the 
The Transfer Phase of 
Mu Machine Trans l at i on 
Nakoto NAOAO 
Jun-ichi TSUJII 
Department of Electrical Engineering 
Kyoto University 
Kyoto, Japan 606 
Sys t (.~m 
1 Introduction 
The interlingual approach to MT has been repeatedly 
advocated by researchers originally interested Jn 
natural language understanding who take machine 
translation to be one possible application. However, 
not only the ambiguity but also the vagueness which 
every natural language inevitably has leads this 
approach into essential difficulties. In contrast, 
our project, the Mu-project, adopts the transfer 
approach as the basic framework of MT. This paper 
describes the detailed construction of the transfer 
phase of our system from Japanese to English, and 
gives some examples of problems which seem difficult 
to treat in the interlJngual approach. 
The basic design principles of the transfer phase of 
our system have already been mentioned in (i) (2). 
Some of the principles which are relevant to the 
topic of this paper are: 
(a)Multiple Layer of Grammars 
(b)Multiple Layer Presentation 
(c) Lexicon Driven Processing 
(d) Form-Oriented Dictionary Description 
This paper also shows how these principles are 
realized in the current system. 
2 The Construction of the Transfer Phase 
The transfer phase of our system consists of the 
following three sub-phases (Fig. i). 
Pre-Transfer Phase (Pre-TP) 
Main Transfer Phase (MTP) 
Pc st -Transfer Phase (Post-TP) 
f-re-Transfer p .ha.:,l-~ Ma in Transfer Phase ~ P:st-Transfer :has J 
Fig. I. Construction of the Transfer Phase 
Analysis results 'of input sentences of the source 
language (SL) are represented in the form of 
annotated tree structures, from which one can 
retrieve various levels of information contained in 
the input sentences. The MTP is performed recursively 
from the top of the tree to the bottom (Fig. 2). At 
each step of the recursion, the sub-structure 
governed by a node (current node, node X ira Fig. 2) 
is transferr(~d to the corresponding structure of the 
target language (TL). This phase mainly performs 
lexJcal tran~'{fer, that is, it chooses an appropriate 
target lexical item for node X by examining the 
annotation parts of that node and its dependent nodes 
(nodes YI,..Y2,..Yn). The selection of a target 
lexical item may place certain constrains on the 
transfer of the dependent nodes. These constrains are 
expressed as property-value pairs and added to the 
annotation parts of the dependent nodes, which are to 
be utilized in the subsequent recursion steps. For 
language pairs such as Japanese and English which 
belong to quite different language families, however, 
the lexical transfer is not so straightforward. It 
often happens that single lexical items of SL 
correspond to complex (-~xpressions of TL and vice 
versa. Furthermore, certain structural changes are 
also required. 
Because the MTP recursively transfers sub-structures 
governed by single nodes, certain global structural 
differences cannot be naturally treated. Such global 
changes are deal t with by the Pre-TP and Pest-TP sub- 
phases (See section 7) . 
? 
Fig. 2. Data Structure in the Transfer Phase 
eal~Ite= Equivalent Code Speech 
Column-h 
SJ.~anese I Deep ~nglish • 
face Harker J____Case Relation Surface ~rker 
Coluan=B 
apanese \] Deep English 
rfaee Harker| Case Relation Surface Harker J 
Column-(: 
Japanese \] Translation Part~of- 
Hodifler \[ Equivalent Speech 
Column-D 
Translation Part-of- 
Equiv_ ale nt Speech 
1 I 2 
Fig. 3. Fora-orlented Dictionary for Nouns 
(Di-lingual Dictinary) 
97 
3 The Form-Oriented Dictionatz and Lexical Transfer 
of Nouns 
The following four columns are provided in the form- 
oriented bilingual dictionary of nouns (Fig. 3). The 
description of each column is expanded into 
corresponding types of lexical rule (i.e. GRADE rules 
which are stored in the dictionaries and invoked at 
specified processing phases : GRADE is the 
programming language for writing grammar rules used 
in our project). 
(1)Column A : Transfer based on the Relationship to 
the Governor (Fig. 4) 
Even major parts-of-speech such as nouns need not 
correspond between two languages. Certain Japanese 
nouns correspond to words of different parts-of- 
speech in English, depending on the surrounding 
context. 
Ex-I :~ 0) $~ ---> wooden desk 
(tree) (desk) 
1~ -~0) )~)3 ---> interactive input 
(interaction) (input) 
However, the same nouns should be translated as 
nouns in Engl~sh in contexts such as : 
Ex-2. :/g 0) ~ ---> growth of trees 
(tree) (growth) 
~(~ 0) ~U,~ ---> advantage of interaction 
(interaction) (advantage) 
Japunese Translation Field Part-of- 
_ l-Item Equivaleettree GENC°de SpeechN 
Column-A 
Marker ~ Deep English Tr~ 
Surface Case Relation Surface Marker Equivalent \[ Speech~ 
RATerial null wooden I ADJ __\] 
This indicates that: 
if '~' is used as a noun a~ifier 
and the case relation between '9};' and the governor is 'RATerial' 
then the translation equivalent is 'wooden', else 'tree'. 
Fi~. 4. Example of Descriptions in Coluan-A 
(2) Column B : Selections of Prepositions(Fig. 5) 
Certain nouns determines the prepositions which 
relate their dependents of certain deep cases to 
them, as predicates (verbs) usually do. 
(teacher) (qualification) 
..... > qualification fo_~r a teacher 
(teacher) (position) 
..... > position as a teacher 
Ex-4. 
(results) (effect) 
..... > effects on the results 
(family) (duty) 
..... > duty to the family 
98 
The semantic relationships are not sufficient for 
selecting such preposJ tions appropriately. Same 
postpositional case particles should be translated 
into different prepositions, even though the deep 
semantic relationships in Japanese are the same (thai: 
is, Japanese native speakers cannot intuitively 
distinguish the difference.) In Ex-4, for example, 
English native speakers can clearly distinguish the 
semantic relationship of 'results' and 'effects ~ 
(GOAL or OBJECT case) from that of 'family' and 
'duty' (BENEFICIARY case), whereas in Japanese the 
same postpositional case particles are used and so 
the distinction of the semantic relationships is not 
so clear for Japanese natives. We cannot, therefore, 
even expect the stability of semantic relationships 
across the two languages. 
xical-Item Equivalent 
~ effect 
Co IuJn-B \[~ur apunese 1 Deep 
face Marker\[ Case Relation 
Fie ld Part-of- 
Code Speech 
GEN i! 
English 
Surface ~rker 
'on' \[ effect 
~npaeese i Translation Field 
cal-Item Equivalent Code 
...... duty GEN 
Pert-of- Spe~h 
Column-B 
\[Japanese \[ Deep English 
lSurface Marker I Case Relation. Surface ~rker 
/ E}~'~ I GOAL 'to' 
TranslationJ Part-of- 
Equivalent \[ Speech 
These descriptions indicate: The same case marker should be translated 
differently deneodh~ on the governors. Note that the marker '~,\]~' 
usually correspond to English prepositlon'agalst'. 
Fig. 5. Example of descriptions in Column-B 
(3) Column D : Transfer based on Collocations with 
Predicates (Fig. 6) 
Certain combinations of nouns and predicates (verbs, 
adjectives, etc.) in Japanese are translated into 
single words in English : the combinations are 
lexicalized by single English words, combinations of 
nouns and adjectives, for example, are often 
\].exicalized by single English adjectives. 
Ex-5. ~ ~{ ~ .... > lustrous 
(luster) (to exist) 
~g ~ ~ .... > efficient 
(efficiency) (to be high) 
These combinations can appear in the position of an 
embedded clause and cause structural changes between 
two languages(Fig.7). Combinations of verbs and their 
case elements may also correspond to single English 
verbs. 
Ex-6. ~,~ % ~ ..... > focus 
(focus) (to adjust) 
It also happens that Japanese verbs with wide ranges 
of meaning should be translated into certain English 
verbs when collocated with specific nouns. Rules 
which choose appropriate English verbs by referring 
to semantic class:ifications of case elements (nouns) 
are defJ ned as \].exical rules in the verb dictionary 
(See Section 4). However, certain collocations of 
verbs and nouns are so specific that choices of 
appropriate target verbs cannot be expressed by the 
lexica\] rules of verbs of this type. column D in the 
form-oriented dictionary of nouns is used to specify 
such collocations between nouns and verbs. 
Ex-7. Ih~ll~ %1 ~b W ~ ....... > leave a space 
(space) (??) 
The description of this column is not only expanded 
into \]exica\] rules of the nouns but also into the 
property (J-DIC-DER:V) of those nouns. The values of 
this property is a set of Japanese predicates which 
require special treatments when they are collocated 
with the nouns. When node X ill Fig. 2 is a predicate, 
the rules in the main grammar check whether there 
exists a dependent node whose property J-DIC-D\]'\]RIV 
contains the predicate, and i f such a node exists, 
they invokes the lexical rules of the corresponding 
nouns. 
In the dependency structures produced by the 
Japanese analysis grammar, simple modification of 
nouns by adjectives such as 
Ex-8. ~ i~J ...... > heavy rain 
(to be strong, (rain) 
to be big, 
to be heavy, etc.) 
are also represented as embedded clauses (Fig. 8), 
and so column D is used to choose adjectives in 
English. Note that most of the combinations between 
nouns and appropriate adjectives are highly 
conventionalized in each language and so it is hard 
to imagine the conceptual primitives for adjectives 
that could be language independent. 
apanese Translation Field Part-of- 
xical-ltca Equivalent Code Speech 
~-~ efficiency GEB B 
Columa-O 
1 2 3 
SUBJ 
SffB 
OBJ 
J$C: Japanese surface case marker JDC: Japanese deep cam 
ESC: English surface case marker EDC: English deep case 
BOD: Additional specification ('¢dei' shows the case element 
should be deleted in English, i.e. the meaning of the 
case element is lexically included by English predicate.) 
This shows :If '~'(efficiency) is collocated mith ',~#~t~'(high), 
then the combination should be translated into 'efficient', 
else the translation equivalent is 'efficiency'. 
Fig. 8. An Example of Descriptions in Coluaa-D 
~O EOD 
\[\[relative c lause)J 
T SI\]BJ 
LOC SIIBJ 
I (surf°c°) I /(the ga. of the I 
I(tho ~ap of the I ~-~"~)\] 
I embedded clause}\] 
Fig. 7. Structural Changes Caused by Lexical Transfer 
EOD MOD 
i J 
(the predicate J ~the translation equivalee 
of the embedded clause ~f '~,b~' whoa it modifies 
- adjective) \[ 'rain') 
I T 
S~J SUBJ 
I~ rain 
Fig. 8. Lezlcal Transfer of an Adective 
(4) Column C : Transfer based on Collocation with 
Modifiers 
We have several words of minor parts-of-speech in 
Japanese which roughly correspond to determiners, 
quantifiers, etc. Jn English. Almost the same kind of 
information as column D is specified in this column 
for these words. 
4 The Form-Oriented Dictionary and Lexical Transfer 
of Verbs 
When the node X in Fig. 2 is a verb or an adjective, 
the transfer grammar for predicates is invoked. If it 
dose not exist:, the other rule in the grammar invokes 
the lexical rules derived from the form-oriented 
dictionary of the predicate (node X). By examining the 
annotation parts of that node and its dependents, the 
lexJcal rules of a predicate may determine 
(\]) the trans\].ation equivalent in English 
(2) the deep case relationship and surface ease maker 
of those dependents strictly governed by the 
predicate. 
If a Japanese predicate is really ambiguous, a 
separate case frame is provided for each of its 
meanings. The Japanese analysis grammar disambiguates 
the meaning and a separate lexical entry is prepared 
in the bilingual dictionary, i.e. different meanings 
of a predicate are treated as different lexica\], items 
99 
in the transfer phase. However, the real problems in 
translation is not caused by ~mbiguity such as this 
but by vagueness of meaning. When we treat a language 
pair such as Japanese and English, it is not 
exceptional but rather usual that a verb of SL has to 
be translated into different target lexical 
items, even though the native speakers of SL cannot 
clearly realize the meaning difference. 
Ex-8. ~ ~ Jz~ .... > ~ the performance 
(performance) 
9~ ~ _L~ .... > increase the speed 
(speed) 
~K~i~ ~ \]zCf~ .... > raise the water surface 
(water surface) 
The above three usages of the verb '~ ' are 
continuous in the sense that all of them have the 
core meaning in common. If we considered them as 
different meanings, the Japanese verb '~' would 
have plenty of different meanings and be a highly 
ambiguous word. Note that the English verb 'to wear' 
should be translated into more than five differnt 
Japanese verbs depending on what is to be worn. 'To 
wear shoes', 'to wear a watch', 'to wear spectacles', 
etc. should all be translated differently. These 
facts show that it is impossible to establish the set 
of lexical items of the interlingua. In our system, 
then, these 'translationally ambiguous' lexical items 
are treated in the transfer phase. 
The form-oriented dictionary of verbs is shown in 
Fig. 9. Each pair of condition and a transformation 
is expanded into a tree transformation rule of GRADE. 
Japanese 
Predicate 
SDBJ 
Condition-\] 
Condition-~ 
Condition-~ 
transformation-1 
improve ~E SUB 
~DC CPO 
IDC SUBJ 
transformation~2 ~ 
C SUB 
~DC CPO 
JDC SDBJ 
transformatlos-3 
C SUB 
KD\[ CPO 
IDC $UBJ 
rranslatio. 
OBJ £quivalent 
*AP improve-2 
*MO increase-I 
~alse-I 
OBJ1 
OBJ l 
OBJ 
OBJl 
OBJ 
OBJ 
OBJ1 
OBJ 
OBJ 
Fig. 9. Form-oriented Dictionary for Verbs and 
an Example of Descriptions 
Because certain Japanese verbs are translated into 
complex expressions in English, one can specify not 
only the English main verbs but also arbitrary 
phrases governed by the verbs as constants. 
Ex-9 X~ ~q'~ 
..... > to produce trans\[X\] on a trial base 
Note that X in the above example indicates a 
variable an arbitary Japanese noun phrase can fill 
in. T RANS(X) shows the result of transferring the 
noun phrase into English. 
100 
5 Recursive Processing and Multiple Layer of Grammars 
Fig.10 shows that the schematic construction of the 
MTP. The substructure governed by the node X is 
transferred recursively by an appropriate subgrammar, 
depending on the properties of that node. For 
simplicity, only the subgrammars for main clauses and 
noun phrases are shown in detail. The blocks 
surrounded by bold lines in this figure are those 
which are performed by lexical rules described in 
section 3 and 4. The lexical rules are invoked at 
the beginning of the subgrammars, because they are 
the rules for treating idiosyncratic phenomena 
specific to lexical items and are applied before the 
other, moregeneral rules are applied. Constraints on 
some of the dependent nodes such as syntactic forms 
(a prepositional phrase with a specific 
preposition,etc.) are determined by these lexical 
rules, and added to their annotation parts. These 
constraints are utilized at the next recursion step 
where the substructure under each dependent node is 
X 
Subgrammnr for \[$ubgrammar for 
Clauses | Noun Phrases 
Invocation of " 
lexical rules 
derived from column D 
of node Vi 
When there exists a 
node ~i with colloca- 
tiorml information 
with node X 
Invocation of 
Lexieal Rules of 
node X ¢ 
Invocation of recursive 
Process for transferring 
the substructure 
governed by W i 
__,.~Return from thJ 
\[recurslon 
General rules for treating 
the case elements which mr, 
not transferred by lexica\] 
rules 
Rules for dependents of 
other kinds (i.e. adverb) 
Invocation of. lexical 
rules derived from 
~olumn A 
invocation of ieslcal 
"ules derived from 
:olumn C 
invocation of lexical 
• ules derived from 
:oluan B 
Invocation of recursiv( 
process for transfer- 
ins the substructure 
~overned by Z~ 
from the 
rules for 
; modifiers of 
leneral rules for 
:resting quantifiers 
~to. 
Fig. I0. Schematic Constr.ctlon nf s.hgrammar~ nf )4T? 
transferred . Only the dependent nodes which are not 
treated by the \].exieal rules are dealt with by 
general rules. That is, general rules are applied to 
the dependent nodes of a predicate, only when the 
node Wi in Fig. i0 is not treated by 
(i) lexical ru\].es from the column D of the node Wj 
(2) lexical rules of the predicate, the node X 
(3) lexica\] rules from the column A of the node Wi 
(4) lexical rules from the column C of the node Wi 
The general rules are further divided into the 
following two categories : 
(i) Rules in the case when the deep case 
relation between the node Wi and the governor (the 
node X) is uniquely determined by the analysis 
grammar : They determine the surface preposition of 
English by referring to the deep case interpretation, 
the surface case marker of Japanese, and the lexica\] 
item and the semantic markers attached to the node W. 1 
(55 semantic markers are used in our system to 
classify Japanese nouns) . 
(2) Rules in the case when the deep case relation is 
not uniquely determined in the analysis phase : They 
determine the preposition just by referring to the 
surface case marker of Japanese. The preposition 
roughly corresponding t:O the Japanese surface case 
marker is selected. 
The above two categories of rules are just rough 
c\]assificat\[ons and, in reality, more detailed rules 
are prepared for each Japanese case marker. In 
particular, there are several type 2 rules for each 
surface case marker which take into account the set 
of possible case interpretations given by the 
analysis phase. 
Thus, tl~e dependent nodes of a predicate are 
transferred by several kinds of rules with differing 
preferences in order to utilize as much of the 
in \[ormatJon extracted duri ng the ansi ys is phase as 
possible. The same multiple layer construction of 
subgrammars is a\].so adopted for the other grammatical 
units such as subordinate clauses, embedded 
clauses, etc. 
6 Lexica\] Rules and the Form-Oriented Dictionaries ............................. 
The form-oriented dictionaries are provided just for 
preparing dictionary descriptions for a large number 
of ordinary lexica\] J terns. The forms given in the 
preceding sections are used by lexicographers who do 
not have any detail ed knowledge about the transfer 
grammar. At execution time, these descriptions are 
expanded into GRADE lexica\] rules (Fig. ll). 
If one wants to specify complicated transfer rules 
which cannot be expressed in these forms, one can 
provide \]exica\] rules directly i n GRADE, and attach 
them to specific lexica\], items. Such lexica\] rules 
are also invoked at the appropriate time during tha 
transfer phase. The rules in the transfer grammar 
checks whether the \]exical items have \]exJca\] rules 
of certain types, and if they have, the \]exical rules 
are i nvoked whether they are derived from the form- 
oriented dictionaries or prepared directly in the 
GRADE form. On<! can specify arbitrary tree- 
transformations in GRADE so that one can prepare very 
flexible transfer rules specific to \]exica\] items. 
Lexical rules for certain items such as Japanese 
verbs with wide ranges of usages are given directly 
in GRADE. 
~eneral Rule,' 
-invecati( 
-invocati~ 
Dictionar\] Dictionary 
for execution for Maagement 
Noun \[ Noun 
i=o,,'~%el ~.i----T I (co----inm.-^ 
~f eoiu=n h / ((surfece-marker 
~q-.*.a.lio,-- ~) 
-------I / \[exieal rule\] \] LOC) 
,f eolu=n ~ I / ...... ) 
Descr ipt ion 
in for|at paper=~ 
I l \] 
o K-N 
Fig.ll Relationships betveen Format Dictionaries and Dictionaries for Execution 
Though mosl Japanese verbs and nouns are 
respectively translated into English verbs and nouns, 
certain parts-of-speech in Japanese do not have such 
direct equivalents in English, and the word of such 
parts-of-speech need to be translated into various 
kinds of expressions. The transfer rules are highly 
specific to each lexica\] item, and therefore, we do 
not prepare any dictionary formats for these words. 
The tranfer rules are directly prepared in the GRADE 
form. The adverbial postpositional particles in 
Japarlese, for examp\].e, are translated into adverbs, 
prepositions, sty\].es of sentences, etc., depending on 
each \]exica\] item and its surrounding context. 
(John) (to do) 
(John) (to do) 
A, B, Ct~ E~9 D 
h, B, (;~,~. b* 
---> Even John does .... 
---> It is John vh9 does " 
.... > 1) such as A, B and C 
---> A, B, C and so on 
NoLe a\]so that, because the roles of these particles 
are to give additional, meaning to the core meaning 
(i.e. the propositional contents) of the sentences 
and some of them are related to the attitude or the 
intention of the speaker, the inter\] ingua\] 
representation for these patti cles can be very 
comp\]ieated. \]it is a\] so the case for the Japanese 
auxi.\]iary verbs which follow the main predicates and 
express vari ous kinds of modal i ty, aspect, 
politeness, and so on. The correspondence of these 
expressions is highly dependent on language pairs and 
so should be treated in the transfer phase. 
7 The Structural Transfer 
The MTP transfers Japanese structures into 
corresponding English structures recursive\]y by 
traversing the Sapanese analysis trees (dependerlcy 
trees) from the top te tbe bottom. The order of 
processing is })re-determined by the dependency trees 
given by the analysis phase. If the substructures are 
changed unexpectedly durLng the recursion, the upper 
\]eve\] of recursi ve processing cannot respond to the 
change ; if it could, tee rules which cbeck the 
results of the transfer of the substructures and take 
appropriate actions would need ko be provided, making 
the construction of subgrammars unnecessarily 
complicated. 
101 
There are pairs of stereotypibal sentence sty\] es J n 
the two languages which cannot be translated by 
phrase-to-phrase trans\]ation. 
translated irlto an adverb or a preposJ tiona\] phrase 
in EnglJ sh. Rules are prepared in Pre-TP, which 
transform clausal constructions into phrasal 
constructions. 
Ex-11AtZW$~a~12t~<, B_~....8~6 
---> not only h is ~ but also B is "o" 
Because the clues of such stereotypical sentence 
patterns are embedded deeply in the analysis trees 
(see Fig.14) and resultant tree structures of the 
transfer phase become quite different from those of 
the analysis phase, it is difficult for the recursive 
processing in MTP to treat them. 
The two phases, Pre-TP and Post-TP, are provided for 
such global structural changes. In these two phases, 
each rule traverses the whole tree independently in 
order to find where the rule is applicable. 
8 Pre-Transfer Phase 
In this phase, certain structures in Japanese which 
do not have direct Engli sh equivalents are 
transformed into more English-oriented structures. 
For example, the following structural transformation 
(Fig. 12) is taken place, because Japanese 
quantifiers such as ~b ~ (many, much), ~f~b~ (few, 
little) etc. can be used as predicates but English 
quantifiers cannot. 
Ex-12 X2~; ~b ....... > :~<~) Xh~ l~Y-£~xo 
(many) (many) (to exist) 
SUBJ SOBJ 
QOAHT 
Fig.12. Structure Chang~ in Pre-~ 
Furthermore, the following structures in Japanese 
are treated. 
(i) Subordinate clauses which should be expressed by 
adverbs or prepositional phrases in English : 
Ex-13 
(to pay attention to) (machine) (to control) 
............ > to control (the) machine carefully 
A subordinate clause with a predicate of 'TE'-form 
(~,\[~7\[ - to pay attention to) is usually expressed 
in Engllsh as a subordinate clause with a conjunction 
such as 'while', 'when' etc. or a participle clause. 
However, when the predicate of the subordinate clause 
is a verb of a certain type, the clause expresses the 
'manner' case of the main clause and it should be 
Such structural transformations are often required 
in the translation of Japanese into English. Some 
complex expressions which contain subordinate clauses 
or embedded clauses are used in Japanese only for 
expressing deep case relationships. 
(A with a subject marker)(cause) (to become) 
..... > (d irect translat ion) 
Because 'A' becomes the cause ....... 
(deep interpretation) 
'h' fills the deep case 'cause' of 
the main clause --> 'by' 
Because direct translations of these expressions 
result in clumsy English, they are reduced into much 
simpler structures in the transfer phase (Fig. 13). 
main clause main clause 
\[predicate= X\] \[predieate=X I 
S -- I subordinate el CAUSE 
predicate= ~ ;5 .... \] 
SUBJ GOAL 
Fig. 13. Reduction of a Structure in Pre-1? 
(2) Stereotypical expressions of Japanese which have 
corresponding English stereotypical expressions : The 
correspondence of stereotypical expressions in the 
two languages such as given in Ex-ll cannot be 
recovered appropriately by the phrase-to-phrase 
transfer in MTP. Rules are prepared in Pre-TP, which 
discover the existence of such stereotypical 
expressions and insert special nodes in the 
dependency trees to facilitate the recursive 
processing of MTP (Fig. 14). 
main clause 
Ipredicate= X\] 
subordlnate~clause ~OgJ 
predicate= 
(to be) 
negation = T I 
PRED 1 
adverbial- \] 
particle= ~\] 
ldv e~b i a I - 
=ain-elause 
L' predicate= X~ 
OBJ / 
durum' node 
for facilitatiug mr.  
ELleN ELEM 
Fig. 14. Correspondence of sterotyplca| patterns 
102 
(3) Complf~-x Expressions following predacates : 
Though auxi liary verbs in Japanese fo\] \] ow main 
predicates to express various kinds of information 
such as modality, aspect, po\]iteness, etc., some 
complex expressions which contain embedded clauses 
are also used to express the same kind of information 
and should be expressed in English by auxiliary 
verbs, aspect verbs (ex : to begin, to continue, keep 
--ing, etc.), etc. (Fig. 15). 
Ex-15 X~:t ..... =J'~ ~z ~)~ 
(embedded clause) (tendency) (to be) 
...... > (direct tr-anslat ion) 
X is in the state of tendency ~ 
(natural translation) X tends to ~ 
~aln clause 
SllllJ LOg 
embeddedlelause 
\[ predicat----e-~\] 
7 SIIBJ ........ 
~ain clause 
wcdicate~ Y 
~eni.-~odality= ~1~ 
(tendency\] ! 
SIIBJ ....... 
o~°~ 
Fig. 15. Reduction of Structures in Pre-'l? 
Note that what kinds of information can be expressed 
hy simp\].e &uxiliary verbs and so by simple linguistic 
constructions is dependent on each language, and the 
adjustment of the di. fference requires certain 
structural changes. 
(data (advance) (case (automated (to increase 
processing) particle ships) -'past tense) 
-'by') 
.... > (direct translation) 
Due to advances of data processing, 
the number of autonlated ships increased. 
(natura I transl at ion) 
Advances of data processing increase(\] 
the number of automated ships. 
\]0 Conclusions 
We explained ~n this abstract the construction of 
the transfer phase of our Japanese-Eng\] i. sh 
translation system. The implementations of the whole 
system has already been completed and the trans\]atJon 
results (i0,000 sentences) are now being evaluated by 
professional translators and native speakers of 
Eng\] ish. '\]'he evaluation results obtained by now are 
quite sati sfac tory. 
The descri ption in the form-oriented dictionaries 
discussed in this abstract are currently prepared for 
abou 74,000 nouns and 5,000 verbs and adjectives. 
9 Post-Transfer Phase 
The structures which reflect the characteristics of 
Japanese are transformed into more natural structures 
in English at this phase. Some o~ the typical 
transformation are given below. 
(\]) Deletion of causative verbs : Causative 
constructions are often used in Japanese to express 
events which can simply be expressed by using 
transitive verbs in English. 
Ex-16 MJ~ B~ H~ ~5o 
(to rotate) (auxiliary suffix 
for causative contruction) 
--->(direct translation) h makes B rotate. 
(natural translation) A rotates B. 
(2) Transformation from constructions with 
intransitive verbs J nto constructions with transitive 
verbs : It happens quite often that an event is 
naturally expressed by an intransJ tive verb i n 
Japanese but by a transitive verb in English. 
{ 03 

References

(i) Nagao, M. et.a\] . : <Dealing with the 
Incompleteness of LJ ngui stic Knowledge in Language 
Translation', Prec. of COI,ING 84, Stanford 
University, California, i\]984 

(2)Nagao, M. et.al. : <The Japanese Government 
Project for Machine Trans\]ation', Computat Jona3 
Linguistics, Vol. ii, no. 2-3, \].985 
