See my website for more information: Website
Miguel Ballesteros is a postdoc at Universitat Pompeu Fabra.
Miguel's main research interest relies on applying new methods for automatic feature selection in order to speed up and facilitate the process of optimizing a data-driven dependency parser. Besides this, he is carrying out several experiments by modifying the work-flow and behaviour of current transition-based and graph-based dependency parsing algorithms with the intention of enhancing the performance and speeding up the training process.
- Became a PhD, 19th December 2012.
- November 2012. PhD defense on 19th December 2012.
- October 2012. Co-authored article with Joakim Nivre at Computational Linguistics Journal accepted for publication. Issue 39:1. Abstract link (13 nov 2012)
- May 2012. Miguel has completed two Research Stays at Uppsala University (Sweden) supervised by Joakim Nivre.
- April 2012. Release of MaltOptimizer: Miguel and Joakim Nivre have released MaltOptimizer, a tool for MaltParser optimization and automatic feature selection. They demonstrated the system at EACL 2012 and Miguel presented it at LREC 2012.
- Email: email@example.com
Phone: (+34)91 394 7606
Address: Universidad Complutense de Madrid, Computer Science Faculty, Office 420bis
C/ Prof. José García Santesmases, s/n. 28040 Madrid (Spain)
- Dependency Parsing.
- Data-Driven Dependency Parsing.
- Machine Learning for Natural Language Processing.
- Algorithms for natural language processing.
- Processing negation and modality.
- Simplified Texts.
- Design principles and annotation schemes for treebanks.
- A System that infers the Scope of Negation.
We participated in the *SEM Shared Task on resolving the scope and focus of negation!!