namesfurther

namesfurther is a computational tool designed for the automated generation of additional personal or place names derived from a supplied base set. The system was first introduced in 2017 by the Name Analysis Lab at the University of Bolton as part of an effort to expand small anthroponymic corpora for machine learning research. It employs a combination of morphological analysis, phonotactic constraints, and probabilistic suffix substitution to create plausible variations that respect the phonological and orthographic rules of the target language. For example, given the base name “Olivia”, namesfurther can produce variants such as “Oliviah”, “Olivian”, or culturally specific derivatives like “Olivia-Maria”.

The underlying algorithm is modular. Initially, the input name is segmented into root and suffix. The suffix module then applies a set of language‑specific transformations: vowel alternation, consonant palatalization, or the addition of diminutives. A probabilistic scorer, trained on large public name databases, evaluates each output variant for naturalness and assigns a likelihood score. Researchers can filter outputs by score thresholds or by restricting transformations to particular morphological classes (e.g., patronymic, diminutive, or compound forms).

namesfurther has been applied in several academic contexts. Linguists use it to simulate name variation in historical corpora, while data scientists employ it to augment datasets for training name‑entity recognition models. In the social sciences, the tool has supported studies on naming patterns across cultures and time periods. The software is distributed under an open‑source license, available as a Python package on public repositories. Its development continues with community contributions that expand its support to additional languages, including Icelandic, Mandarin, and Swahili.