Tools for Finding Scientific Names in texts

by wencan for Encyclopedia of Life

The goal of this project is to build fast and reliable scientific names finding tools by enhancing the existing name finding engine NetiNeti in two ways. 1) Improve the performance in terms of f-measure. I will try to develop new feature sets, new rules for candidate names, new algorithms for this goal. 2) Adaptive it to different target languages using supervised or semi-supervised methods. We also want to increase the speed of the algorithm.