Corpus-Based Methods for Recognizing the Gender of Anthroponyms

Abstract

This paper presents a series of methods for automatically determining the gender of proper names, based on their co-occurrence with words and grammatical features in a large corpus. Although the results obtained were for Spanish given names, the method presented here can be easily replicated and used for names in other languages as well. Most methods reported in the literature use pre-existing lists of first names that require costly manual processing and tend to become quickly outdated. Instead, we propose using corpora. Doing so offers the possibility of obtaining real and up-to-date name-gender links. To test the effectiveness of our method, we explored various machine learning methods as well as another method based on simple frequency of co-occurrence. The latter produced the best results: 93% precision and 88% recall on a database of ca. 10,000 mixed names. Our method can be applied to a variety of natural language processing tasks such as information extraction, machine translation, anaphora resolution or large-scale delivery or email correspondence, among others.

Keywords:

• anthroponymy
• co-occurrence statistics
• corpus linguistics
• gender recognition
• given names
• Spanish

Acknowledgments

The authors would also like to thank the reviewers and the editor for the many helpful comments and insights.

 

Correspondence to: Rogelio Nazar, Instituto de Literatura y Ciencias del Lenguaje Pontificia Universidad Católica de Valparaíso, ValparaÍso, Chile. Email: [email protected]

Notes

1 The lists of masculine and feminine names for our experiments were obtained from the following Wikipedia pages:

https://es.wikipedia.org/wiki/Categor%C3%ADa:Hombres

https://es.wikipedia.org/wiki/Categor%C3%ADa:Mujeres

Additional information

Funding

This research was made possible thanks to two successive grants: project 035.691-32, funded by Pontificia Universidad Católica de Valparaíso (2017), and project Fondecyt Regular 1191481 (2019-2021), funded by ANID (Chile Government).

Notes on contributors

Rogelio Nazar

Dr. Rogelio Nazar is a professor of linguistics in the Institute of Literature and Language Sciences of the Pontifical Catholic University of Valparaiso, Chile. He specializes in computational linguistics and currently leads the research group Tecling.com, dedicated to the development of linguistic technologies.

Irene Renau

Dr. Irene Renau is a professor of linguistics in the Institute of Literature and Language Sciences of the Pontifical Catholic University of Valparaiso. Her main research interest is lexical semantics and the syntax - lexicon interface. She is a member of the Chilean Language Academy.

Nicolás Acosta

Nicolás Acosta is a student of linguistics at the National University of Cuyo, in Mendoza, Argentina. He is also an active member of Tecling.com, where he works as a software developer.

Hernán Robledo

Hernán Robledo is a PhD student at the Pontifical Catholic University of Valparaiso, where he also teaches undergraduate courses in linguistics.

Maha Soliman

Maha Soliman is a PhD student at the Pontifical Catholic University of Valparaiso, where she also teaches undergraduate courses in linguistics.

Sofía Zamora

Sofía Zamora is a PhD student at the Pontifical Catholic University of Valparaiso, where she also teaches undergraduate courses in linguistics.