliteration strategy based on their specific language, task, and resource constraints.

Problem

• cross-lingual transfer
• script barrier
• transliteration
• NLP
• writing systems

Innovation

• transliteration
• cross-lingual NLP
• script barrier
• language models
• lexical overlap