Kyfd Version 0.0.1

This is the Kyoto Fst Decoder (Kyfd), a general purpose beam-search decoder for weighted finite state transducers (WFSTs). It has been used for a number of applications including statistical machine translation, speaking style transformation, OCR correction, and speech segmentation.

Download/Install

Source files for Kyfd can be found here.

Before installing Kyfd, OpenFst and Xerces-C++ must be installed.

Program Documentation

kyfd

The main executable in the Kyfd package is the Kyfd decoder. It can be run as follows.

kyfd [options...] config.xml

An example configuration file can be found here, with descriptions of the various options. Options specified at the command line will override options specified in the configuration file.

Tutorials

These are a few short tutorials on using the Kyfd decoder.

1. Simple Modeling/Decoding: Shows how to create a simple FST model to represent a word dictionary, and uses OpenFst to re-discover word segmentations from a corpus with spaces deleted.
2. Combining Multiple Models (Under Construction)
3. Training Log-Linear Weights (Under Construction)
4. Using Hierarchichal Failure Transitions (Under Construction)

Development Information

Kyfd is currently developed solely by Graham Neubig, but any additional developers are welcome. If you are interested, please send an email to kyfd@.

Kyfd is released under the Apache License, Version 2.0

Revision History

Kyfd - Release 0.0.1 (9/2/2009)

• Support for Beam-search or best-first decoding of WFST models
• Storing and output of the contribution of multiple models for later log-linear weight training
• Output of n-best lists
• Support for hierarchical failure transitions