LINGUIST List 4.485

Sat 19 Jun 1993

FYI: Preprint: The Acquisition of Morphology

Editor for this issue: <>

Directory

1. "Michael Gasser", Technical report on morphology acquisition available by ftp

The following paper is available in compressed postscript form by
anonymous ftp from the Indiana University Computer Science Department
ftp archive (instructions below). The paper is 60 pages long.
Hardcopies are not yet available, maybe in the fall.

Comments welcome.

Michael Gasser
gassercs.indiana.edu

=================================================================
 Learning Words in Time:
 Towards a Modular Connectionist Account
 of the Acquisition of Receptive Morphology

 Michael Gasser
 Computer Science and Linguistics Departments
 Indiana University

 To have learned the morphology of a natural language is to have the
capacity both to recognize and to produce words consisting of novel
combinations of familiar morphemes. Most recent work on the
acquisition of morphology takes the perspective of production, but it
is receptive morphology which comes first in the child. This paper
presents a connectionist model of the acquisition of the capacity to
recognize morphologically complex words. The model takes sequences of
phonetic segments as inputs and maps them onto output units
representing the meanings of lexical and grammatical morphemes. It
consists of a simple recurrent network with separate hidden-layer
modules for the tasks of recognizing the root and the grammatical
morphemes of the input word. Experiments with artificial language
stimuli demonstrate that the model generalizes to novel words for
morphological rules of all but one of the major types found in natural
languages and that a version of the network with unassigned
hidden-layer modules can learn to assign them to the output
recognition tasks in an efficient manner. I also argue that for rules
involving reduplication, that is, the copying of portions of a root,
the network requires separate recurrent subnetworks for sequences of
larger units such as syllables. The network can learn to develop its
own syllable representations which not only support the recognition of
reduplication but also provide the basis for learning to produce, as
well as recognize, morphologically complex words. The model makes
many detailed predictions about the learning difficulty of particular
morphological rules.

 ************************************************

 INSTRUCTIONS FOR ELECTRONIC RETRIEVAL VIA ANONYMOUS FTP

unix> ftp cs.indiana.edu # or ftp 129.79.254.191
Connected to cs.indiana.edu.
220 moose FTP server (Version 2.0WU(11) Tue Apr 20 16:27:56 EST 1993) ready.
Name (cs.indiana.edu:gasser): anonymous
331 Guest login ok, send your complete e-mail address as password.
Password: <your-email-address>
230-Welcome, archive user! This is an experimental FTP server. If have any
230-unusual problems, please report them via e-mail to rootmoose
230-If you do have problems, please try using a dash (-) as the first character
230-of your password -- this will turn off the continuation messages that may
230-be confusing your ftp client.
230-
230 Guest login ok, access restrictions apply.
ftp> cd pub/techreports
250 CWD command successful.
ftp> binary
200 Type set to I.
ftp> get TR384.ps.Z
200 PORT command successful.
150 Opening BINARY mode data connection for TR384.ps.Z (311529 bytes).
226 Transfer complete.
local: TR384.ps.Z remote: TR384.ps.Z
311529 bytes received in 2.2 seconds (1.4e+02 Kbytes/s)
ftp> quit
221 Goodbye.
unix> uncompress TR384.ps.Z
unix> lpr TR384.ps # or however you print PostScript files