conferences | speakers | series

NLTK, Scikit and Damegender (a gender detection tool)

home

NLTK, Scikit and Damegender (a gender detection tool)
Opensouthcode 2019

The natural language processing allows sentence similarity, text summary, classify documents, manage words, gramatical trees, ... For these tasks we could need extend the nlp toolkits (example: nltk) with another machine learning libraries (example: scikit). Damegender is using these techniques to: + to guess the gender about a name in spanish or english (current status). + to determine gender gap in free software projects or mailing lists. + to research with statistics about why a name is related with males or female + to use the main solutions in gender detection (genderize, genderapi, namsor, nameapi and gender guesser) from a command. Damegender is free software you can access to the source from https://github.com/davidam/damegender/

The natural language processing allows sentence similarity, text summary, classify documents, manage words, gramatical trees, ... For these tasks we could need extend the nlp toolkits (example: nltk) with another machine learning libraries (example: scikit). Damegender is using these techniques to: + to guess the gender about a name in spanish or english (current status). + to determine gender gap in free software projects or mailing lists. + to research with statistics about why a name is related with males or female + to use the main solutions in gender detection (genderize, genderapi, namsor, nameapi and gender guesser) from a command. Damegender is free software you can access to the source from https://github.com/davidam/damegender/

Speakers: David