Toolkits for weighted finite-state machines (WFSM's) have proven to be tremendously useful in a wide variety of speech and language applications. While WFSM's can directly represent finite-state statistical models such as hidden Markov models, this is not the case for many models of interest. In this paper, we consider extending a WFSM toolkit to a non-finite-state formalism. We select a formalism that is both useful and efficient to compute with, and analyze what finite-state operations can be extended to this automaton class. We describe a design for a toolkit for manipulating these automata, and give examples of how our toolkit can be used to quickly train and evaluate models for a variety of language tasks.
By: Stanley F. Chen
Published in: RC24829 in 2009
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .