This page provides a link to TurboSemanticParser, a free broad-coverage semantic dependency parser developed by André Martins, based on joint work with Mariana Almeida.
TurboSemanticParser implements the system described in the SemEval paper  below, which achieved the best result in the open track and the second best in the closed track.
The software is integrated with TurboParser v. 2.2.0, which can be downloaded here. Please follow the installation instructions described in the provided README.
 André F. T. Martins and Mariana S. C. Almeida.
Priberam: A Turbo Semantic Parser with Second Order Features.
In International Workshop on Semantic Evaluation (SemEval), task 8: Broad-Coverage Semantic Dependency Parsing, Dublin, August 2014.