Current Themes in
Computational Phonology and Morphology:
Seventh Meeting of the ACL Special Interest Group in
Computational Phonology
Held in cooperation with ACL-2004
26 July 2004
Barcelona, Spain
Order copies of this and other ACL proceedings from:
Association for Computational Linguistics (ACL)
73 Landmark Center
East Stroudsburg, PA 18301
USA
Tel: +1-570-476-8006
Fax: +1-570-476-0860
acl@aclweb.org
SIGPHON
Current
Themes
in
Computational
Phonology
and
Morpholgy
26
July
2004
SIGPHON EXECUTIVE COMMITTEE:
Jason Eisner, The Johns Hopkins University, President
Richard Wicentowski, Swarthmore College, Secretary
Paul Boersma, University of Amsterdam
Julie Carson-Berndsen, University College Dublin
John Coleman, University of Oxford
John Goldsmith, University of Chicago
ADDITIONAL PROGRAM COMMITTEE MEMBERS:
Adam Albright, University of California, Santa Cruz
Steven Bird, University of Melbourne
Bruce Hayes, University of California at Los Angeles
Lauri Karttunen, Palo Alto Research Center
Mike Maxwell, Linguistic Data Consortium
Kemal Oflazer, Sabanci University
Janet Pierrehumbert, Northwestern University
Richard Sproat, University of Illinois at Urbana-Champaign
WORKSHOP ORGANIZERS:
John Goldsmith, University of Chicago
Richard Wicentowski, Swarthmore College
WORKSHOP WEBSITE:
http://www.cs.swarthmore.edu/˜richardw/sigphon04/
PREFACE
The ACL Special Interest Group in Computational Phonology organized a workshop on July 26,
2004, after the 24th meeting of the Association for Computational Linguistics in Barcelona, Spain. The
papers in this volume were accepted for presentation at that workshop.
In the call for papers, we asked for papers addressing questions concerned either with computational
morphology or phonology, and we listed the following topics as possible areas for discussion:
a0 Speech technologies relating to phonology
a0 Unsupervised learning of phonotactics, morphology, and phonology
a0 Stochastic or probabilistic phonology
a0 Computational evolutionary modeling of phonological systems
a0 Language-independent learning algorithms relating to computational phonology
a0 Finite-state formalizations of phonology
a0 Computational morphology and morphological modeling
a0 Speech generation
a0 Assistive learning tools for second language speakers
The papers were reviewed by a gracious committee, who agreed to read and evaluate papers in a
very short period of time. This committee consisted of the executive committee of SIGPHON as well
as a volunteer panel of outside experts.
We thank this committee for their work, and we want to give an extra special expression of our
gratitude to Jason Eisner’s efforts. Jason helped us at every step of the way, always going the extra mile
to make sure things were moving the right way and at the right time.
John Goldsmith
Richard Wicentowski
June 2004
Table of Contents
Category competition drives contrast maintenance within an exemplar-based production/perception loop
Andrew Wedel.................................................................................1
Non-locality all the way through: Emergent Global Constraints in the Italian Morphological Lexicon
Vito Pirrelli, Basilio Calderone, Ivan Herreros and Michele Virgilio............................11
A Diachronic Approach for Schwa Deletion in Indo Aryan Languages
Monojit Choudhury, Anupam Basu and Sudeshna Sarkar ..................................... 20
Automatic Acquisition of Feature-Based Phonotactic Resources
Julie Carson-Berndsen, Robert Kelly and Moritz Neugebauer .................................27
Priors in Bayesian Learning of Phonological Rules
Sharon Goldwater and Mark Johnson.........................................................35
Induction of a Simple Morphology for Highly-Inflecting Languages
Mathias Creutz and Krista Lugas.............................................................43
Unsupervised Induction of Natural Language Morphology Inflection Classes
Christian Monson, Alon Lavie, Jaime Carbonell and Lori Levin...............................52
A Comparison of Two Different Approaches to Morphological Analysis of Dutch
Guy De Pauw, Tom Laureys, Walter Daelemans and Hugo Van hamme.......................62
Multilingual Noise-Robust Supervised Morphological Analysis using the WordFrame Model
Richard Wicentowski.........................................................................70
Segment Predictability as a Cue in Word Segmentation: Application to Modern Greek
C. Anton Rytting ............................................................................ 78
Vi-xfst: A Visual Regular Expression Development Environment for Xerox Finite State Tool
Kemal Oflazer and Yasin Yılmaz ............................................................. 86
i
Technical Program Schedule
Monday, July 26
8:45-9:00 Welcome
9:00-9:25 Category competition drives contrast maintenance within an exemplar-
based production/perception loop
Andrew Wedel
9:25-9:50 Non-locality all the way through: Emergent Global Constraints in the
Italian Morphological Lexicon
Vito Pirrelli, Basilio Calderone, Ivan Herreros and Michele Virgilio
9:50-10:30 Break
10:30-10:55 A Diachronic Approach for Schwa Deletion in Indo Aryan Languages
Monojit Choudhury, Anupam Basu and Sudeshna Sarkar
10:55-11:20 Automatic Acquisition of Feature-Based Phonotactic Resources
Julie Carson-Berndsen, Robert Kelly and Moritz Neugebauer
11:20-11:45 Priors in Bayesian Learning of Phonological Rules
Sharon Goldwater and Mark Johnson
11:45-13:30 Lunch
13:30-13:55 Induction of a Simple Morphology for Highly-Inflecting Languages
Mathias Creutz and Krista Lugas
13:55-14:20 Unsupervised Induction of Natural Language Morphology Inflection Classes
Christian Monson, Alon Lavie, Jaime Carbonell and Lori Levin
14:20-14:45 A Comparison of Two Different Approaches to Morphological Analysis of Dutch
Guy De Pauw, Tom Laureys, Walter Daelemans and Hugo Van hamme
14:45-15:10 Multilingual Noise-Robust Supervised Morphological Analysis using the
WordFrame Model
Richard Wicentowski
15:10-15:50 Break
15:50-16:15 Segment Predictability as a Cue in Word Segmentation: Application
to Modern Greek
C. Anton Rytting
16:15-16:40 Vi-xfst: A Visual Regular Expression Development Environment for
Xerox Finite State Tool
Kemal Oflazer and Yasin Yılmaz
16:40-17:00 General Discussions
i
THIS IS A BLANK PAGE PLEASE IGNORE
Author Index
Basu, Anupam................................20
Calderone, Basilio ............................ 11
Carbonell, Jaime ............................. 52
Carson-Berndsen, Julie ....................... 27
Choudhury, Monojit..........................20
Creutz, Mathias ..............................43
Daelemans, Walter ........................... 62
De Pauw, Guy................................62
Goldwater, Sharon............................35
Herreros, Ivan ................................11
Johnson, Mark ............................... 35
Kelly, Robert.................................27
Laureys, Tom.................................62
Lavie, Alon...................................52
Levin, Lori ................................... 52
Lugas, Krista.................................43
Monson, Christian............................52
Neugebauer, Moritz...........................27
Oflazer, Kemal ............................... 86
Pirrelli, Vito..................................11
Rytting, C. Anton............................78
Sarkar, Sudeshna.............................20
Van hamme, Hugo............................62
Virgilio, Michele..............................11
Wedel, Andrew ................................ 1
Wicentowski, Richard.........................70
Yılmaz, Yasin ................................ 86
