Rapid growth in natural language processing for Tibetan languages
Towards the Roof of the World: NLP Progress in Tibetan Languages
Computation and Language
Summary
Tibetan is a language spoken by millions but has had little attention in language technology. The authors surveyed 140 papers about Tibetan language processing from 2004 to 2026, showing rapid progress since 2018. Most research comes from China and covers many topics from basic data collection to large language models. They also highlight areas needing more work, like dialect coverage and sharing data openly. The authors suggest Tibetan NLP progress can guide efforts for other less-resourced languages.
What this means in practice
- •For language technology developers: Use the survey’s overview to identify gaps and resources for building NLP tools tailored to Tibetan and similar low-resource languages.
- •For digital librarians: Leverage the identified research on Classical Tibetan to improve digital archiving and text processing of historical Tibetan documents.
A survey. It maps existing work.
Authors
Xi Cao, Yijie Li, Yuan Sun, Shiwei Dong, Zeguang Huang, Nuo Qun
Abstract
Tibetan, spoken by some seven million people on and around the Qinghai-Xizang Plateau, remains underrepresented in natural language processing (NLP). We present, to our knowledge, the first peer-reviewed systematic bibliometric survey of Tibetan NLP: 140 publications from 2004 to 2026 in the ACL Anthology and DBLP, annotated for venue type, research area, first-affiliation country, and resource release. Output has grown rapidly, with 84% of the publications appearing since 2018, and has expanded bottom-up along the NLP pipeline, from corpora and word segmentation through script, speech, and applications to large language models (LLMs). Researchers based in China first-authored 87% of the publications, which span all 25 represented research areas, whereas work from other countries concentrates on Classical Tibetan. We argue that this full-pipeline paradigm, realized under the compounded constraints of a complex script, dialectal diversity, and geographic remoteness, offers a reference model for other low-resource languages of the Global South. We also identify gaps in dialect coverage, responsible NLP, native and comparable evaluation, cross-community visibility, and resource release (only 29% of the publications release data, code, or models), and recommend open science, shared standards, and community participation for the LLM era.