Seminar on Computational Learning and Adaptation


  Automatic Acquisition of Pronunciation Rules Using Error-Driven Learning

Raymond Flournoy
Amikai, Inc
San Francisco, CA
ray.flournoy@amikai.com

The development of error-driven learning, also known as transformation-based learning or Brill's algorithm, was an important landmark in part-of-speech (POS) tagging research, because it showed that very good tagging results could be attained with simple training and almost no human intervention. Its results were equivalent to much more labor-intensive systems which were based on human-encoded rules and grammars. In this work, I show how error-driven learning can be adapted and generalized to apply to grapheme-phoneme conversion (GPC), the task of determining the pronunciation of written words. After describing the fundamental differences between POS tagging and GPC which keep us from applying error-driven learning directly, I describe how to adapt the approach to handle these differences and I then give some experimental results. In addition, I discuss how a number of other tasks within Natural Language Processing can also be handled by this generalized form of error-driven learning.


Date: Thurs., Jan 25

Time: 4:15-5:30PM

Place: Cordura 100


Return to the seminar schedule