NLP experiments for anaphor resolution using Centering and Centering+Veins theories. This code was developed for my MSc thesis. In summary, it has algorithms for pronoun resolution based on linguistic theories only.

For a detailed description about these algorithms and the experiments, please refer to http://www.bibliotecadigital.unicamp.br/document/?code=000855492 (MSc thesis in Portuguese) or http://link.springer.com/chapter/10.1007%2F978-3-642-16952-6_34 (paper published in English at IBERAMIA-2010). If you're using this code to support your research/publication, I kindly ask you to refer one of them.

The project is composed by code to open an input from the Summ-it corpus, which can be found at http://www.inf.pucrs.br/~linatural/procacosa.html.

As this code was firstly developed aiming experimental research only, it hasn't received any peer code review up to now, so I appreciate any review or test case contribution! :-)

PS: It was tested only for Portuguese