Loanword formation: a neural network approach 
Alan D. Blair 
blair@cs.uq.edu.au 
John Ingram 
jingram@lingua.cltr.uq.edu.au 
Department of Computer Science 
and Electrical Engineering 
Department of English 
University of Queensland, 4072, Australia 
Abstract 
Loanword phonology seeks to model the 
process by which foreign words are 'nativised' 
or incorporated into the phonological system 
of the 'borrowing' language. We can conceive 
of this as a parsing of the phonetic input 
provided by the foreign word forms, in 
accordance with phonological output 
constraints of the borrowing language. 
Following Silverman (1992) we conceive 
loanword formation as fundamentally a two- 
stage process: the first of which yields a 
parsing of the phonetic input into segmentally 
organised phonetic feature bundles, 
interpretable as segmental targets in the 
borrowing language. In the second stage of 
processing, these segmental targets are parsed 
into phonological structures (syllables, mora, 
feet...etc) compatible with the word-prosody 
of the borrowing language. 
Japanese borrowings from English provide a 
good test-bed for models of loanword 
formation, because examples are abundant 
and, while the segmental mapping from 
English to Japanese is relatively 
straightforward, their respective word-level 
prosodies are strikingly different, providing 
ample opportunity to observe prosodic re- 
structuring in loanword formation. 
to construct 'symbolic' or 'analytical' parsing 
algorithms for this task, either with or without 
reference to a framework of learnability 
theory. This approach came under strong 
challenge from 'empirical' Connectionist 
models of language processing in the 1980's. 
The debate between these competing 
paradigms, or the search for some suitable 
'hybrid', continues. It may be argued that 
loanword formation provides a more 
restrictive, and hence better controlled, 
environment for studying parsing mechanisms 
than other natural language processing tasks, 
which involve a host of lexical, 
morphological, syntactic or pragmatic 
influences. 
In this paper, we report the results obtained 
from a feed-forward neural network, trained 
on an 1100 word corpus of American English 
loanwords "borrowed' into Japanese, post- 
WWII. We make preliminary comparisons 
with an analytical constraint-based approach 
to modeling loanword formation. 
An intended application for the NN parser, 
was to devise an English-Japanese proper or 
place-name translator, which would map an 
English phoneme sequence into Katakana 
(e.g.: Brisbane/brIzbOn/=> 7" ,J z" ~," :, ). 
The theoretical aim of this study is to 
investigate the learning mechanisms required 
for phonological parsing in loanword 
formation. Phonologists have typically sought 
Introduction 
The Japanese language has borrowed 
thousands of words from English, particularly 
since World War II, under the overwhelming 
45 
economic and cultural influence of the United 
States. This massive borrowing over a 
comparatively short period of time provides a 
unique window on processes of loanword 
formation. Borrowed words may reflect 
varying degrees of nativisation to the 
phonological patterns of the borrowing 
language. 
While the segments and phonetic features of 
English words tend to be remarkably well 
preserved by the process of loanword 
formation, the resulting Japanese word forms 
are so completely transformed in terms of 
their prosodic structure that English listeners 
almost invariably fail to recognize their 
English sources, when loanwords are 
presented to them as isolated words carefully 
spoken by a native speaker of Japanese 
(Ingram, 1998). The main factor underlying 
poor recognition of the English source words 
appears to lie in the extensive 
resyllabification, involving vowel epenthesis, 
which is required to parse the segmental input 
into Japanese prosodic frames. Some 
examples are given below: 
orthographic phonemic Japanese 
Olympic olimpik oriNpikku 
truck trak torakku 
cut kat katto 
cud kad kado 
cart kart kaato 
cat kmt kJatto 
Japanese syllable structure is predominantly 
CV, lacking complex onsets and codas. To 
maintain faithful representation of the 
segment structure of the English source words, 
extensive use is made of the epenthetic vowels 
(chiefly, ha/, /o/ and /I/). The temporal 
structure of the English source word is 
converted to Japanese moraic timing. English 
tense (long) vowels and diphthongs are 
usually treated as two-mora units, whereas lax 
(short) vowels are assigned to a single mora. 
(Stress pattern in the English source word 
plays a moderating role. Tense vowels or 
diphthongs in unstressed syllables may 
emerge as one-mora vowels, as in Olympic 
\[ollmptk\].) 
English voiceless obstruents following a lax 
vowel are almost always treated as geminate 
(two mora) stops. But voiced obstruents 
usually do not geminate in this environment in 
loanword formation. Also, if the preceding 
vowel is tense (long) in the English source 
word, gemination of voiceless obstruents does 
not occur in the loanword. The reasons for 
these timing changes need not concern us 
here. 
The segmental mapping from the English 
source word to segments in the Japanese loans 
is basically one-for-one, without any feature 
exchange between adjacent segments. There 
are some palatalized consonants in Japanese 
borrowings which appear to 'pick up' the 
palatalization feature from the following 
vowel (see, cat above). However, this feature- 
swapping between adjacent segments occurs 
only under quite restrictive conditions. Note 
that Japanese has no sound which corresponds 
to the low front English/~e/. We hypothesise 
that Japanese listeners respond to the 'palatal' 
quality of English /m/, by relocating this 
feature onto the preceding consonant, thereby 
regularizing the foreign phonetic contrast to 
Japanese phonemics. 
The examples given above illustrate the major 
phonological transformations required to parse 
English source words into English loanwords 
in Japanese, within the limits of a phonemic 
transcription. Implicit in these 
46 
transformations, though they are not explicitly 
captured by the phonemic representation, are 
the contrasting prosodic structures, such as 
syllable structure constraints, which motivate 
the transformations. 
Modeling loanword formation 
In an 'analytic' account of loanword 
formation, these prosodic constraints would be 
explicitly represented in the form of re-write 
rules, filters or constraints on well-formedness 
for particular aspects of prosodic structure. 
The output of parsing would take the form of 
assignment of an explicit prosodic phrase 
marker. By contrast, in a NN based account of 
loanword formation, the details of prosodic 
feature assignment are not explicitly 
represented, but are typically regarded as 
emergent features, contained in the weight- 
states of the trained network. The NN 
demonstrates acquisition of the prosodic 
constraints on word formation by being able to 
transform phonetic segments and features of 
input source words into well-formed 
phonemic sequences in the borrowing 
language. (The further step of transforming 
Japanese phonemic representations into 
Katakana script is trivial.) 
In a complete model of loanword formation, it 
would of course be necessary to specify more 
precisely how the stage I extraction of 
phonetic segments and features from the 
speech signal is achieved and what perceptual 
filtering takes place on the segmental phonetic 
properties of foreign words as processed 
through the ear of the native listener. These 
initial auditory representations are not, strictly 
speaking, sequences of phonemic segments or 
features. Rather, they are likely to be 
evanescent and somewhat fragmentary, made 
up of phoneme-like segments and 'foreign' 
phonetic features of sufficient auditory 
saliency that they cannot be ignored by the 
perceptual mechanism. 
However, for purposes of modeling stage II 
processes of loanword formation, whether an 
analytical or a statistical NN model is adopted, 
an initial segmental parsing of the input word 
into sequences of phoneme-like feature 
bundles was assumed (see Appendix I for the 
segments and features used). 
The Database 
We compiled a database of 1100 words from 
a dictionary of neologisms borrowed mainly 
from American usage in the post-war era 
(Bailey, 1962). 
The English phonemic transcriptions of these 
words were obtained from the Carnegie 
Mellon Pronouncing Dictionary 
( ftp://ftp.cs.cmu.edu/project/fgdata/dict/) 
which generally reflects American rather than 
British pronunciation. 
Network architecture 
We use a two-layer feed-forward neural 
network with 65 inputs, 20 hidden units and 
53 outputs. A featural representation is 
employed for the (English) input and a 
phonemic representation for the (Japanese) 
output. This architecture was inspired by 
NETtalk (Sejnowski & Rosenberg, 1987) 
although the task performed is, in a sense, the 
reverse of that performed by NETtalk, since 
the latter used an orthographic representation 
for its input and a featural representation for 
its output. 
If the aim of the exercise were to model the 
way humans leam the task of loanword 
formation, it would be more appropriate to 
train the network on some task involving only 
the target language, prior to testing it on input 
from the source language. In that scenario, the 
training task would presumably involve 
deriving the correct surface form from some 
hypothesised underlying structure. However, 
many choices and assumptions would need to 
be made in order to devise an appropriate 
47 
framework and representation for these 
underlying structures. By avoiding such 
choices, our approach has the advantage of 
allowing phonological constraints to be 
studied in a more canonical context. But it 
means that the network is really performing a 
composite task, since it can make use of the 
constraints and statistics of the source 
language as well as those of the borrowing 
language. 
The 65 inputs are divided into 5 groups of 13, 
which encode the phonological features of the 
current phoneme, the two preceding phonemes 
and the two following phonemes (13 features 
x 5 phonemes = 65 inputs in all). 
The featural input representation has several 
advantages over a phonemic one: 
(1) 
(2) 
(3) 
it reduces the number of inputs, 
features often influence the form of 
loanwords in a systematic way, 
the same word is often rendered 
differently in different dialects (for 
example, British vs. American 
English) and the featural 
representation is less sensitive to this 
than a phonemic one would be. 
Input and output phonemes do not always 
correspond on a 1-to-1 basis. In some cases a 
phoneme may be deleted, or it may have a 
consonant and/or a vowel appended to it. In 
order to allow for these possibilities, we 
divide the outputs of our network into three 
groups. The first group has one output for 
each possible phoneme (consonant or vowel); 
the second group has one output for each 
possible consonant; the third group has one 
output for each possible vowel. Each group 
has one additional output representing the 
"empty' phoneme "_". Since there are 20 
consonants and 5 vowels in Japanese, the total 
number of outputs is 26+21 +6=53. 
For example, consider the English word cat 
which has the phonemic representation/k~et/ 
and becomes/kjatto/in Japanese. The network 
views this as three separate training items: 
__k~et => kj_ 
k~et => a 
k~et => tto 
This means that the network, when presented 
with the features encoding the input/__k~et/, 
should be trained to produce an activation of 
1.0 for the/k/output of the first group, the/j/ 
output of the second group and the/_/(empty) 
output of the third group (and an activation of 
0.0 for the other 50 outputs). 
When it comes to the testing phase, within 
each group the output with the largest 
activation is selected, and this determines the 
three-phoneme sequence chosen by the 
network to correspond with the salient input 
phoneme. 
The networks were trained by 
back-propagation (Rumelhart et al., 1986) for 
100 epochs, with a learning rate of 0.01 and a 
momentum of 0.9. The cross-entropy 
minimization criterion was used. 
Results 
Each of 11 networks was trained on 1000 
words from the database, and tested on the 
other lO0 words. Each word occurred in the 
test set of exactly one network. 
The 1100 words in the database had an 
average of 8.8 phonemes per word, making a 
total of 9658 input phonemes. Each of these 
input phonemes can produce output consisting 
48 
50 Z. 
I 
40- 
~30 - 
® 
0~ 20 - 
10- 
0 
0 
_ 
4- 
.~2- 
1 --- 
0 
0 
_ 
4- 
  3- 
1 
0 
0 
Head Phoneme 
~liillllllJllJllilJOligilllOlOlililllJlOJOOlOllllliOilllllJlll Ji JlJillillllllJJlll 
20 40 60 80 100 
epoch 
train ................. test 
Added Consonant 
20 40 60 80 100 
epoch 
train ................. test 
Added Vowel 
°" o I IlelOllllllllli|lofililOlOlllllOilellillll!  llillllllllJlll141 111illltlelllllJl IJ 
20 40 60 80 100 
epoch 
train ................. test 
of a head phoneme (group 1 outputs), plus an 
optional added consonant (group 2) and/or 
added vowel (group 3). 
Figures 1-3 show the percentage of errors on 
the training and test sets for each of these 
three groups. In our data set, the head 
phoneme was nonempty 97% of the time, 
while the added consonant and added vowel 
were nonempty only 4% and 17% of the time, 
respectively, so the network error is much 
smaller for the latter two groups. After 30 
epochs the training and test errors, 
respectively, reach a level of 7.4% (resp. 
9.9%) for the head phoneme, 1.1% (resp. 2%) 
for the added consonant, and 1.1% (resp. 
1.6%) for the added vowel. After this, the 
training error continues to fall while the test 
error levels off. (Note: the test error was 
computed at the end of each epoch, while the 
training error was computed during the epoch. 
Therefore the training error may exceed the 
test error in the first few epochs.) 
Error Analysis 
An analysis was undertaken of all 'errors': 
cases where there was a discrepancy between 
the romanji (Japanese Romanized) 
representation of a loan word and the 
phonemic representation assigned by the fully 
trained network, when the item in question 
was not included in the training set. These are 
summarised in Table 1. The 'error' categories 
are not necessarily mutually exclusive; nor do 
they necessarily indicate an error on the part 
of the network, but simply a discrepancy 
between the dictionary-based phonemicization 
(Romanji transcription) and that assigned by 
the network. 
Discrepancies of Schwa vowel colouring: 
The most common 'error' or discrepancy 
between the network-assigned Japanese 
phonemicization and the Romanji dictionary 
49 
entry for loanwords (27% of cases) involved 
unstressed vowels in English source words. 
Table 1. Primary "error" count 
Error or discrepancy Incidence 
Schwa vowel colouring 148 27% 
Vowel length discrepancy 107 19% 
Obstruent gemination 45 11% 
Vowel epenthesis 39 7% 
Dipthongs/ou/and/ei/ 23 5% 
Spelling pronunciation 20 4% 
Post vocalic/r/ 20 4% 
Vowel quality, unexplained 20 4% 
Palatalization of/t/to/if/ 18 3% 
Back vowel phonemicization 10 2% 
Epenthetic vowel quality 10 2% 
Alternation:/o55/and/z/ 8 2% 
Silent/g/in ng 7 1% 
Alternation:/w/and/u/ 7 1% 
Alternation:/s/and/j7 7 1% 
Alternation:/h/and/f/ 6 1% 
/y/epenthesis: breaking 5 1% 
Others 8 2% 
TOTAL 489 
Such vowels would normally be transcribed 
with a schwa \[o\] in English phonemic 
representations. Japanese has no equivalent to 
schwa and Romanji transcriptions of such 
vowels are guided by English spelling in the 
selection of an appropriate symbol. Because 
the network had no access to the orthographic 
representations of English source words, these 
discrepancies were frequent. 
Discrepancies of vowel length: 
The second most frequent error involved 
discrepancies of vowel length. English tense 
vowels and diphthongs should be perceived as 
long (two mora) vowels in Japanese. 
However, stress and position in the word may 
act as moderating influences. In primary 
stressed position English vowels are 
lengthened, while reduced vowels in 
unstressed syllables may be very short. 
Therefore, tense English vowels in unstressed 
position may not be perceived as long 
(bimoraic) by Japanese listeners. 
An analysis of discrepancies between the 
network predictions and the romanji assigned 
vowel durations (Table 2) revealed that only 
13% of cases (example \[1\]) could be 
accounted for by shortening of a tense vowel 
in an unstressed syllable. 
Table 2. Discrepancies of Vowel Length* 
Romanji form of loanword 
orthography 
Network assigned Romanji English phonemic 
Incidence 
l.a f ut a n u u N afternoon 
a f ut a a n u u N ~eftornuun 14 13% 
English 
2. a k ut i b i t i i z u activities 
a k uC i b i t i z u ~ektivotiiz 42 39% 
3. a n a r o J i i analogy 
a n a r o J i on~elo~ii 21 20% 
4. a d ob a N t e eJ i advantage 3 03% 
a_ddob e N C i JJi odvaenticl3 
5. a N C o b e anchovy 14 13% 
a N C o o b i i ~entJ'ouvii 
6. C e kkuo f u checkoff 
C_e_k o_o_f u t~ekoof 8 07% 
7. a u too b ufa SS o N out-of-fashion 
au ut oa b ufa SS o N autavf~eSan 3 03% 
*Source of discrepancy indicated in bold. 
In the majority of cases (59%), the 
50 
discrepancy between the romanji and the 
network assigned vowel length was caused by 
the network shortening phonemically 
long/tense vowels in final position (example 
2\[2.\]) or elsewhere in the word (2\[3\]). We are 
presently unable to account for this behaviour 
of the network. In 13% of cases (2\[5.\]) vowel 
length discrepancies could be sourced to 
irregular romanization on the part of the 
compilers of the Japanese dictionary, or to 
errors of vowel length phonemicization in the 
the American dictionary (7%, 2\[6\]). The 
influence of English spelling could be clearly 
seen in the romanji forms in 3% of cases: e.g., 
advantage => adobaNteeJi because age => 
eeJI, though the pronunciation \[edv~entI~\] 
indicates the vowel is short/lax. In a small 
proportion of cases (3%, 2\[7\]) the vowel 
length discrepancy appeared to be attributable 
to the network's allowance of three-mora 
vowel sequences within a single syllable 
(super-heavy syllables), not sanctioned by 
Japanese syllable structure. 
Gemination of obstruents: 
The basic rule of gemination for English 
loanwords is that voiceless obstruents 
geminate following short vowels in stressed 
syllables. Voiced stops also geminate 
irregularly in this environment. The most 
common error of gemination involved the 
network failing to geminate a voiceless 
obstruent in the expected environment (Table 
3, example \[1\]). But the network also 
inappropriately produced geminates following 
an unstressed vowel (312\]), though not 
consistently. We observed that gemination did 
not occur in romanji forms derived from a 
consonant cluster in the English word (e.g.: 
the/k/in vector does not geminate, becoming 
Romanji/bekutoru/). However, this constraint 
was not respected by the network (3\[3\]). The 
network occasionally produced geminate 
consonants linked to its propensity to shorten 
vowels (3\[4\]). Gemination of voiced 
obstruents was irregular in the Romanized 
forms (3\[5,7\]) and consequently in the 
network output as well (3\[4,5\]). Nor was the 
gemination of voiceless obstruents entirely 
regular in the romanji forms (3\[9\]). 
Table 3 Errors of Consonant Gemination* 
_desired_output_ English-orthography Incidence 
_actual output_ English-phonemes 
1. a N r a kk i i unlucky-net 
a N r a k i i onlakiinet 18 
2. a n e k ud o o t o anecdote 
a n e kkud o t o ~nokdout 12 
3. b e k ut o r u vector 
b e kkut o a vektor 10 
4. f ii d ob a kku ~edback 
f i ddob a kku fiidbmk 
5. b o bbus ur e e bob-sleigh 3 
b o b us ur e e bobslei 
6. a d ob a N s u advance 
a ddob a N s u adv~ns 
7. a d or I b u ad-lib 
a ddor I b u aedlib 
8. a_i_ky_a CC a a eye-catcher 2 
a i kk a CC a a aik~etfer 
9. fe t i S i z u m u fetishism 
fe tt i S i z u m u fetifizem 
4 
* The inferred site of error is indicated in bold. 
Vowel epenthesis: 
Errors of vowel epenthesis are of particular 
interest in assessing the network's capacity to 
adapt to Japanese syllable structure. 
Epenthetic vowels are very frequent in English 
loan words (averaging 1.28 per word in 
romanji forms in the current data set, or 
slightly over 1400 occurrences). However, 
only 39 discrepancies of vowel epenthesis 
were observed (an error rate of 3%). 
51 
Furthermore, the largest sub-category of 
epenthesis errors were related to word 
boundaries in compound forms, (see Table 4). 
Table 4. Epenthesis at word boundaries* 
desired output English-orthography Incidence 
actual output_ English-phonemes 
a t o m i kkue i J i atomic-age 
a t o m i kk e e J i otomikeid33 
d or a i b ui N drive-in 
d or a i b i N draivin ll 
*Epenthesis associated with boundary in bold 
The network, having no information about 
word boundaries, could not predict epenthetic 
vowels at word endings in compound forms. 
However, such boundaries are inherently 
problematic in loan word formation, as they 
may or may not be apparent to speakers of the 
borrowing language. 
The quality of the epenthetic vowel (\[I\], \[u\], 
\[a\], \[e\], \[o\]) was also well predicted by the 
network, with only 10 discrepancies (<1%); in 
all cases caused by irregular romanization, 
some of which were clearly related to English 
spelling. 
Dipthongs /ou/ and /ez/: 
The diphthongs /ou/ and /eI/ are usually 
represented as long vowels 'oo' and 'ee' in 
romanji, but not consistently. In 
approximately 40% of cases, English/el/was 
rendered as Romanji 'ei' and in 32% of cases 
English/ou/converted to the short vowel 'o' 
in Romanji. These irregularities in the romanji 
representation of the diphthongs/ei/and/ou/ 
are the probable cause of the occasional 
discrepancies with the network predictions. 
In summary, the network's performance in 
predicting the phonological forms of loan 
words in Japanese, was on the whole, very 
good, except for the features of vowel quality 
in reduced syllables of English words, and in 
the prediction of vowel length and consonant 
gemination in romanji forms. Except in the 
case of English vowels in reduced syllables, 
spelling was found to play a subordinate role 
to the phonological features of words in the 
source language. Some improvement in the 
prediction of vowel length, and substantial 
improvement in the prediction of consonant 
gemination may be expected by providing the 
network access to the locus of primary stress 
in English words. We are currently 
investigating this. 
Discussion 
We confine discussion to observations on the 
main practical and theortical objectives of this 
on-going study. With respect to the goal of 
devising an English-Japanese proper or 
place-name translator, which will convert 
English phonemic representations to romanji 
or kana forms, we find the results 
encouraging. With the inclusion of primary 
stress, and access to orthographic 
representations for the prediction of vowel 
quality in reduced syllables, it should be 
possible to obtain near optimal performance 
for the prediction of romanji or kana forms, 
given a degree of indeterminism that is present 
in loan word dictionary entries. Precisely how 
English orthographic information can be 
incorporated as required is a problem that we 
have not yet addressed. For the data set of our 
study (post-war borrowings of general lexical 
items), it is clear that English spelling plays a 
strictly subordinate role to the phonetic form, 
as perceived by the Japanese listener. There is 
typically much disagreement amongst 
Japanese lexicographers on the romanji or 
kana representations of English place names. 
This is probably because lack of exposure to 
the spoken form promotes greater reliance on 
the (highly irregular) English orthographic 
52 
representation. 
With respect to the theoretical goal of the 
study, an anonymous reviewer made the 
following astute observation: "If the intent is 
to 'investigate the learning mechanisms 
required for phonological parsing in loanword 
formation,' then training on a corpus of 
loanwords is a surprising choice, since it is 
usually assumed that loanword phonology is 
not learned separately but is a side effect of 
having trained on the internal phonology of 
the target language". In other words, perhaps 
there is an irreconcilable conflict between the 
engineering and scientific goals of the study. 
The most direct approach to the problem fi'om 
an engineering perspective is to train the 
neural network to perform the mapping 
between English phonemic and Japanese 
romanji representations. But this seems clearly 
the wrong approach from the perspective of 
psycholinguistic modeling of loan word 
fomaation, where we postulate an initial stage 
of segmental phonetic mapping, subsequently 
constrained by the word prosody of the 
borrowing la.nguage. 
It is certainly true that our NN modeling has at 
least simplified some of the processing which 
we hypothesise takes place, firstly in accepting 
as input (American) English phonemic 
representations, where our model postulates 
quasi-phonemic segmental representations in 
the borrowing language. We have, in other 
words, fudged on a level of phonetic to 
phonemic segmental mapping. This has had a 
demonstrable, but minor impact on the 
accuracy of the network performance. 
However, the more serious objection that the 
network should have been trained on native 
Japanese words may be addressed in the 
following way. From the perspective of 
constraint satisfaction, we require an input 
that highly over-generates with respect to the 
target forms, but which nevertheless contains 
all the segmental features to which the output 
should strive to be faithful. We have not 
attempted to directly simulate the generative 
capacity of GEN, but rather, provided a 
mechanism which ensures that segmental 
faithfulness is met, within the over-generative 
capacities of the three segment window of the 
NN architecture. In other words, we argue that 
by training on the English-Japanese mapping, 
we have indirectly or approximately simulated 
the over-generative capacity of GEN, while 
providing the network with all (and only) the 
segmental phonetic input to which it is 
required to be faithful. It is not clear to us how 
this could be accomplished by training 
exclusively within the target language. 
However, even if this argument carries 
weight, the second theoretical leg of this 
study remains to be undertaken: the 
construction of an analytical (rule-based) 
competitor to the NN model, and the 
systematic testing of both against the 
behaviour of native Japanese speakers' 
intuitions. We are grateful for the assistance of 
Chiharu Tsuratani in providing native speaker 
assessments of the NN responses. This testing 
needs to be more systematically pursued in 
further investigations. 
Acknowledgments 
This work was partially funded by a 
University of Queensland Postdoctoral 
fellowship. 

References 
Bailey, D.C., 1962. A Glossary of Japanese 
Neologisms, University of Arizona Press. 
Ingram J. C. (1998) Word Prosody, lexical 
access 
and the perception of foreign loan words. In 
J.Wiles (Ed) Perspectives on Cognitive 
Science 11: Theories, experiments, and 
foundations, Ablex: \[In press\] 
Lovins, J. B.(1975) Loanwords and the 
phonological structure of Japanese, 
Bloomington : Indiana University Linguistics 
Club. 
Rumelhart, D.E., G.E. Hinton & R.J. 
Williams, 1986. Learning representations 
by back-propagating errors, Nature 323, 
533-536. 
Sejnowski, T.J. & C.R, 1987. Rosenberg, 
Parallel Networks that Learn to Pronounce 
English Text, Complex Systems 1, 145-168. 
