Automated Lexical Coverage for Language Learning: From General to Specialized Word Lists

Abstract:A General Service List (GSL) is a commonly used resource for language learners to identify important English words. Traditional GSL creation is resource-intensive, relying on linguistic expertise and subjective input. We created our own GSL and evaluated its performance against the New General Service List (NGSL). We found that creating a Specialized Word List (SWL), tailored to a specific text, is a practical method for language learners. Because an SWL is derived from the target text itself, it reaches the 95% coverage required for language comprehension by construction, and it does so with substantially fewer words than a general list applied to the same text: across nine texts spanning fiction, academic papers, and scripts, the NGSL covered 64-85% of each text, whereas a text-specific list reached 95% with far smaller vocabularies. By restricting the SWL process to objective criteria only, it can be automated, scaled, and tailored to the needs of language-learners across the globe.

Computation and Language (cs.CL)

arXiv:2512.15552 [cs.CL]

(or arXiv:2512.15552v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2512.15552 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.