FLinK - A Framework for the Linearization of Kernel Functions
FLinK stands for “a framework for the linearization of kernel functions”.
The software has been developed as part of my PhD to support our research on the linearization of kernel functions, whose main results so far are published in the following papers authored by me with my co-advisor Alessandro Moschitti:
- On Reverse Feature Engineering of Syntactic Tree Kernels (CoNLL 2010, [1])
- Reverse Engineering of Tree Kernel Feature Spaces (EMNLP 2009, [2])
- Efficient Linearization of Tree Kernel Functions (CoNLL 2009, [3])
(My thesis contains more in-depth information, but I didn’t make it public yet because I am still fixing things here and there).
Although it could possibly be estended to support a large variety of kernel functions, at the moment the framework only supports the Syntactic Tree Kernel [Collins and Duffy, 2001] and the Partial Tree Kernel [Moschitti, 2006].
SVM-Light-TK by Alessandro Moschitti is used for learning and classification in Tree Kernel spaces.
For more information about the linearization process, please refer to the aforementioned papers. More details, as well as comprehensive documentation of the user interface and the programmer API can be found here.
FLinK is distributed under a double licensing scheme. For personal, teaching or research uses, the software is available under the GNU Lesser GPL (LGPL) v.3 license. The text of the license is available at http://www.fsf.org/licensing/licenses/lgpl.html. If you use this software for research, please consider referencing these papers [1],[2],[3] in your publications. Please note that research uses do NOT include those involving the development of technology to be employed for commercial or any other kind of revenue purposes. These include selling, releasing, or providing commercial services based on the software. For any other uses, the software is released under a commercial license. The terms of the license are defined on a per-request basis. You can contact me by email for more information.
Follow this link to download the latest version of the software.
References
- On Reverse Feature Engineering of Syntactic Tree Kernels, , Conference on Natural Language Learning (CoNLL-2010), 08/2010, Uppsala, Sweden, (2010)
- Reverse Engineering of Tree Kernel Feature Spaces, , EMNLP'09: Empirical Methods of Natural Language Processing, 08/2009, Singapore, (2009)
- Efficient Linearization of Tree Kernel Functions, , CoNLL'09: Thirteenth Conference on Computational Natural Language Learning, 06/2009, Boulder, CO, USA, (2009)