Idiosyncratic Gap: A Tough Prolem to Structure-bound 
Machine Translation 
Yoshihiko Nitre 
Advanced Research Laboratory 
Hitachi Ltd. 
Kokubunji, Tokyo 185 Japan 
ABSTRACT 
Current practical machine translation systems (MT, 
in short), which are designed to deal with a huge 
amount of document, are general\]y structure-bound. 
That is, the translation process is done based on tile 
analysis and transformation of the structure of 
source sentence, not on the understanding and para- 
phrasing of the meaning of that. But each language 
has its own :~yntactic and semantic idiosyncrasy, and 
on this account, without understanding the total mean- 
ing of source sentences it is often difficult for MT 
to bridge properly the idiosyncratic gap between 
source~ and target- language. A somewhat new method 
called "Cross Translation Test (CTT, in short)" is 
presented that reveals the detail of idiosyncratic 
gap (IG, in short) together with the so-so satis- 
fiable possibility of MT. It is also mentioned the 
usefulness olf sublanguage approach to reducing the IC 
between source- and target- language. 
i. Introduct:ion 
The majoJ:\[ty of the current practical machine 
translation system (MT, in short) (See \[Nagao 1985\] 
and \[Slocum 11.985\] for a good survey.) are structure- 
bound in tile sense that al\] the target sentences (i.e. 
translated ,~entences) are composed only from the 
syntactic st:ructure of the source sentences, not from 
the meaning understanding of those. Though almost 
all tile MT are utilizing some semantic devices such 
as semantic feature agreement checkers, semantic 
filters antl preference semantics (See \[Wilks 1975\] 
for example.) which are serving as syntactic structur- 
al disambiguation, they still remain Jn structure- 
hound approaches far from tile total\[ meaning under- 
standing approaches. 
\]?he structure-bound MT has a lot of advantageous 
features among which the easiness of formalizing 
translation process, that is, writing translation 
rules and the uniformity of lexicon description are 
vital from the practical standpoint that it must 
transact a huge vocabulary and \]numerable kinds of 
sentence patterns. 
On the other hand, the structure-bound MT has the 
inewttable limitation on the treatment of lingu:istic 
idiosyncrasy originated from the different way of" 
thinking. 
In this paper, first of all, we will sketch out 
the typical language modeling techniques on which the 
structure-bound MT(= current practical machine 
translation systems) are constructed. Secondly, we 
will examine the difference between the principal 
mechanism of machine translation and that of human 
translation irom the viewpoint of the language under- 
standing abi\]ity, l'hirdly, we will illustrate the 
structural idiosyncratic gap (IG, in short) by com- 
paring the sample sentences in English and that in 
,lapanese. These sentences are sharing the same reCall- 
ing. This comparison will be made by a somewhat new 
method which we call "Cross Translation Test (CTT, in 
short)", which will cventual\]y reveal the various IGs 
that have origins in the differences of culture, i.e., 
the way of thinking or the way of representing con- 
cepts. But at" the same Lime, CTT wiJl give some 
encouraging evidence that the principal technologies 
of today's not-yet-completed structure-bound HTs have 
the potentia\] for producing barely acceptable trans- 
lation, if the source language sentences are taken 
from tile documents of less equivocations or are ap- 
propriately rewritten. Finally, we will briefly 
comment on the sub\]anguage to control or normalize 
source sentences as the promising and practical ap- 
proaches to overcoming the IGs. 
2. Modelin~ of Natural Lan~ 
Modeling natural, language sentences is, needless 
to say, very essential to all kinds of natural 
language processing systems inclusive of machine 
translation systems. The aim of mode\]ing :is to 
reduce the superficia\] complexity and variety of the 
sentence form, so as to reveal the indwell:Lug struc- 
ture which is indispensable for computer systems to 
analyze, to transform or to generate sententia\] 
.representations. 
So far various modeling techniques are proposed 
(See for example \[Winograd 1.983\].) among which the 
two, tile dependency structure modeling (Figure l) and 
the phrase structure modeling (Figure 2) are impor- 
tant. The former associated with semantic cole 
labeling such as case marker assignment is indispen- 
sable to analyze and generate Japanese sentence 
strueture (See for example \]Nit,a, et all. 1984\].), 
and the latter associated with syntactic rote label- 
ing such as governor-dependent assignment, head-com- 
plement assignment, or mother-daughter assignment 
(See for example \[Nitta, et el. 1982\].) is essential 
to analyze and generate English sentences. 
Kono kusuri-wa itsft.rli sugu 
(thisj \[medicine\] \[on stonmchache} \[immediately I 
\[Lit. Fhis medicine takes effect on stomachache mlmediately.l 
kiku Afr T 
kusuri itsu sugu 
kono 
Figure 1. 
kiku 
\[take effect\] (Jl) 
(E':) 
A, L, M : Semantic Roles (or Case Markers), 
A : ABeRIwe, M : Modifier, L : Locative 
Example for Dependency Structure Modelin!! 
"To what extent should (or can) we treat semantics 
of sentences?" is also very crucial to the decision 
for selecting nr designing tile linguistic model for 
107 
machine translation. But it might be fairly asserted 
that the majority of the current "practical" machine 
translation systems (MT, in short)are structure-bound 
or syntax-oriented, though almost all of them claim 
that they are semantics-directed. Semantics are used 
only for disambiguation and booster in various 
syntactic processes, but not used for the central 
engine for transformation, generation and of course 
not for paragraph understanding (See \[Slocum 1985, 
pp. 14 ~16\] for a good survey and discussion on this 
problem; and see also \[Nitta, et al. 1982\] for the 
discussion on a typical (classical) structure-bound 
translation mechanism,i.e, local rearrangement 
method). Here "practical" means "of very large scale 
commercial systems" or "of the daily usage by open 
users", but neither "of small scale laboratory sys- 
tems" nor "of the theory-oriented experimental sys- 
tems". For structure-bound machine translation 
systems, both the dependency structure modeling and 
the phrase structure modeling are very fundamental 
technical tools. 
* This medicine has an immediate effect on stomachache. (El) 
° \[Lit. Co) ~1~ FHi~a) &l£-~/-lk¢9 I~ ~/l~tz ~.~C~,~To.\] (J'l) 
Kono kusuri-wa itsft no ue-nl subayai kikime-wo mottedm. 
S 
NP 
Ni P PIP 
(SUB J) (I'RH)) (On J) (ADV) 
Ttlis medicine has an immediate effect on stonlachache. 
SUB J, PRED, OBJ, ADV : Syntactic Roles. 
SUBJ: Subject, PRED: Predicate llead, OBJ: Object. ADV: Adverbial. 
Figure 2. Example of Phrase Structure Modeling 
The semantic network medeling, which is recently 
regarded as an essential tool for semantic process- 
ing for natural languages (See for examples 
\[SimmOns 1984\].), might also be viewed as a variation 
of dependency modeling. However modeling problems 
are not discussed further here. Comparing Figure 1 
and Figure 2, note that the dependency structure 
modeling is more semantics-oriented, logical and 
abstract, in the sense of having some distance from 
surface word sequences. 
3. Machine Translation vs. lluman Translation 
Today's practical machine translation systems (MT, 
in short) (See for example \[Nagao 1985\] and \[Slocum 
1985\].) are essentially structure-bound \]iteral type. 
The reasons for this somewhat extreme judgement are 
as follows: 
(i) The process of MT is always under the strong 
control of the structural information extracted 
from source sentences; 
(2) In all the target sentences produced by MT, we 
can easily detect the traces of wording and 
phrasing of the source sentences; 
(3) MT is quite indifferent to whether or not the 
output translation is preserving the proper 
meaning of the original sentence, and what is 
worse, MT is incapable of judging whether or 
not; 
(4) MT is quite poor at the extra-sentential infor- 
mation such as situational information, world 
knowledge and common sense which give a very 
powerful command of language comprehension. 
Now let us see Figure 3. This rather over- 
simplified figure illustrates the typical process of 
Japanese-English structure-bound machine translation. 
Here the analysis and transformation phase are based 
on the dependency structure modeling (cf. Figure i) 
and the generation phase is based on the phrase 
structure modeling (cf. Figure 2) (For further 
details, see for example \[Nitta, et al. 1984\].). 
This figure reveals that all the process is bound by 
the grammatical structure of the source sentence, 
but not by the meaning of that. 
Source Sentence: 
Kono kusuri-wa itsu-ni sugu kiku. ~ 
Analysis 
Model Representation: 
kiku (TNS: PRESENT ....... SEM: KK, .....) 
\[take effect\] 
kusuri ( ...... SEM: KS, .....) 
\[medicine\] 
kono 
\[this\] 
itst~ (.....) sugu (.....) 
\[stomachache\] \[immediately\] 
Transformation --\[" Maybe some heuristic l'ule, 
HR (KK, KS, ...-) suggests \] 
the change m the predicate-\] 
L argument relation. 3 
motsu (,...) 
\[have l 
kusuri (_...) itsu (.....) k6ka (...-) 
\[medicinel \[stomachache\] \[effect\] 
M! M l 
kono sugu (...,.) 
\[this\] \[immediate\] 
~ Genelation 
Phrase Structure Formation: 
Target Sentence: 
(El): This medicine has an immediate effect on stomachache. 
Figure 3. Simplified Sketch of Machine Translation Process 
Thus, the MT can easily perform the literal 
syntax-directed translation such as 'from (Jl) into 
(E'I)' (cf. Figure i). But it is very very dif- 
ficult for MT to produce natural translation which 
reflects the idiosyncrasy of target language) pre-- 
serving the original meaning. (El) is an example of 
a natural translation of (J1). In order for MT to 
produce this (El) from (Jl), it may have to invoke 
a somewhat sophisticated heuristic rule. In Figure 
3, the heuristic rule, HR (KK, KS, ...), can sucess- 
fully indicate the change of predicate which may 
improve the treatment for the idiosyncrasy of target 
sentence. 
But generally. , the treatment of idiosyncratic gap 
(IG, in short) such as 'that between (Jl) and (El)' 
108 
is very difficult for MT. It might' be almost im- 
possible to find universal grarmnatical rules to 
manipulate this kind of gaps, .and what is worse, 
the appropriake heuristic rules are not always 
found successfully. 
On the other hand, tile human translation (HT, in 
short) is essentially semantics-oriented type or 
meaning understanding type. 3?he reasons for this 
judgement are as follows: 
(i) HT is free from the structure, wording and 
phrasing of a source sentence; 
(2) liT can "create" (rather than "translate") freely 
a target sentence from something like an image 
(Hagram obtained froln a source sentence (F~gure 
4); (Of course the exact structnre of th\].q image 
diagram is not yet known); 
(3) }IT often refers tile extra-linguistic knowledge 
f~uch as the common sense and the culture; 
(4) Thus, tIT cart overcome the idiosyncrat:ic gaps 
(\]G) freely and unconsciously. 
Source Sentence(s) ..... ~/ b m" ng \ \[ hkc \ 
\[ Image Diagram ) 
Citation \ \[ What tile source \] \] 
Iarget Sentence(s) ................. -~ ~e.Uence(s)nlean(s)/ 
• . ~%_.~__ J 
Fiqure 4. Human \]'ra.slation Process 
meaning but each of which be\].ongs to different 
language. The reason for comparing tile two sen- 
tences is that we cannot: examine the linguistic 
idiosyncrasy itself. Because, currently, we cannot 
fix the one abstract neutral meaning without 
using something like the image diagram (cf. Figure 
4) which is not yet elucidated. 
In order to examine tlm idiosyncratic gap, we 
have devised the practical method named "Cross 
Translation Test (CTT, in short)." The outline of 
CTT is as follows: 
\]first, take an appropriate well-written sample 
sentence written in one language, say English; Let 
E denote this sample sentence; Secondly, select or 
make the proper free translation of E in the other 
\].anguage, say Japanese; \],et J denote this proper 
free translation; J must preserve tile orlginal mean- 
ing of E properly; At the same time, make a literal 
Lrans\].tion of F, in the same language that ,\] is 
written in; Let J' denote this literal translation; 
Lastly, make a Literal translation of J in the same 
language.that E is written in; Let E' denote tM.s 
literal translation. 
iIere, the "literal" translation means the transla- 
tion that :\[.s preserving the wording, phras:ing and 
various senteatial structure of the original (source) 
sentence as much as possible. Then, eventually we 
may be able to define (a~d examine) the idiosyncratic 
gap, \].C, by Figure 5. Iu. other words, we may be able 
to exam:ine and grasp tile i.di.osyncratie gap by compar- 
l.ng \]:he structure of 1)', and that ot! 1,',', or by comparing 
that of ji and that of J. 
\[n order {:o s:imp\]ify the arguments, let us assume 
Lhat some kind of diagram is to be :\[nvokezd item \]:he 
understaadiing of the original scntence. 'I/his d:iagram 
may (or should) be completely free from the sopcr- 
ficta\] struclnre such as wording, phras~nF,, subject- 
object relation and so on, and may be strengthened 
and rood:irked l)y varleus exCra--\]iuguistlc knowledge. 
\] t may be early for hnmalTl to compose the sentetlces 
such as (J2) arm (E2) from tlu{s kind of :\]aaage din-- 
gram .invoked from (J1). But the sentences su<h as 
(J'\]), (J'2), (E'l) and (g'2) will never be composed 
by huma\[\] unc\[(lr tile nolTnla\] eond\].tlons. 
o ~o) ~.'& f,.ktT~ '¢IcOf, ft'~/~ s J ¢ £tl./a., (J2) 
Ko,,o ktlsu it.we \[iomll.to 1 lio-ita,,i,.ga sugu tore-ru. 
\[this\] ~nlellicme I \[if(you) take I \[stomadlacne\] \[soon / \[delmved l 
o \[l.it. If you Iake this medicine :,ou will sonn be dep\[ived of a stomachache \] # (E'2) 
* This medicine will so.n cure you ol lhe stmnachache. 
o \[l,a. c_v\] )~la &(~t:{- J ¢1c ~'It,llb~G ~;)t~4~ d 
Kono kusun-wa :ma{a.wo saga-hi ilsu-kara suku/i d~ro. 
{tills\] \[medicine\] \[>m:\] \[so(ml \[of tile stonlache\] \[will cure\] 
(E2\] 
#(r2) 
Now, note that there are b:\[g structural, gaps 
between (gl) and (\],;\]), and between (,\]2) and (E2), 
whic.h are tile natura\] ref\]eetJons o\] \]:ingu:istic 
idiosyncrasy orginated in thc culture, i.c, lhe 
difference of the way of thJnki.ng. So far we have 
seen that MT is poor at tile idiesyncrasy treatment 
and eonverse\]y HT :is good at that. This d:ifference 
between MT and HT depends on whether or not it has 
tile ahi\]i.ty c f meaning underst:and:ing. 
Iff 
........... ~ ...... E ........................... j' ....-, .... / I 
.... '-' - E' ~ ............... ± J - - 
IG: Idiosyncratic Gap 
I,T: Literal Translation 
FT: Free Translation 
E, E': Sentences Written m English 
J, J': Sentences Written in Japanese 
Is this paper, we have assumed that: 
I,T '= MT and I:T ~ HT, 
where, MT: Machine Translation, and lfi': Human Translation. 
Fiyure 5. Illustrative Definitioil of Idiosyncratic Gap 
Now, note that we (:all assume the re\]atJonshil) , 
i,'\]\] e= MT, 
a n d 
\]\]'T -& \]HT, 
where "-" " denoLes "near\]y equal" or "be a\].most equiv- 
alent to". Namely, we can assume that the \]itera\] 
LranslatJon, ILl', which i.s preserving the wording, 
phrasing and structure of tile source sentence, Js 
almost e-qu:\[va\].ent to the idealized competence of 
today's practical structure-bonnd machine trans\]ation, 
MT. Tim rationale of this assumption has already been 
discussed in Section 3. 
£n this section, let us examine the idiosyncratic 
gaps between the two sentences which share the same 
In this paper, the litera\] trans\]ation, \],T (" MT), 
is performed by tracing the \[)roeedural steps of a 
virtual machine translation system (VMTS) theoretical- 
ly. \]1ere, the VMTS is a certain hypothetical system 
109 
which never models itself upon any actually existing 
machine translation systems, but which models the 
general properties of today's practical structure- 
bound machine translation systems. 
Now let us observe the gap, IG, by applying CTT to 
various sample sentences. First, let us take an 
example with large gaps. 
Kokkyo-no nagal tonnent-wo nuken~-to yuki-guni de-atta. 
\[of borderl \[Iongl \[ tunnell (after passing throughl \[snow countryl Iwasl 
• \[Lit. After passing through the long border runnel, it was the snow country.\] +(E'3) 
• Tile train came out of the long tunnel into the snow country. (E3) 
Ressha-wa nagal tonnenl-wo fluke-re ytlki-guni-ni de-ta. 
(J3) is taken from the very famous novel "Yuki- 
guni" written by Yasunari Kawabata, and (E3) is taken 
from the also famous translation by Seidensticker. 
(E'3) :is the slight modification of \[Nakamura 1973, 
p.27\] and (J'3) is taken from the same hook. In (E3) 
the new word "the train \[ressha\]" is supplemented ac- 
cording to the situational understanding of the para- 
graph including (J3) which may, currently, be possible 
only for HT. 
(J3) is a very typical Japanese sentence possessing 
the interesting idiosyncrasy, i.e., (J3) has no super- 
ficial subject. But in (J3) some definite subject is 
surely recognized, though unwritten. That is "the 
eyes of the storyteller", or rather "the eyes of the 
reader who has already joined the travel to the snow 
country by the train". So the actual meaning of (J3) 
can be explained as follows: 
After I (= the reader who is now experiencing the 
imaginary travel) passed through the long border 
tunnel by the train, it was the snow country 
tha~ I encountered. 
Thus (J3) is very successful in recalling the 
fresh and vivid impression of seeing (also feeling and 
smelling) suddenly the snow country to the readers. 
(J3) has a poetic feeling and a lyric appeal in its 
neat and concise style. 
But the English sentence such as (E3) requires the 
concrete, clearly written subject, "the train \[ = res- 
sha\]" in this case, and this concrete subject requires 
the verb, "came", and again this verb requires the two 
locative adverbial phrases, "out of the long tunnel" 
and "into the snow country". Thus, the original 
phrase "yuki-guni de-atta. \[ = it was the snow 
country.\]" in (J3) has completely disappeared in 
(E3), but the new adverbial phrase "into the snow 
country \[=yuki-guni-ni\]" appears instead. These 
drastic changes are made under the strong influence 
of linguistic idiosyncrasy, and, at the same time, 
with the effort to preserve the original poetic 
meaning as much as possible. 
Consequently, these changes have invoked a large 
distant gap, IG between (J3) and (E3). But this gap 
is indispensable for this translation from (J3) into 
(E3), 
HT: (J3) ÷ (E3) , 
where, \](J3) - (E3) I ~ l( E 3) - (E3) I ~ ~G = 
large. 
One more comment. Note that as a result of this 
large gap, the literal translation from (J3) into 
(E'3), 
LT: (J3) ÷ (E'3) 
where, J(J3) - (E'3)J~J(E'3) - (E'3) I = 0 
has failed to preserve the original meaning, i.e., 
(E'3) is an unacceptable translation which is 
misleading. Because (E'3) can be interpreted as: 
After something (=it) finished passing through 
the long border tunnel, something became 
(= changed into) the snow country. 
However, it is not always the case with idio- 
syncratic gaps. Lastly, let us now observe the 
somewhat encouraging example favorable for struc- 
ture-bound machine translation, MT ("-LT). In the 
following quadruplet, the gap is not so small but 
the gapless translation, i.e~, LT ('MT) is accept- 
able. The following sample sentence (E4), is the 
news line taken from \[Newsweek, January 18, 1982, 
p.45\]. 
• tie may \]lave saved fi~e flight from a tragic 
\[kare\] \[kamo-~hire-nail\[ kyfljo-shi-ta \] \[sono\] \[teiki-bin\] \[kara\] \[higeki-teki) 
repeat performance of tile American Airlines DC-IO crash that Killed 275 
\[hanpukul I jikk6 I \[nol \[tsuirakul \[l~oroshi-tal 1275 nin-nol 
people in Chicago in 1979. 
\[hito-bitol \[Cllicagc-de\] \[1979 hen-nil 
Kare~'a sono teiki-bin-',~o, 1979 nen-m Chicago-de 275 nin-no hito-bito-wo koroshi-ta 
American-K6ktl-no DC-I(\]-no tsuiraku-no higeki-teki hanpuku-no jikk6-kara 
$~J~btc 9)6 b~tX~0 
kyfljo-shi-ta kamo-shirenai. 
kore-ni-yotte kono ki-wa, shisha 275 m¢i-wo dashi-ta 1979 nen-no Chicago-kf~k6-de-no 
tsuintku-jiko-no higeki-no ni-no-mai-wo sake-eta-to ie-y6. 
• Lit. It may safely be said that. by this, this airplane could eseapefrom 
\[to-ie-you\] \[kore-m-yottel Ikono hikouki\] \[sake-etal \[kara\[ 
tragic repetition of crash accident of American Airlines 
\[higeki-tekil \[hanpuku, ni-no~mail \[nol Itsuirakul Ijikol \[nol 
DC-10 in Chicago Airport in 1979 that produced 275 dead persons. 
\[Chicago-KflkO-de-no\] \[ 1979 nen-nil \[daslfi-tal \[silishal 
(Ed) 
#(J'4) 
(g4) 
a(E'4) 
• The soldiers fired at the women and we saw several of them fail. 
Heishi*taehi-ws on-na.tachi-ni happo-shi-ta soshite 
\[soldiers\] \[at the womanl \[firedl \[and\] 
wareware-wa kare-ra-no s~nin~ga taoreru-no-wo 
\[we\] \[of them\] \[several\] If all\] 
The free translation, (Jd) is taken from \[Eikyo 
1982, p.203\] with slight modifications. For tile 
reason of space limitation we have omitted the 
comments to this example. 
Let us see one more example sentence (iS) in 
order to confirm that the structure-bound MT, which 
lacks the ability to understand the meaning of source 
sentences, can produce the barely passable trans- 
lation, and to try to search for the reason for this. 
(as) 
1~o } 0'5) mila 
Isaw\[ 
(E5) is one of the sample sentences in \[Wilks 
1975\] where anaphora and references are discussed as 
the important elements of sentence understanding. 
As is pointed out by Wilks, a certain extent of 
understanding is necessary to solve the anaphora and 
reference problem of the sentence (E5), that is, 
whether "them" refers "the soldiers" or "the women". 
And actually, the structure-bound MT, which cannot 
understand the meaning of "fired.at" and "fall", 
may translate "them" into "kare-ra" being indiffer- 
110 
cut tO tile anaphora and references. ?in Japanese 
"kare-ra" denot:es the pronoun of \]male, third person, 
plural\], and "kanojo-ra" denotes tile pronoun of 
\[female, third person, plural\], so (,7'5) \].s somewhat 
misleading translation. Nevertheless, human (i.e. 
almost all thc~ Japanese readers) can sure\].y under- 
stand the sentence (J'5) correctly; that is, they 
can understand that "kare-ra" (="them") is referring 
"on-na-tachi" (= "the women") uot "heishi-tachi" 
(="the soldie-rs"). The reason of this is that the 
human's brain can understand lille ,leaning of the 
sentence (J'5) with the support of the colmnon sense 
like : 
X fires at Y + Y will severly wounded 
+ Y will fall and die, 
which functions as the compensator for the anaphora 
and references. 
The above example shows that the lack of the 
anaphoric ability in structure-bound MT may sometimes 
be compensated by the human-side, which is the en- 
couraging fact for MT. 
So far the point we are trying to make clear is 
that even IG-neglecting MT (= structure-bomld machine 
translation systems) can generate target sentences 
that convey the correct meaning of source sentences, 
when tlre \].att:er are written J.n simple, logical, struc- 
tures. 
5. Conclusions 
This paper has dealt with the \].imitations and 
potentials of structure-bound machine translation 
(MT) from the standpoint of the idiosyncratic gaps 
(IG) that exist between Japanese and \]';nglish. Tile 
conmmrcial machine translation system (MT) curreut\].y 
on the market: are inept at handling riG since they are 
still not capable of understanding the nleaning of 
sentences l:i.ko human translators can, and are thns 
bound by the ,qyntactic structures of the source 
sentences. This was pointed out by applying the 
Cross Translation Test (CTT) to several sample 
sentences, which brought the performance limitations 
of structure-bound mach:i.ne translation into sharp 
relief. But the CTT applications also showed that if 
the source language sentence Js simple, logical and 
contains few ambiguities, today's fG-neglectJng 
machine translation systems are capable of generating 
acceptable target sentences, sentences that preserve 
the meaning of the original (source) sentences atrd 
can be understood. 
However ~ source sentences are not always simple, 
logical and unambiguous. Therefore, to improve the 
performance of machine trans\]ation systems it will be 
necessary to develop technology and techniques aimed 
at rewriting .';ource sentences prior to inputting them 
into systems, and at formalizing (norma\]izing) and 
control.ling source sentence preparation. One move in 
this direction in recent years has had to do with tile 
source language itself. Research has been steadily 
advancing in the area of Sub\].anguage Theory. Sub- 
languages are more regulated and controlled than 
everyday humml languages, and therefore make it easier 
to create simple, logical sentences that are re\].ative- 
ly free of ambiguities. Some examples of sublanguage 
theories currently under study are "sublanguage" 
\[Kittredge and Lehrberger 1982\]~"controlled language" 
\[Nagao \].98311 and "normalized language" \[Yoshida 
\]984\]. 
The aim of these sublanguage theories is to assign 
certain rules arld restrict:lens to \]:he everyday human 
\]anguagea we use to trausmXt and explain information, 
improving the accuracy of parsing operations necessary 
\]for nlachJ.ne processJ.ng~ aud enhancing human under- 
standing. Some examples of the \].ingnJstic rules and 
restrictions envisioned by the sublanguage theories 
are rules governing the creation of lexicons 
\[Kigtredge and Lehrberger 1982\], rules governing 
the use of function words related to the log:tca\] 
construction of sentences \[Yoshida 1984\] and ru\]es 
governirlg the expression of son\]cut\]el dependencies 
\[Nagao 1.983\] . 

References 

Eikyo \[Nihon-Eigo-Ky~Jku-Ky$kai\] (eds.) (1982), '2 
Ky~t Jitsuy$ Ergo Ky~hon' ('2nd Class Practical\] 
English Textbook' ) , N:/hon-Eigo-Ky$iku-KySkai, 
Tokyo, 1982 pp.202-203 (in Japanese). 

Kittredge, Richard and J. Lehrberger (eds.) (1982), 
'8ublanguage: Studies of Language in Restricted 
Semantic Domains', Walter de Gruyter, Berlin, 
New York, 1982. 

Nagao, Makoto (1983), 'Selgen-Gengo-no Kokoromi' ('A 
Trial in Control.led I,anguage'), in ShJzen- 
(~n_\]39-Shori-G"i j nt su _S3£m~iun h Yok-~--~l$,'=fn f o r - 
mat\]on Processing Society of Japan, Tokyo, 1983 
pp. 91-99 (in Japanese). 

Nagao, Makoto (\]985), 'Kikai-Ilon-yaku-wa Doko-made 
Kan$--ka' ('To What Extent Can Machine Trans- 
late?'), K ag~u., lwanami, Tokyo, vol. 54 no.9, 
1985, pp. 99-107 (in Japanese). 

Nakamura, Yasuo (\]973), 'ilon-yaku-no Gijutsu' ('Tech- 
niques for Translation'), Ch~-k$-Shinsho 345, 
Ch(~8)-K~ron-Sha, Tokyo, 1973 (in Japanese). 

Newsweek (\]982), 'Newsweek' January, 18, 1982 p.45. 

Nitta, Yoshihiko, et al. (1982), 'A Heuristic Approach 
to F, ug\]ish-into-Japanese Machine Translation', 
in J. Horocky (ed). Prec. COLING 82:__~t Prgg ~ 
\[Proceedings of the 9th Internatim:a\] Conference 
on Computationa\] Lingnistics\]. ~'Iorth-Ilolland 
Publishing Company, 1982, pp.283-288. 

NJtta, Yoshihiko, et al. (1984), '£ Proper Treatment 
of Syntax and Semantics in Machine Translation', 
:in Prec. COLING 84 (at Stanford_) \]Proceed\]ntis 
o£ the-lOi:l~' International Conference on Coln-- 
putatdona\] Lingudstics\], Association for Com- 
l~-UTatl~ffa\]7\]Ti-ngui.~ics, 1.984, pp. 159-166. 

Simmons, Rohert F. (1984), 'Computations from the 
English', Prentice-Hall, Englewood C\].Jffs, New 
Jersey, 1984. 

S\]ocum, Jonathan (1985), 'Machine Translation: Its 
llistory, Current Status and Future Prospects' 
Cqnli~utational LJ_nguist.ies, vol. 1.1 , no.l, 1984, 
pp. 1-17. 

Wilks, Yorick (1975), 'An Intelligent Analyzer atrd 
Understander of EnglJ.sh', Communications of the 
ACM, vo\].18, no.5, I!)75, iIp.264-274. 

Winograd , Terry (1983), 'Language as a Cognitive 
Process: vol. I : Syntax', Addison-Wesley, Menlo 
Park, Calif. 1983. 

Yoshida, Sh$ (1984), 'Nihongo-no Kikakuka-nJ-kansuru 
KisotekJ Kenky~,' ('Basic Study on the NornmlJza- 
tion of Japanese Language'), Sh\]wa 58-.non-do 
Kagaku Kenky~-Hi IIojokin Ippan-Kenky-~-TB) 
Kenkyu-Seika Hokoku-Sho (Research Result Report 
on the General\[ Study (B) Sponsored by tile Sh~wa 
58 Fund for Science Researc\]1) Kyushu University, 
Kyushu, \]-98~n-Japat~e)-7 
