A large scale feature extraction tool for text-based machine learning
A large scale feature extraction tool for text-based machine learning.
Make sure you have installed the dependencies:
g++
or clang
make
cmake
3.0 or latergit
Clone the source with git
:
$ git clone https://github.com/ten-blue-links/fxt.git
$ cd fxt
Build and install:
git submodule update --init --recursive --progress
mkdir build
cd build
cmake ..
make
The toolkit offers a large number of text-based features that can be configured for extraction. See the feature list for the feature types and descriptions.
For a quick tour see the quick start guide. Then refer to the main documentation for specific topics in more detail.
Fxt is distributed under the terms of the MIT license.
See LICENSE for details.