The Constructive Process Theory and  

  the Multi-Level Translation Method




        NTT Information Network Systems Laboratories                                              
               Satoru IKEHARA             




    List of Abbreviation

  L    :Language                

  E    :English  

  J    :Japanese 

  JL   :Japanese Language            

  pre-E  :pre-editing               

  J-to-E :Japanese to English

  CPT   :Constructive Process Theory

  NL   :natural language 

  NLP   :natural language processing

  CLs   :computational linguistics

  SWD   :semantic word dictionary

  SSD   :semantic structure dictionary 

  pvt-M  :pivot method              

  trs-M  :transfer method            

  MP   :meaning processing            
  MA   :meaning analysis             
  MU   :meaning understanding           

  SE   :subjecyive expression           
  OE   :objective expression           





○ Thank you very much, Mr. Chairman, for your kind words of introduction.
○ I am also thankful to Professor Rigsby and the Organizing Committeefor the
  opportunity to visit this beautiful countryand to get to know my
  Australian and other colleagues better.
○ I am particularly honored to be hereto speak at this Anniversary of your
● Today I would like to speak about CPT and MLT method.

@ I think it would be appropriate to start by some introductory remarks about
  myselfand the research efforts exerted on NLP by our Laboratories.
A Almost 20 years have elapsedsince I joined the Electrical Communication
  Laboratories at NTT. 
・ The first 10 years were spent in research work onForm. Al.Mani. and traffic  theory, with emphasis on QN. 
・ It is therefore 10 yearssince I started research work on NLP.

@ NTT currently has 13 laboratories. 
A Research on CLs have been conducted for long timeat basic research
  laboratories in Musasino city.
B Research on NLP were startedat the Laboratory in Yokosuka 10 years ago. 
・ I was involved in this research effort from the very beginning. 
・ From a staff of three in the beginning,the number of researchers has grown
  to over 30 persons. 
C In the area of NLP,I have undertaken research efforts in
   ・J text to speech,      ・key word extraction,
   ・error detection and correction of J text,  
   ・and statistical approaches for voice recognition.
・ This research effort continues on today. 
D I am now engaged mainly in J-to-E MT.  

@ While research work on CLs and NLP resemble each other,they are not the
  same and it would be adviseable to handle them separately. 
A My current research efforts have been concentrated on NLP and not on CLs.
・ It is not research on how a NL can be transcribed by a theoretical model.
・ It is research on how can J, that is actually in everyday use, can be
  translated into understandable E. 
・ My research efforts are directed toward realization of this method.
B Upon starting research work on MT,a major problem was a considerable gap
  between CLs and NLP. 
C It can be stated thatif we apply the results of CLs to actual every day
  words,there arise many exceptional cases and appropriate processing is
× It may be that if CLs would achieve further progress and development, these
  problems would cease to exist. 
× But can we afford to bide our time and wait for such an event before
  proceeding any further with our MT system ?
× Our Laboratory is an institution engaged in information processing. 
× In conducting MT research, regardless of the method, the final objective is
  to make possible the translation of actual words. 
× To await the development of CLs, would make it difficult to start MT research.
× We would be denied the budget for this purpose. 
× It was no easy task for us to obtain approvals for conducting research on MT.

@ NL is something like a custom or habitthat has spontaneously grown up
  within its own group of the L. 
・ It reflects the very human societyin which it was born. 
A It is no easy task to explain each individual phenomenonwithout conflict by  a unified model. 
B If Ls are a social custom, there should be a method of processing that
  matches them. 
C Researches of NLP require the pursuitof every one of these words.

@ I have decided to begin research workfrom the viewpoint of NLP and not CLs.
A Accordingly,I have sought a new approach amidst the results of
  conventinonal linguistics,promoting a new methodology. 
B The background for my research work isthe CPT of L by Motoki Tokieda,who
  followed up on the workinitiated in the 18th century by Norinaga Motoori.
・ Our MT research efforts have been based on this theoryand has resulted in
  a MLT methodand a test product J-to-E experimental MT system.

@ Today,I would like initially to introduce the outline and experimental
  resultsof our MT system in the half of my talk. 
A In the latter half,I propose by describing our thinking and methodsmaking
  comparisons with the thinking behind CLs.


@ Let us start with the relation between our puporse and the ccurrent methods
 in Japan.
A As you are aware,MT methods have advancedand many commercial systems have
  appeared recently in Japan.
B Our major concern, at this stage, is J-to-E translation.
C JL is very different from European Ls.
・ The quality of J-to-E translation is not goodcompared to French to E or
  E to Russian translations.
・ Current methods can be classified as a word-to-word translation,or literal  translation.
E JL itself has been enhanced by importation of European culture in the M-Era.
・ Therefore, JL has certain expression patternsthat are easily translatable
  into European Ls.
・ These parts can be translated by current methods.
○ However,conventional J expressions are required to be rewritten into easily
  translatable J.
D That is, pre-E is inevitablein order to apply the current MT system to
  practical use.
F The purpose of our research is to realize communication services with
  translation.    ・ We hope to realize direct communications.
・ However,current methods are not satisfactory in realizing such services
  because of the need for pre-E.
G Thus, our aim is to achieve translation without pre-E.
H Let's look at the manner in which pre-E ia conductedto know about the
  limitations of current methods and their causes.


@ How should original sentences be rewritten before translation ?
A Let us look at the examples in this figure.
・ The four essential points of pre-E are shown.
B First, every word should have only one meaning.
・ This example shows the J verb 「kakeru」having, in this case, six different
  meanings,pour, place, build, sit, mop, and play.
・ Such J words need to be rewritten into other wordswhich correspond to a E
  word,but there are cases which present difficulties in rewriting.
C Second, structures of sentences and expressions should be simple.
・ In this example, the adjective 「utsukushii」 meaning beautiful,is placed
  in front of the pronoun (I, me or my).
・ This can resault in two interpretations,"beautiful me" and "beautiful
・ To avoid these ambiguities,modifiers should be placed immediately in front
  of the word to be modified,as in this rewritten example.
D Third, supplementation of elliptical subjects and objects will be required.
E Fourth, idiomatic expressions and metaphores need to be rewritten into other  expressions.
F It can be stated thatthese requirements have derived from limitations of
  literal translations.


@ Let's consider the translation methods.
A Conventional translation methods can be classified into two types, the pvt-M
  and the trs-M.
B Among researchers of MT, there have been arguments as to which method is
○ Among the translation systems developed by private companies, there are many
  which seek to achieve the pvt-M.
・ However, there have been none that can be stated to have truly realized the
・ This is because universal intermediate L that can be commonly applied to many  L cannot be designed.
○ NL has primarily originated by reflecting the perpsectives and thinking of
  the group of people using such L. 
・ It would appear unreasonable to consider a intermediate L that would be
  commonly applicable to every L which differs in thinking and perspective. 
○ When a translation between Ls which are very close each other is considered,  or if a rough ranslation is to suffice, the pvt-M may be satisfactory. 
・ But in either case, I think pvt-M has a basic misunderstanding of Ls in its
@ The trs-M can be stated as being more realistic compared to the pvt-M,
  because it does not assume that intermediate L is universal.
A However, if intermediate L can be thought of as a meaning expression such as  deep structure, the same difficulties as in the case of the pvt-M would arise.
B The meanings of surface structure cannot necessarily be retained by deep


○ Let us consider the manual translation method.
@ In the expression that is to be translated, the state of the objects as
  recognized through the eyes of the speaker is tied with the expressions.
・ And at the sane time, the awareness of the speaker toward the object is also
  tied with the expression.
A To tie the speaker's recognition with the expression, a rule of words,
  i.e. linguistic norm, is used. 
・ This norm differs with every L, such as in E and in J.
○ A human translator experiences the speaker's recognition through the
・ He is required to know both the state of object and speaker's recognition
・ These contents are expressed in the framework of the target Lon behalf of
  the speaker.
@ This figure showswhat is objective in this path and the what is subjective
  in this path.
A Thus,translation is conducted through a re-grasping of the speaker
B A simulation of this process is the MLT method which we proposed.


@ This figure shows the MLT method. 
A The source L is J, and the target L is E.
B The term "Multi-Level" indicates thattranslation is being conducted at
  various levels of abstraction.
@ This system is divided up into 2 major conversion paths. 
A The one is the conversion of the speaker's sense or what is subjective. 
B The other is the path for conversion of the description for the object.
・ And this path splits up into 3 more paths,depending on the abstraction
  degree in conceptualizing objects.
C Thus, the MLT method has currently four translation paths. 
○ The major difference between this method and the conventional methods is
  whether the speaker's recognition and the object are regarded separately
  or not.


○ To realize a MT system, a knowledge of L is essential.
○ NLP can be stated as being a battle with ambiguityfrom the beginning to end.
・ In the translation process,various types of ambiguities arise,but this is
  regarded as being a lack of knowledge that is required. 
@ To overcome such ambiguity, it is necessary to study what knowledge is
  lacking and to have such knowledge established as the rule or as a dictionary.
A It is important to consider the type of ambiguity and relationshipwith
  the knowledge corresponding to it. 
○ In our MT system,we place importance on knowledge for MPfor the purpose
  of solving ambiguity of sentence structureand of the meaning of individual
○ We have collected 2 major types of informationand have compiled them into
  a form of dictionaryas shown in the figure.
@ When the speaker expresses an object, abstraction is conducted and the object  is conceptualized. 
A Details will be mentioned later, but in L expressions, the concept of object
  is expressed separately in terms of a concept of substance and a concept of
○ Linguistic conventions which combine concepts to expressions have therefore
  been compiled into 2 separate dictionaries.
○ The one is knowledge related to semantic use of words. 
・ This has been compiled in a SWDic. 
@ The other is knowledge related to meanings of expression structures. 
A The meanings of expressions are not necessarily represented by the sum of the
  meaning of every word in the expression. 
B In fact, it would appear thet the meanings of linguistic expressions actually  used cannot be explained solely by the meaning of each word used in the
C I believe thatexpression structures need to be consideredas units of
  meanings in NL.
D Based on such thinking, the abstraction of expression structures centered
  around declinable words and compiled as units of meaningshas resulted in
  the SSD.
E This is one of the important points asserted in our systemand I shall be
  dealing with this factor later in this presentation. 
○ I would like to state clearly thatthe knowledge we have discussed here is
  a L knowledgeand not a worldwide knowledge such as general commonn sense
  nor some knowledge of specialists.


○ As discussed in the foregoing,we have compiled a SWD and a SSD.
○ The meanings of words and their translation are listed in ordinary
・ But it does not serve to have the computer knowhow they are to be used.
・ For example,the word "school" is used as a "place"and also as an
○ As a means of desscribing these knowledge,we have compiled the use of the
  meaning of words as a SA system. 
@ It is important to consider precision of knowledge descriptionin relation
  to the degree of ambiguity.
A For example,an algorithm which was valid in a world of 1,000 wordsmay not
  necessarily be valid in a world of 100,000 words. 
・ Experiences indicate thatincrease of the number of words causes rapid
  growth of ambiguities.
B It is a rule of science thatquantity gives rise to changes in quality. 
C We need to keep this rule in mind, especially in NLP.
@ Seeking to establish practical method, we have collected words including
  proper nouns normally used day to day and have compiled a dictionary of
  about 400,000 words for our system.
@ Thus, it is necessary for SA system to work with this environment.
A We began with about 500 categories.
・ But this has resulted in that translation of verbs cannot be precisely
B With the consideration of our aim and environment,we set up 2,800
  categories for general noun SAsand 200 categories for proper noun SAs.
@ Working with these SAs,we have compiled a SWD consisting of 400,000 words
  and a SSD consising of 15,000 sentence forms. 
A The SSD is in a Valentz pattern formand the index words are verbs and


@ This figure shows the nodesfor the top 4 levelsof the SA system for
  general nouns.
・ General nouns are branched off into concrete and abstract,with concrete
  branching off into subjects, places, and concrete objects.
A There is a total of 2,800 category names.
B Here, I have taken one example at the deepest level. 
・ The depth of category amounts to 12 levels at the deepest level.


@ Next we have the SA system for proper nouns.
A Attributes for proper nouns are divided into 4 types,the names of persons,
  of places, of organizations and other. 
・ These are sub-divided further.
× Names of persons will stop at about the 4th level, but names of places go
  further reflecting on the difference in use of names of persons as opposed
  to places in J sentences. 
× Names of places are used in the form of "nesting" such as prefecture country,  ,county, towns and aza (local sub-division) thus accounting for depth of categorization.
@ The number of nodes amounts to 200 and the maximum depth is 9 level.
A An example of the deepest node is shown here.


@ Now, take a look at how these SAs are located in the SWD. 
A This figure shows the contents of one record within the SWD. 
@ The index word is "Tokyo".
A One record consists of 350 Bytes and some 200 to 300 various types of
  information have been input into a record. 
B SAs of words have been registered in the final 15 fields.
@ In the SWD, each word has been given a lower level of attribute. 
A Conversely, with the SSD, higher level attributes have been used.
B This is due to consideration for retaining the relationship between higher
  and lower level attributes.
・ Expression structures should be defined by generalized format as far as


○ At this point,we would like to see the differences of description
  capabilitiesbetween of our SA systems and other similar systems.
○ Case 1 is a typical example of a J-to-E MT system which has recently been
・ The number of semantic categories are between 30 to 50.
○ Case 2 is an example of the dictionary of word conceptbeing planned by the
  Japan Electronic Dictionary Research Institute (EDR)established by MITI
  (Ministry of International Trade and Industry) of Japan.
○ Case 3 is an example of our translation system ALT-J/E.
@ A comparison was made of the three cases.
・ And, the capabilities of describing the translation rules for verbs are
A In the comparison, the case of ALT-J/E has been assumed to be 100%. 
B The dictionary in the case of EDR is just in the planning stage so that the
  values for Case 2 have been obtained from experiments conducted in our system  based on similar conditions.
○ The results of this comparison are as follows.
○ The capabilities of description was 31% for case 1 and 59% for case 2.
@ Those results indicate thatwhen precision levels of SAs are low, essential
  rules cannot be written. 
A Our experiences also indicates that,in J-to-E MT,precision level for some
 3,000 types of SAs are necessaryfor differentiation of translation for verbs.
B However, this is not sufficient for translation of nouns.
・ I think that some other different system from the SA is required for
  differentiation of translation in the case of nouns.


○ Let me showwhat kind of translation has become possible by our system.
@ The first example is differentiation in the translation of the J verb 「kakeru」.
・ This is the same example as shown in the beginning of Pre-E.
A The verb in the J sentences are all the same 「kakeru」.
・ But, the translation by ALT-J/E showspoured, made, caused and other
  different words.
B J verbs in generalneed to be translated into many different E words. 
C In the case of 「kakeru」,there are about 15 different ways of translation
  for general useand to include idiomatic usage,there will be a need to
  consider some 80 types of translations. 
○ The verb with the largest number of variations would be 「suru」with over 300
  different ways of use.
・ This verb resembles the E verb "do".
@ The second example shows differentiation in the translation of the noun 「mure」.
A The same word 「mure」 is used 8 times in the J textbut the translations are
  different for each case.
B In this case,the E word varies depending on what is referred to.
× According to a native E speaker who was interviewed, the word "bevy" here is  used only in the case of beautiful women. 
× It was also pointed out that "mod" sounds strange. 
× It would appear that we need to change our rules somewhat. 
× Here, it would suffice if our audience can appreciate that differentiation
  needed in the translation of nouns has also progressed to certain level.


○ The next is an example of an automatic rewriting function of J sentences.
@ Here is a proper J sentence.
A The literal translation of this sentence is=(英語を読む)
・ I think this E may be understood,but it does not sound like proper E. 
A The reason for this can be seen clearlyas having excessive number of verbs.
○ J is a L of "circumstantial logic",and it necessarily uses many verbs. 
・ In contrast, E is a L of "substantial logic"and is said to prefer
  structural expressions.
@ Thus, to reduce the verbs,a partial rewriting of the J text in the figure
  is undertaken.
A This rewriting is performed by the translation system automatically. 
B After automatic partial rewriting,we get the translation as =(英語を読む)
・ I think the quality of E has improved.
×@ It goes without saying that it is our goal to think through J texts that
  are difficult to translate and to translate these into E that is readily
×A Yet it is another alternative to change Japanese text that is difficult
   into one that is easily translatable automatically. 
×B This method is particularly convenient when a translation function that is
   already completed can be applied without having to establish the function
○ The next example is supplementation of subjects and objects.
@ The J convention is to refrain from mentioningwhat is already known to the
A Lengthy, redundant expressions are not popular. 
B Particularly, the subject and object are omitted unless absolutely necessary.
・ Becausethese can generally be judged by the partnerby joshi and auxiliary
  verb expressions.
@ In contrast,in E,both subject and object are generally necessary. 
A There are caseswhen the subject is missing and the object is turned into
  the subjectand rewriting into the passive voice. 
B But this is not always appropriate. 
@ Here are two sentences which are linked to one another. (日本語を読む)
A The first sentence has the subject and object,but the second sentence has
  two subjects omitted.
B Therefore,ALT-J/E has supplemented the first subject by the object of the
  first sentence.
C And the latter subject is supplied by the subject of the first sentence.
○ I have shown some of the new functions that have been realized by ALT-J/E. 
○ I believe that,with the realization of these new functions,the
  possibility of MT without pre-Eis now real possibility.

@ The foregoing is the initial portion of my presentation.
・ I have introduced the MLT method and our MT system ALT-J/E.
A In the latter half of my presentation,I would like to mention details of
  our conceptual background. 
B If there should be any questions on the discussions up to this point, I shall  be happy to answer them.

@ I shall begin the latter portion of my presentation.
A I have already mentioned thatour research efforts are being conducted from
  the viewpoint of NLP, not CLs.
B Let me discuss the thinking behind our MT system.
@ The background to our research lies in the CPT of L. 
A This theory was advocated some 50 years agoby a J linguist, Motoki Tokieda.
B Tokieda took after the J grammarwhich was established some 200 years ago by  Norinaga Motoori,and introduced the CPT from a standpoint ofcriticizing
  the philology of Ferdinand de Saussure.
@ First, I wish to present the differencesbetween the concepts of CLs and of
A I shall follow by discussinghow the CPT is related to our MLT method.


@ Let's consider the background of the CLs, first.
A In considering logics,there has been two types of logics since the olden
@ The one is dialectics.
・ Dialectics was advanced by Hegel.
A This type of logics asserts thatactual existence should be thought of as a
  meaning theory.
・ Hence, it deals with contents.
@ The other type is formal logics.
・ This type of logics has appeared in the era of ancient Greece.
A This logics insisted on purity and handling of an ideal world.
・ And it cut itself offfrom the realistic world.
○ Symbolic logics and computational logics are derived from the latter, formal
@ There appears an effort to apply CLs to NL. 
A But NL is a Lthat deals with the realistic world.
B This would seem to be the cause of various problems.
・ For example,Frege's principle, which is compositional semantics and
  constitutes a major assumption in CLs,is not valid in a NL.


@ Let us look at the differences between the J and Ind-European Ls.
A The Ind-European Ls have sentence patterns such as 5 patternswhich are
  relatively independent from contents.
・ These Ls can be classified as a suitcase type L.
・ Structualism was developedfrom the viewpoint of importance of forms and
  structures of expressions.
・ Chomsky took notice of the importance of contents to overcome the limitation  of structualism.
B In contrast,JL is relatively free from formsand does not have a rigid
  sentence structure.
・ J can be classified as a 「furoshiki」(wrapping cloth) type L.
・ Forms are dependent on contents.
・ In other words, the shape of contents appears in a form of expression.
C Thus, contents are important in J processing.
D In J, there are 20 different types of grammars.
・ And four of them are well known. 
○ Here, I would like to take up twoout of the four.
・ One is Hashimoto grammar.
・ This grammar is strongly influenced by European philology.
・ And this grammar was adopted for use in schoolby the Ministry of Education
  of Japan. 
・ Another grammar is Tokieda grammarwhich was derived from Norinaga Motoori.
E As nature is a complexed body of processesthat develops with conflicts as
  the motivating force,so also is L.
F Tokieda established the CPT of Lbased on this idea.
----------------------------------------------------------------- Fig. 16


@ This figure shows the differencesbetween the CPT and Chomsky's concept.
A CPT asserts thata L should be considered as a complex body of processes
  comprised of objects, speaker recognition and expressions.
B Objects reflect recognition. 
・ This process is explained by the reflection theory.
C #Recgnts are combined into expressions using norms,namely the rule of Ls.
・ #Ling-norms are national ruleswhich have been fostered in each community.
・ These norms are referred to as a grammarin the broad meaning of the word.
D In contrast,Chomsky interpreted L in the form of a dual structure,a
  surface structure and a deep structure.
E The existence of deep structure has been assumedas the meanings of surface  structure. 
・ This is certainly a strange theorywhere because meanings are assumed for
  the purpose of explaining meanings.
・ It would further appear that there would be difficulty in explaining the
  existence of deep structure. 
・ More recently,he appears to be attempting explanation based on mystic
・ He saysL cannot be explained without assmuming thathumans are born with a
  basic linguistic ability.
F Well, results are achieved from causesand these results, in turn, become
  the causes for the next series of results. 
・ Nature is a composition of such processesand it is the conflicts and
  discrepancies which activate these processes.
・Conflict is energy. === ・I believe this is the thinking followed by science.
・Language is a spiritual by-product of humans. 
・There is room for various theories to arisebased on how the human spirit is  to be considered.
----------------------------------------------------------------- Fig. 17


○ Let us now seewhat happenswhen we regard L as a causal sequencebetween
  object, recognition and expression.
○ The world of objects consists of a speaker and other objects.
・ Objects are composed from substances, attributes and relations.
B The speaker recognizes the object worldand at the same time, recognizes
  things about himself. 
・ In recognition of objects,conceptualization takes place. 
○ There are two occasions regarding recognition of self.
・ One is the occasion wherespeaker represents himself directly in the
 expression without conceptualizing himself.
・ On other ocassions,he conceptualizes himself and represent it as an object.
○ When he conceptualizes himself,the phenomena of self disunion take place.
・ A separate imaginary self other than the actual self appears.
・ And the self conceputualizes the actual self.
○ Recognition related to subjects and objects is representedby two types of
  forms in linguistic expression.
・ One is a SE and the other is an OE.
C SEs represent speaker emotions and intentions.
・ These expressions are expressed in the JLby post positionals and adverbs.
D OEs represent conceptualized objects. 
・ And these expressions are generally expressed by nouns and verbs.
E This relation is somewhat different in E.
・ Inflections usually express SEs in E.
------------------------------------------------------------------ Fig.18


@ Let us take a look at this example.   == 日英単語対を読む==
A This sentence means"He will also want to go to America".
B "He, America, go" are OEs.
C "also, to, want, will" are SEs.
・ A similar view is witnessed in the grammar of Port Royal in France300
  years ago.
D The difference is an important factor in the translation method.
・ I plan to mention this later in relation to the MLT method.


● Here, let us proceed to the problem of meanings.
@ Recently, the importance of semantic processing in NLP isbeing strongly
・ Much efforts have been devoted to semantic or meaning processing,but it is
  felt,in many cases, the definition of meaning is ambiguous.
○ I would like to point out here what we regard as meaning.
A Let us consider the structure of Ls. 
・ If we assume that meaning is a substance,it is one of either "object",
  "recognition" or "expression"and the fourth element of "interpretation".
・ If we say, at this point, thatmeaning is born out of forms,we would
  arrive at a "formal semantic theory".
・ But this would be ideological.
B Next, if we say that forms are born out of contents,this would result in a  "object semantic theory" or "recognition semantic theory".
C If we assume that objects and recognitions are meanings,how should we
  explain the sentence that has been erroneously written. 
・ This would result in a sentence that is incorrectin which something that is  opposite is written,yet stating that the meaning is correct.
D Further,the object and recognition can never remain the same indefinitely
  and will undergo changes.
・ Then, the meaning of the sentence will change independently from expressions.
E Motoki Tokieda chose eclecticism and took meanings to be listener's reactions.
・ Tsutomu Miura took after the Tokieda grammar,but improved the theory and
  advocated the "relation meaning theory".
F He proposed thatstructural processes from object to recognition are
  combined to make an expression.
・ He explained the meanings of linguistic expression as the relationship
  between object, recogntion and expression.
G This kind of relationship is concrete and specific. 
・ As long as the expression exists,so will the meanings.
・ When expression is cancelled out,so will all relationships,and the
  meanings are also lost.
H The concept of regarding relationships as meaningresembles recent situation  semantics,but actually, the two are entirely different.
I In situation semantics,the meanings of expressionsand the meanings re-
lated to the location in which the expression is placedare completely mixed up.
・ The Miura grammar features a clear distinctionbetween linguistic expression  and expression of locations.
----------------------------------------------------------------- Fig. 20


○ How do we go about MPfrom the viewpoint of "relation meaning theory".
○ Meaning is the relationship between object, recognition and expression. 
○ SE involves the emotions and intentions of the speaker,whereas OE expresses  the status of the objectas viewed from the eyes of the speaker.
・ Thus, MU would involve re-tracing such relationshipand to relive and
  experience the status of object and recognition.
C Here, let us think of MP in two steps.
D The first step would be the processwhich designates the rules or
  conventions used in linguistic expression.
E Conventions regarding Ls are complex and liable to be construed in many ways.
・ The listener must identify the convention used by the speaker. 
・ I would wish to define this act of identifying the convention as "MA".
F The second step would be the process of identifying the recognition of the
  speakerand the status of the object that is tied in with the expression.
・ Here, we would like to refer to this action as "MU".
G Therefore, MP consists of two processes,"MA" and "MU".
H The knowledge that is required for MA would be linguistic knowledge,that is,  conventions or norms regarding Ls. 
・ In contrast,MU would require knowing the status of objectsand this would
  require general knowledge, that is, worldwide knowledge and knowledge in
  specialized fields.
I Let us go over the next example. ------------------------- Fig. 21      ----------------------------------------------------------------------------


@ This diagram is an example of MA.   =日本語と英語を読む=
○ The meaning of the sentence is ------------.
○ Let us think about the convention involved in these words. 
○ The meaning of the word "takai" is expensive, high, noble, loud among others  but here, it is used with the meaning "expensive". 
○ "Abura" has various conventions as shown in the figure,but here the
  convention expressing the meaning of oil is used.
○ Thus,MA is identification of the conventionwhich the speaker actually
  used among numerous conventionsthat exist in the L.
・ MA cannot be achievedby merely staring at the words one by one.
@ Let us look at the lower sentence. ==日本語を読む===
A Look at this portion of the sentence. 背の高い meaning the "back is high".
・ In E, one word "tall" is used to convey this meaning. 
・ But looking at back and high separatelywill not bring the concept of tall.
B The same can be said of the other expression.
・ Sell and oil jointly means idle away one's time in this case.
C Thus,conventions regarding words can never be decisiveif they are thought
  out word by word.
A I said thatthe meanings of expressions are the relationship between objects,  recognition and expressions.
B Structrures of objects reflect themselves into speaker recognition. 
・ These structures are also combined to expressions.
@ This means thatthe structure of an expressinon is a part of the meaning. 
・ Structures cannot be separated from meanings because structures also
  represent meanings.
A Thus, in MA also,there is the need to think the relationship between
  structure and meanings. 
・ More specifically,it is important to grasp the structure of expressions as
  units of meaning.
------------------------------------------------------------------ Fig.22


○ Next, let us consider about MU.
@ As discussed in the foregoing,MU involves the identification of the
  speaker's recognitionand the status of object as tied in with the
A To know the speaker's recognition and the status of object,the listener
  must be equipped with a certain world in his mind.
・ This world must have certain elements in common with the worldwhich the
  speaker is depicting. 
・ To restructure a worldcorresponding to the expressions of the speaker,he
  will be required to link up the elements of the speaker's expressionsand
  the elements of his own world.
B In other words,MU can be considered as linking the elements of the
  linguistic expressionsand within the world model of the listener. 
・ This action of linkage will structure a new portion in the listener's world.
C In contrast to liguistic knowledge for MA,MU will require worldwide
D Compared to linguistic knowledge,worldwide knowledge is massiveand
  considerable amount of difficulties will be involved in research. 
・ We are therefore conducting our reseach effort based on the following
----------------------------------------------------------------- Fig. 23


@ We shall discuss MP in MT by dividing it into MA and MU.
A The relationship between our MT research and MP is as follows.
○ In MT, the contents of source text to be translated are diversifiedand it
  would be difficult indeed to prepare a worldwide knowledge.
D MT can be acceptableeven if the computer cannot entirely understand the
  contents of the textas long as the translation results can be finally
  understood by humans.
E Replacing the linguistic conventions used in the JLby E conventionsand
  leaving it up to the judgment of the average person. 
・ This is the basic stance assumed by our research efforts in MT. 
○ First,we want to realize a translation based on MA.
○ Next,we will extract the expressions and conceptswhich could not be
  translated by MAand attempt a MU with a limited world model.
○ In contrast,with areas such as telephone number information and database
  inquiries,the target world can be contracted into a comparatively small
・ We are structuring world models and conducting research in MU for such fields.
----------------------------------------------------------------- Fig. 24


@ The method of translation based on the foregoing MAis the MLT method.
A I have previously mentioned the need to observe differencesbetween SE and
B And, I have also pointed out the necessity of considerationabout the
  meaning of structures. 
C The abovementioned translation method has been structured based on these
  two factors.
D The first point is considered as follows.
・ J and E are very different in presenting SEs.
・ Therefore,SEs are segregated from OEsand converted into E.
E The second point is resolved by abstraction of expression structures.
・ Three levels of abstraction have been proposed.
・ The first is related to a level of idiomatic expressions.
・ The second concerns specific structures such as loosely coupled words.
・ The last concerns most loosely coupled structure that can be represented by
  general rules.
F From the foregoing,MLT method consists of two major structures. 
○ From the viewpoint of linguistic knowledge,linguistic conventions are
  divided into thosewhich are related to SEs and those related to OEs.
G Of the two,the knowledge related to SEs are smaller in scale compared to
  OEsand have been solved in terms of rules or programming. 
・ But the OEs being massive,we have decided to compile them in the form of a
H We shall next explain the method of summarizing linguistic knowledgerelated  to objectve expressions.
---------------------------------------------------------------- Fig. 25


@ I have already explained thatthe target world of linguistic expression is
  structured by the objectconsisting of substances, relations and attributes  and by the subject which is the speaker himself. 
・ Here,the objectified speaker himself is identical with substances. 
・ Thus,knowledge for OE can be considered as consisting of three types,
  substances, relations and attributes.
A In terms of linguistic expression,substances and relations can be expressed  by nouns. 
・ Thus,the knowledge concerning use of nouns has been summarized in a SWD.
B Regarding attributes,there are a dynamic type and a static typewhich are
  represented by verbs and adjectives, respectively. 
・ Thus, these have been summarized in a SSD.
C As mentioned in the earlier portion of my presentation,linguistic knowledge  has been summarized based on these ideas.
× As an item similar to the SWD, there is thesaurus. 
× In E, the thesaurus by Roget is famous and there are several examples in
× These have perceived the similarity between the meanings of individual words
  and have made classifications accordingly. 
× Our word semantic dictionary features the viewpoint on which the word is
  based and used and has thus added a semantic role.
----------------------------------------------------------------- Fig. 26


@ I have presented an outline of the J to E MT system, ALT-J/Eand the related  conceptual background.
A The current state of NLP research at our research laboratorycan be summed
  up as follows.
B First, morphological analysiswhich constitutes a considerable stumbling
  block in the JL.
・ I think the complexity is not less than that of syntax analysis or meaning
C Technology involved has been almost completed. 
・ A remarkably high level of precision and accuracy has been achieved. 
・ Syntax analysis and MA are being undertaken in the course of MT research.
・ High levels have been achieved,but I do not believe,it is satisfactory
  yet to be applied to newspaper article translation.
C Research on MU has been initiated in question answering.
・ This will require more time and effort.
---------------------------------------------------------------- Fig. 27


@ The main issues confronted by MT researchand future research targets are as  presented in the figure.
A Current subjects are ....==No.1 を読む==
・ Our major research efforts are being concentrated in these areas.
B Our future study efforts will be concentrated on ....==No.2を読む==
・ Preparations for these studies are now under way.

○ Today,I have mentioned the thought and method of our MT system.
○ I am hoping that these ideas will become one of the bases of non-literal
・ The problem of non-literal translation has begun to attract attentionas
  witnessed by the fact thatit was taken up at the IJCAI Workshop in Sydney
  last August.
○ If sharing our experiences in dealing with this systemwould be of interest
  to you,it would be our pleasure to do so.
○ This concludes my presentation,and once again,my heartfelt appreciation
  for this opportunity. 
・ I thank you.
inscription → description  ??
consider, concieve, perceiveの違い
● Here, let us proceed to the problem of meanings.
・ I can't discuss details of meaning theory here.
・ However, we have adopted Miura's theory which assert meanings are
  relationship between object, recognition and expression.
・ This theory is called "relation meaning theory".
H The concept of regarding relationships as meaningresembles recent
  situation semantics,but actually, the two are entirely different.
I In situation semantics,the meanings of expressionsand the meanings
  related to the location in which the expression is placedare completely
  mixed up.
・ The Miura grammar features a clear distinctionbetween linguistic
  expression and expression of locations.
I have not discussed the details of structural meaning of expression.
However, I must point out here the necessity of consideration about the
meanings of structure as the second point of our translation method.