TRANSLATION AMBIGUITY RESOLUTION 
BASED ON TEXT CORPORA 
OF SOURCE AND TARGET LANGUAGES 
Shinichi DOI and Kazunori MURAKI 
NEC Corp. C&C Information Technology Research Laboratories 
4 1 1, Miyazaki, Miyamae-ku, Kawasaki 216, JAPAN 
e-mail: doi%mtl.cl.nec.co.jl/~sj .nee. corn 
ABSTRACT 
We propose a new method to resolve am- 
biguity in translation and meaning in- 
terpretation using linguistic statistics ex- 
tracted from dual corpora of sourcu aud 
target languages in addition to tim logical 
restrictions described on dictiomtry and 
grammar rules for ambiguity resolution. 
It provides reasonable criteria for deter- 
mining a suitable equivalent translation 
or meaning by making tile dependency re- 
lation in the source language be reflected 
in the translated text. The method can 
be tractable because tile required staffs- 
tics can be computed semi-automatically 
in advance from a source language corpus 
and a target language corpus, while an 
ordinal corpus-based translation method 
needs a large volume of bilingual corpus 
of strict pairs of a sentence and its transla- 
tion. Moreover, it also provides the means 
to compute the linguistic statistics on the 
pairs of meaning expressions. 
1 Introduction 
It~ecently many kinds of natural lauguage pro- 
cessing systems like machine translation systems 
have been developed and put into practical use, but 
ambiguity resolution ill translation and meaning in- 
terpretation is still the primary issue in such sys- 
tems. These systems have conventionally adopted 
a rule-ba.~ed disambiguation method, using linguis- 
tic restrictions described logically in dictionary and 
grammar to select the suitable equivalent transla- 
tion and meaning. Generally speaking, it is impos- 
sible to provide all the restrictions systematically 
in advance. Furthermore, such machine transla- 
tion systems have suffered from inability to select 
the most suitable equivalent translation if the in- 
put expression meets two or more restrictions, and 
have difficulty in accepting any input expression 
that meets no restrictions. 
Ill order to overcome these difficulties, following 
methods .~r~ proposed these years: 
1. F, xample-Ba.sed Translation : tile method 
based oil trans\[atiou examples (pairs of source 
text, aml its translation) \[Nagao 84, Sato 90, 
Smuita 90\] 
2. Statistics-Based Translation : the nmthod us- 
ing statistical mr probabilistic information ex- 
tracted from a bilingual corpus \[Brown 90, 
Nomiyama 9\]\] 
Still, each (ff them has inherent problems and is 
insufficient for ambiguity resolution. For example, 
either all e×amplc~b~mcd translation method or a 
statistics-based translation method needs a large- 
scale database of translation exalnpl~, and it is 
difficult to collect all adequate amount of a bilin- 
gual corpus. 
In this paper, we propose a new method to select 
the suitable equivalent translation using the sta- 
tistical data extracted independently from source 
and target language texts \[Muraki 91\]. The sta- 
tistical data used here is linguistic statistics repre: 
senting the dependency degree on the pairs of ex- 
pressions in each text, especially statistics for co- 
occurrence, i.e., how frequently the expressions co- 
occur in the Sallle seutence~ the sanle paragraph or 
tile same chapter of each text. The dependency 
relation in the source language is reflected in the 
translated text through bilingual dictionary by sc~ 
lecting the equivalent translation which ma.ximizes 
both statistics tot co-occurrence in tile source and 
targ(~t language text. Moreover, the method also 
provid~ the means to compute tile linguistic statis- 
tics on the pairs of meaning expressions. We call 
tlds method for equivalent translation and meaning 
selection DMAX Criteria (Double Maximize Crite- 
ria based on Dual Corpora). 
First, we make comments on the characteristics 
and the linfits of the conventional methods of am- 
biguity resolution in translation and meaning inter- 
pretation in the second section. Next, we describe 
the details of DMAX Criteria for equivalent trans- 
lation selection in the third section. And last, we 
explain the means to compute the linguistic statis- 
tics on the pairs of meaning expressions. 
ACRES DE COLING-92, NANTES, 23-28 ^of.rr 1992 5 2 5 PROC, oJ, COLING-92, NA~CrEs. AUG. 23-28, 1992 
2 Conventional Methods of 
Ambiguity Resolution 
2.1 Rule-Based Translation 
In conventional methods, linguistic restrictions 
described in the dictionary and grammar are used 
to select the suitable equivMcnt translation or 
meaning. In general, these restrictions are de~ 
scribed logically on characteristics of another ex- 
pression which modifies or is modified by the ex- 
pression to be processed. For example, to translate 
predicates (verbs and predicative adjectives), se- 
mantic restrictions are deacribed on essential case 
arguments in forms of semantic markers to indicate 
features of words or terms in the thesaurus to show 
a hierarchy composed of word concepts. 
Though these conventional methods have been 
very useful to realize natural language processing 
systems, ttmy have the following problems: 
1. It is impossible to decide the most suitable 
equivalent translation if the input expression 
meets two or more restrictions. 
2. Analysis fails when the input expression can 
meet no restrictions. 
3. Actually the practical systems depends on 
such heuristics as pre-declded application or- 
der of restrictions or some default equivalent 
translations or meanings. 
4. The description of the restrictions is based on 
direct structural dependencies, therefore it is 
quite difficult to describe the restrictions based 
on sister-dependency or between expressions 
belong to different sentences or paragraphs. 
5. Restrictions on any dependencies cannot be 
thoroughly described in advance. 
For example, a Japanese word "booru" has two 
meanings, one is 'a bail(a round object used in a 
game or sport)' and the other is 'a bowl(a deep 
round container open at the tap especially used in 
cooking)'. When this word occurs in the following 
sentence, it must mean ~a bowP. 
JAP: Booru-nl mizu-o ireru 
bowl dative water obj, pour, 
or marker marker put in 
ball or fill 
ENG; To pour water in%o a bowl 
In this case, to select the meaning by the logical re- 
strictions on dependencies, it is necessary to have 
described even the appearance or usage of the in- 
direct object of the verb "irern". To describe such 
detail restrictions on ,all expressions may be possi- 
ble, but it is quite difficult because the trouble of 
description and the cost of calculation. 
2.2 Example-Based Translation 
Besides the conventional translation method 
above, a machine translation system based on 
translation examples (pairs of source texts and 
their translations) is also proposed \[Nagao 84, 
Sato 90, Sumita 90\]. This type of system, called 
Example-Based Machine Translation, has stored a 
large amount of bilingual translation examples ms 
a database, and translates input expressions by re- 
trieving an example most similar to tim input from 
the database. There is no failure of output in this 
method because it selects the most similar example 
not the identical one. 
However this example-based translation system 
needs a large-scale database of translation exam- 
ples, and iL is difficult to collect an adcxluate 
amount of bilingual corpora. Even if it is possible, 
there is no means to divide the sentences of such 
corpora into fragments and link them automati- 
cally, and it costs us too much time and money to 
divide and link manually. Besides, this method can 
neither achieve precise meaning interpretation be- 
cause it selects equivalent translation directly from 
the input expression and leaves meaning interpre- 
tation out of consideration. 
To overcome this problem, we have also proposed 
a new mechanism based on sentential examples in 
dictionary, which utilize the merits of both the 
translation by logical restrictions and the example- 
based methud, by selecting the equivalent transla- 
tion which ha.s tlle most similar example to the in- 
put expression IDol 92\]. This mechanism can guar- 
antee no failure in selecting an equivalent transla- 
tion, but the description of relations are still based 
only on direct structural dependencies. 
2,$ Statistics-Based Translation 
Several new methods especially of machine trans- 
lation have been proposed lately, which select a 
suitable equivalent translation using statistical or 
probabilistic information extracted from language 
text \[Brown 90, Nomiyama 91\]. Because many ma- 
chine readable texts have been already collected 
nowadays, it is not difficult to extract statistical 
information of each expression in the texts semi- 
automatically. Moreover, the statistical informa- 
tion reflects the context in which eactt word occurs 
and implies the logical restrictions based on indi- 
rect structural dependencies. 
Although we call the systems in a same word 
"statistics-based translation", statistical informa- 
tion used in the methods is diverse, such as trans- 
lation probability, connectivity of words, statistics 
for (co-)occurrence, etc. We make comments on 
the characteristics and the limits of these systems. 
The first method uses fertility probabilities, 
translation probabilities and distortion probabili- 
ties \[Brown 90\]. Fertility means the number of 
the words in target language that the word of ttle 
AcrEs DE COLING-92, NANTES, 23-28 AOOT 1992 5 2 6 PROC. OF COLING-92. NANTES. AUG. 23-28, 1992 
source language produces, and distortion means tile 
distance between the position of the word of the 
source language and the one of the target language. 
Tile method has been applied to au experiinental 
translation system from French to English. How 
ever, since these probabilities are extracted from 
a large amount of text pairs that are translations 
of each other, this method must be suffered from 
tile santo difficulties ,as examplc~b~sed translation 
in collecting and analyzing an adequate amount 
of bilingual corpora, and it's very difficult to ap- 
ply this method to the languages whose linguistic 
structures aren't similar each other, such as English 
and Japanese. 
The second method uses tile statistics for occur- 
fence in target language text \[Nomiyama 91\]. It is 
calculated ill advance how frequently the each ex- 
pression occurs in the t~rget language text, which 
needs only to belong the same tiehl as the source 
language text beblngs, but not to be a translated 
text of tile source language text. If there are more 
than one possible equivalent translations, the most 
frequent translation is selected through this calcu- 
lated data. Moreover, this nrethod can be applied 
to make good use of the conventional methods of 
selecting equivalent translations, tbr it employs the 
frequency data exclusively when logical restrictions 
cannot select one out of candldates. 
However this method hms one big problem. The 
high frequency of the expression in the target lan- 
guage text may not originate from the frequency 
of the expression in the source language text to be 
translated, because one target language expression 
does not correspond to only one source language 
expression ill general. 
Suppose the following sentence is a first examph.': 
JAP: Sorlo saibankan-wa kooto-to 
that judge subj. coat and 
marker or 
court 
nekutai o katta. 
tie obj. bought 
marker 
ENG: The judge bought a coat and a tie. 
Figure 1 indicates translation process through 
bilingual dictionary and the statistics for co- 
occurrence of each pair of expressions in both 
Japanese and English necessary to translate tile 
sentence 1. The Japanese word 'qmoto" has two 
equivalent English translations: '(over)coat' and 
'(tennis) court'. We cannot decide which is eligible 
1The statistics for co-occurrence of expressions 
shown in the figures are given provisionally for 
understanding. 
with only logical restrictions on tile direct object of 
the Japanese verb "kau", because we can buy both 
'coLt' and 'court' tile sentence "Tenisu-.kooto o 
kau" :: 'To buy a tennis court' is also quite accept- 
able. In this case, the statistics for co-occurrence 
in the target language English text denotes that 
the most frequent pair is 'court-judge', because the 
word ~COllr|' also lneans a qaw court'. Then using 
only statistical data on the targct language text 
misleads a wrong expression 'court' ms the. C<luiva- 
lent translation of "kooto", and the exanlple sen- 
teach may Im translated into 'The judge bought a 
court and a tic.'. 
Tile second examph! is this sentence~: 
JAP: Kotori no kago-ni mizu o 
bird of cage dative water obj. 
or marker marker 
basket 
ireta booru-o ella. 
filled bowl obj, put 
or market 
ball 
EN(;: I put a bowl filled with water 
in the bird cage. 
q'ranslation process of this sentence and the 
statistics for co-occurrence are shown in Figure 2. 
Because the pair of 'basket' and 'ball' co-occurs 
most frequently in the target language, tile sen- 
teuce nlay be translated into 'I put a ball filled 
with water in the bird basket.'. 
3 Equivalent "Ih'anslation Selection 
by Statistical Data on Dual 
Corpora of Source and Tat-get 
Languages 
Now we propose a new method to provide rea 
sonable criteria for selecting a suitable equivalent 
tralMation or meaning using the simple statistical 
data extracted from source language text in addi- 
tion to tile one from target language text. These 
source and target language texts don't have to be 
translations of each other. The proposed method 
gives us a way to select tile expression with the 
highest frequency of the target language text that 
keeps high frequency of the source language text 
at tim same time, so it overcomes the difficulty of 
the method using the frequency data on the target 
language text only, because it does not select the 
expression with the highest frequency of only the 
target language text. 
~The subject phrase "watashi-wa" = T is omitted 
in this sentence. 
AcrEs DE COLlNG-92, NANT .ES, 23-28 AObq" 1992 5 2 7 PRec. O1~ COLING-92, NANTES, AUG. 23-28, 1992 
3.1 Using statistical data on source 
language text 
The method using only statistical data on the 
target language text may mislead a wrong equiv- 
alent translation, because in general each target 
language expression corresponds to nmre than one 
source language expression. 
The equivalent translation selection with statis- 
tics for co-occurrence in the target language text 
when a source language expression S, has n equiva- 
lent translations in target language T,i(i = 1 •.. r~) 
is shown ~s this: 
S. 
Sb 
where 
Sk 
Tkl 
(i = 1... n) 
SCO(Ei,Ej) 
T,,i --~ SCO(T,i,Tbi) 
T6j 
source language expression 
n target language eqnivalent 
translations of Sk 
statistics for co-occurrence of 
two exprt~sions EI,Ej 
The method using only statistical data on the tar- 
get language text selects T,i which maximizes the 
statistics for co-occurrence in the target language 
text 3 as the equivalent translation of S,, where 
the partner of the co-occurrence Tbj plays the part 
of the basis for the equivalent translation selection. 
The bigg~t problem of this method is that Tbj 
which depends both b and j is selected by only sta- 
tistical data on the targct language text. 
Our new method provides reasonable criteria for 
selecting the basis for the equivalent translation se- 
lection using the statistical data on the source lan- 
guage text. First the source language expression 
Sb which maximizes the statistics for co-occurrence 
in the source language text 4 is selected, then the 
equivalent translation T,i which maximizes the 
statistics for co-occurrence in the target language 
text 5 is selected. The dependency relation in 
the source language is reflected in the translated 
text through this method. We call this method 
for equivalent translation and meaning selection 
DMAX Criteria (Doable Maximize Criteria based 
on Dual Corpora). 
~,.2 Double Maximum Criteria based on 
Dual Corpora 
The algorithm of this method is summarized as 
follows: 
1. Prepare the source and target language texts 
(the target language text needs not to be a 
translated text of the source language text). 
~T.il maxb,15 SCO(T.~, Tbi) 
4 Sb\[ maxl, SCO(S., Sb) 
bT. d max,5 SCO(T.I, Tbj) 
2. Accumulate the statistics for co-occurrence of 
every expression in both texts. 
3. When it source language expression Sa has 
n equivalent translations in target language 
T~i(i = 1...n) 
(a) Select S~l maxb sco(s., sb) 
(b) Select T,, I maxl,j SCO(T,I, Tbj) 
3.3 Operation Example 
Figure 1 3 show operation examples. Figurc 1 
and 2 are examples of Japanesc~Engllsh transla- 
tion. In Figure 1, with only statlstic,t\] data on 
the target language text, ~court' may be chosen as 
an equivah;nt translation of "kooto" because tim 
pair of 'eonrt-judge' co-occurs most frequeatly in 
the target language. However with DMAX Crite 
rio, the equivalent translation of "kooto" is selected 
correctly. 
• The expression which co-occurs with "kooto" 
most frequently in the source language is 
• The pair of the equivalent translation of 
"kooto" and the one of "nekutai" which co- 
occurs most frequently in the target language 
is 'coat tie'. 
• As a result, "kooto" is translated into 'coat'. 
It is the same ms shown in Figure 2. A pair 
of 'basket ball' co-occurs most frequently in the 
target language. But using DMAX Criteria, giv- 
ing attention first to the most frequent pair in the 
source language text, "kotori-kago" cart gain the 
correct equivalent translation 'cage'. Next, a pair 
of "mizu-booru" decides 'bowl' as an equivalent 
translation of "booru'. Finally, correct trauslation 
can be acquired in this way. 
Figure 3 shows the translation proct.~s and the 
statistics for co-occurrence of another English~ 
Japanese tr~tnslation example. 
~NG: The coiling of the court was 
cleaned quite well. 
# 
JAP: Saibansho no tenjoo~wa 
court of ceiling subj. marker 
kireini sonjl-sareteita. 
quite well be cleaned 
In this case, the English words 'court' and 'clean' 
have two meanings respectively. 
'court' 
saibansho a room or building in which law cases 
can be heard and judged 
kooto (a part of) an area specially prepared and 
marked for various ball games, such as tennis 
AcrEs DE COLING-92, NANTES, 23-28 AOOT 1992 5 2 8 PRec. OF COL1NG-92, NANaT.S, AUG. 23-28, 1992 
'clean' 
souji-surn to clean rooms 
kuriiningu-surn to clean clothes with chemicals 
instead of water 
A pair of "kooto-knriining'u" co-occurs most fre- 
quently in the target language, so the sentence 
may be translated into "Kooto -no ten joe-ha kireinl 
kuriiningu-sareteita.". But using DMAX Criteria, 
'ceiling' is selected as a basis for the equivalent 
translation selection of 'court', and "saibansho" is 
selected as an equivalent translation of 'court' by 
the comparison between statistics for co-occurrence 
on the pairs of "tenjoo-saibansho" and "tenjoo 
kooto'. 
4 Calculation of Linguistic 
Statistics for Semantic 
Interpretation 
In language understanding systems or machine 
translation systems throngh semantic expressions, 
one suitable meaning must be selected out of the 
ones described in a dictionary according to an entry 
word. However in conventional systems the mean- 
ing selection mechanism isn't robust and cannot 
select the most suitable meaning only by logical 
restrictions described in the dictionaries. We pre- 
sented a new method for the equivalent transla- 
tion selection in the former chapter using statis- 
tical data on source language and target language 
through bilingual dictionary. To apply this method 
to meaning selection, it is necessary to calculate 
statistical data on the pairs of each meaning in ad- 
vance, but there is no means of calculating them 
automatically. 
We have already devdoped an interlingua- 
based machine translation system whose interlin- 
gun named PIVOT doesn't depend on arty par- 
ticular natural language \[Muraki 86, ichiyama 
89, Okumura 91\]. In its dictionary, a.s illus- 
trated in Figure 4., expressions in the source lan- 
guage are mapped onto some interlingua vocab- 
ularies (CONCEPTUAL-PRIMITIVE:CP), which 
are next mapped onto some equivalent translations. 
Then we propose a new method of computing lin- 
guistic statistics for occurrence of meanings auto- 
matically using this format of dictionary. 
Suppose linguistic statistics on the pairs of ex- 
pressions in both source and target language texts 
have already been calculated. In case of transla- 
tion, when an expression Si occurs in the source 
language text, an equivalent translation Tij k is de- 
cided through the passage of Si :=*'Cij ~Tij~, and 
as a result, CPCIj is also selected from the CPs 
corresponding to the expression Si. Therefore, the 
linguistic statistics on the pairs of CPs or meanings 
is nothing but coupling linguistic statistics on the 
pairs of corresponding exl)ressions in the target lan- 
guage text. Thus, the linguistic statistics ~Z on the 
pairs of the meaning expressions in the dictionary 
can be obtained as the sum of the linguistic statis- 
tics w on the pairs of target language oxpressious 
according to the following equation. 
fi(C.,,Cb,,) = ~wm(Ta.,v,T~,,,q) 
p,q 
This linguistic statistics can be added to the dic- 
tionary in advance I and we c~n select the meaning 
in the same way as equivalent translation selection. 
5 Conclusion 
We lu'oposed a new method DMAX Criteria 
(Double Maximize Criteria based on Dual Corpora) 
in this paper. It can select a suitable equivalent 
translation or meaning using the statistical data 
extracted from both source and target language 
corpora even when linguistic restrictions described 
in the dictionary or grammar cannot. The depen 
dency relation in the source language is reflected 
in the translated text through bilingual dictionary. 
Moreover, the nmthod has the following features: 
1. It utilizes linguistic statistics as context infer 
motion in addition to logical restrictions effec- 
tive for ambiguity resolution. 
2. The source of the linguistic statistics is the 
dual corpora of source and target languages, 
not the bilingual corpora (the target language 
text doesn't have to be the translation of the 
source language text). 
3. The linguistic statistics can be coml)uted send- 
automatically in advance. 
4. Tim linguistic statistics on the pairs of mean- 
ing expressions are computed from the lin- 
guistic statistics in source and target language 
texts with the interlingua-based bilingmd dic- 
tlonary to resolve ambiguity in meaning inter-. 
pretation. 
Based on this method, we have carried out an 
experinmnt on a limited-scale translation system, 
attd confirmed eti~ctiveness of the method. We are 
preparing further experiments on a large-scMe dual 
corpora with PIVOT interlingua dictionary. Their 
result will he reported on another paper. 
6 Acknowledgments 
The authors wish to thank Mr. Masse WATARI 
for his continuous encouragement. The authors 
also thank the members of Media Technology Lal> 
oratory for their good suggestkms. 
Acrgs DE CoLING-92, NANT~, 23-28 Aot~r 1992 5 2 9 PRec. OF COLING-92, NA~rES, AUG. 23-28, 1992 
~tatistics for co-occurrence ~ bilingual dictionary t statistics for co-occurrence in source language text I ~ in target language text 
f nekutai ~ ; nekutai--t|e ,, .-tle ~ ~ 50 
50 ,' ' ~-coat ~, ,' _~- coat ; 
\ Yi" ..... ' saibankan .. , ~.salbankan--Judge ; 
Baibansho J ....... ~ ..... ¢.saibansho .... court" ,, 
Figure 1 -sono saibankan-wa kooto-to nekutai-o katta." 
'The judge bought a coat and a tie.' 
AcrEs DE COLING-92, NANTES, 23-28 AOt'rr 1992 5 3 0 PROC. OF COLING-92, NANTES, AUG. 23-28, 1992 
• ~, ~' fstatistics for eo-occurrcllCe J statistics for co-occurrence, . ~ I bilingual dictionary ;. . , , 
m source language text ~ ; ,,in target langoage text , 
_~oeorl ~-----~,---~r~oeori .bird ~ ~ bird "~ ,, 
/ 50 " ~ ,'~-e ".L____ ____N. catle ~ ! 
' , , 60 , 4,0 I i jba,, be,, I 
l booru ~booru ~ ~ ! 3. i ~ --'-bowl ~v----"~--~ bOWl \] 
=izu ~=izu ~water ~water'1 
$ ........... ....... e , ................................ *' 
Figure 2 "Kotori-no kago-ni mizu-o ireta booru-o oita." 
'I put a bowl filled with water in the bird cage.' 
$ s t 
;statistics for co-occurrence, l .... ,' I statistics for co-uccurrence . I , bihngoal dictionary , 
in source language text ~ I ,, ~ in target langmige text 
celllnn -. @celllng--een3oo ~,~eon3oo 
4 ; '~ ; ' • 
'2~ court ~-----~-~, Crourt<:~kooeo ~ kooeo ~\]~0 30 i • N , , -, ,--7 ""q- / 
:~ 20 ~ ~ ! ;/20 .. At 
i X I ', $ ~sou~i -~,-~s°uJ:L '-~"d~|l 
: x. clean d~rclean<z~ .", • ~ "~,~ kuriinin~" ~-~ ~" , , , Kurllnln ~ - ~u 
: ~.o ~, '~ ~" ' 
coat J ....... ~o.-~-coat kooeo 
Figure 3 'The ceiling of the court was cleaned quite well.' 
"Saibansho no tenjoo-wa kireini souji-sareteita." 
source language expressions interlingua target language expressions 
• ~'--~.~..~_. • ~.......... • 
Figure 4 Bilingual dictionary of the interlingua-based translation system 
AETES DECOLING-92. NANTES, 23-28 AOt~" 1992 5 3 1 I'ROC. OV COLING-92, NANIT, S. AtJc;. 23-28. 1992 

References 

\[Brown 90\] P.F.Brown et al. "A Statistical Ap- 
proach to Machine Translation", Computa- 
tional Linguistics, Vol.16, No.2, 1990 

\[Doi 92\] S.Doi and K.Muraki "Robust Translation 
and Meaning Interpretation Mechanism based 
on Examples in Dictionary", Prec. of 44th 
Annua\] Conference oflPSJ , 1P-2, 1992 (in 
Japanese) 

\[Ichiyama 89\] S.Ichiyama "Multi-lingual Machine 
Translation System," O~ce Equipment and 
Products, 18-131, pp.46-48, August 1989 

\[Muraki 86\] K.Murakl "VENUS: Two-phase Ma- 
chine Translation System," Future Genera- 
tions Computer Systems, 2, pp.117-119, 1986 

\[Muraki 91\] K.Muraki and S.Dol "Translation 
Ambiguity Resolution by using Text Corpora 
of Source and Target Languages", Proc. of 5th 
An~ua/ Conference of JSAI, 11-7, 1991 (in 
Japanese) 

\[Nagao 84\] M.Nagao "A Framework of a Mechani- 
cal Translation between Japanese and English 
by Analogy Principle", ArtificiM and Human 
Intelligence, ed. A.Elithorn and R.Banerji, 
North-Holland, 1984 

\[Nomiyama 91\] H.Nomiyama "Lexieal Selection 
Mechanism Using Target Language Knowl- 
edge and Its Learning Ability", IPSJ-WG , 
NL86 8 , 1991 (in Japanese) 

\[Okumura 91\] A.Okumura, K.Muraki and S.Aka- 
mine "Multi-lingual Sentence Generation from 
the PIVOT interlingua," Prec. of MT SUM- 
MIT III, pp.67-71, July 1991 

\[Sat, o 90\] S.Sato and M.Nagao "Toward Memory- 
based Translation", COLING-90, 1990 

\[Sumita90\] E.Sumita, H.Iida and H.Kohyama 
"Example-based Approach in Machine Trans- 
lation", hffoJapan'90, 1990 
