<?xml version="1.0" standalone="yes"?>
<Paper uid="C86-1147">
  <Title>Translation by Understanding: A Machine Translation Sy,i;tem LUTE Hirosato NOMURA, Shozo NAITO, Yasuhiro KATAGIRI, and Aldra SHIMAZU</Title>
  <Section position="4" start_page="6271" end_page="6271" type="metho">
    <SectionTitle>
3. Extended Case Structure Model
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
3.1 General Framework
</SectionTitle>
      <Paragraph position="0"> The Extended Case Structure Model (ECS) is a linguistic model for representing the meaning structures of the text. Thus the ECS presents a representation scheme for the episodic memory. Figure 1 shows its fundamental construction. The traditional case structure (Fillmorean type) is a structure for a unit sentence which consists mainly of relations between nouns and a verb. This is not sufficient to represent structures of real sentences which sometimes have complex noun phrases, compound sentences, etc. Also, the ECS has to have facilities for representing other structures involving relations between a noun and a noun, a verb and a verb, etc. The ECS has been designed to integrate those structures into one linguistic model. Its nature is hierarchical as to the compoundness of constituents, iterative as to conjunction, and recursive as to embedding. Using these formalisms, the syntactic and semantic structures of sentences can be represented uniformly and correctly.</Paragraph>
    </Section>
    <Section position="2" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
3.2 Semantic Structure in ECS
</SectionTitle>
      <Paragraph position="0"> There are two types of semantic structurcs, composite and primitive structures. A cmnposite structure is made by integrating semantic structures using semantic relations. A primitive structure, by definition, cannot be divided into further substructures. In general, a single word corresponds to a primitive structure, and a phrase corresponds to a composite structure. Since syntactic information can also contribute to define meaning structures, each semantic structure simultaneously incorporates not only meaning information but also syntactic information.</Paragraph>
      <Paragraph position="1"> We do not assume a language-independent universal semantic representation. Thus, it is necessary to define a proper ECS for each language: Japanese ECS (J-ECS) \[6\] for Japanese language and English ECS (E-ECS) \[7\] for English language. In the translation process from Japanese into English, the analysis procedure generates a J-ECS for a Japanese sentence, and the transfer procedure generates an E-ECS corresponding to the J-ECS.</Paragraph>
    </Section>
    <Section position="3" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
3.3 Semantic Relation in ECS
</SectionTitle>
      <Paragraph position="0"> Senmntic relation connects semantic structures and builds a larger semantic structure, ranging from a word structure to a sentence structure. Figure 2 shows types of semantic relations, and each of them can be explained briefly as fellows: 1) Noun relation: Relationship between nouns; Examples are whole-part, upper-lower, possession, material, etc.</Paragraph>
      <Paragraph position="1"> 2) Case relation: Relationship between a case element and a predicate; Examples are object, agent, instrument, place, etc.</Paragraph>
      <Paragraph position="2">  3) Embedded relation: Relationship between an embedded sentence and a noun phrase, which can be categorized into three types; a) case re'lation between a modified noun phrase and the predicate iu a modifier embedded sentence, b) noun relation between a modified noun phrase and a noun phrase in a modifier embedded sentence, and c) an appositive or subsidiary relation between a modified noun phrase and a modifier embedded sentence.</Paragraph>
      <Paragraph position="3"> 4) Conjunctive relation: Relationship between sentences; Examples are cause-result, time-advance, assumption, etc.</Paragraph>
    </Section>
    <Section position="4" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
3.4 Concept in ECS
</SectionTitle>
      <Paragraph position="0"> Concepts are associated with structures mentioned above. Among them, concepts associated with word structures represent word meanings which appear when the words are used in a sentence. A word meaning is represented by principal concepts, supplenmntary concepts, and their semantic dependencies. Principal and supplementary concepts are dcfined by using semantic categories, and prepared for nouns, adverbs, verbs, adjective-verbs and modalities as shown in Figure 3. Semantic dependencies are defined by using semantic relation fi'ames and semantic structure frames. Semantic categories, semantic relation fi'amcs and semantic structure frames have the following characteristics: 1) There are two types of concepts: prototype and instance. Prototypes play a part of selectional constraint to define semantic dependency structures. Instances show an assimilated structure which satisfies the selectienal constraints.</Paragraph>
      <Paragraph position="1"> 2) They shows semantic commonness and analogy between two structures. This allows the system to share information and to provide facilities for paraphrase. 3) Semantic categories make tip a hierarchical structure. This provides the system with inheritance ability and information sharing.</Paragraph>
      <Paragraph position="2">  4. Dictionaries, Knowledge and Their Representation</Paragraph>
    </Section>
    <Section position="5" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
4.1 Dictionary
</SectionTitle>
      <Paragraph position="0"> There are two typos of dictionaries in LUTE. Mono-liugual dictionaries are used in analysis and generation, while bMingual dictionaries are used in transfer. Mono-lingual dictionaries have the following information about words and concepts: 1) tIow the word is expressed, 2) how the word is used in the syntax of a sentence, and 3) what concept the word corresponds to. Bi-lingual dictionaries has information on the correspondence of concepts in two different languages, and will be explained in section 6. (Note that concepts are defined here by associating structures which are generally language dependent.) Figure 4 shows the contents of a word dictionary.</Paragraph>
      <Paragraph position="1"> A word meaning can be regarded as an entry to the conceptual knowledge description. The LUTE dictionaries contain the following semantic information: 1) Semantic category (for word meanings): Principal concepts associated with the word meaning. Those for nouns and adverbs are used as selectional constraints in semantic relation analysis.</Paragraph>
      <Paragraph position="2"> Those for predicate s are used to analyse modality.</Paragraph>
      <Paragraph position="3"> 2) Case fi'ame (for predicate word meanings): Constraints and case relations which are applied to construct unit sentence semantic structures. There are three types of ease frames: intrinsic for each predicate word nmaning, common for several predicate word meanings, optional for outer ease relations.</Paragraph>
      <Paragraph position="4">  3) Noun relation frame (for noun word meanings): Constraints and semantic relationships which ace applied to construct semantic structures made up of two nouns. Case frames are also used as a ldnd of object relation frames for predicate-type nouns.</Paragraph>
      <Paragraph position="5"> 4) Event relation frame (for predicate word meanings): Constraints and semantic relationships to be applied to construct complex sentence semantic structures. An example is the relation between the verb in a main clause and the verb in a subordinate clause.</Paragraph>
      <Paragraph position="6"> 5) Heuristics (for semantic categories and relation fi'ames): This is  used for resolving ambiguity of semantic categories, semantic relations, and semantic structures by linguistic information such N~oun-ielalot~ .... tri~ci;on ca~se~rel--ati~on ;gent:a-ctio~n~objec~t--actio~i-nst--ru--n,e,;t~;ctio~n- ' -Catego-ries for-~ouns-a~ld adverbs:: =,-~a-ture~m-a-teriT;i lnstri,,,~;~,i i .... time-action location-action destination-action source-aetim~ co-object-action manner- I society organization \[ cultllre i buman l action l state \[ number l degree l enmtion l action freque cy-action object-state action-location action-time action-result action- time l location |a bstract l concrete animate J plant I others degree I state'object property-object possessor-object number-object material-object Categories for verbs:: = voice active statlve movemental I transitional\] Iota, on-object object.property object-element object-number object-location species- emotional I thinking perceptual existential judgenlental non-willing object l re ative-location Iocat on-specificatio ~ time-specification human-relation noun- v oi c e : : = passive l affected-passive possible l sponraneous causa tive \] pet fective I cative:: =momentallcontinual suffix prefix-noun \[ parallel l others Case relation:: = OBJECT-TYPE METHOD-TYPE DfRECTION-TYPEJ TIME-SPACE-TYPE 1 stative:: = ~ teiru\[ -teiru Categories for adlectives and adjective-verbs:: = SUPPLEMENT-TYPE I MODIFICATION-TYPE  0 gJ E CT-TY PE :: = object I co-object \[ statem ent-object J compared-object I seconds ry-obje ct I theme J agent \[ experiencer METHOD-TYPE:: = method I instrument I material\[ element I ca use DIRECTION-TYPE:: = source I destination I purpose I result \] giver I recipient TIME-SPACE-TYPE:: = location J time SUPPLEMENT-TYPE::=Ocasion content role contrast region MODIFICATION-TYPE:: = manner \[ frequency degree tbing rate I number emphasis I true tf  Embedded relation:: = case relation\] relation that modified noun phrase modify case instance in tJm enlbedded sentencel apposition.Event-result Con unctive relation:: = condition right-affirmative cause lpurposelright assumption\[ contrary-assumption contrary-affirmativeljuxtaposition introducr on pallare t merelation before simultaneous after continuation limitecl-continuationlduring I examplilTcation selection interrogative-contentslcitationlexplanationlspecificlnlinimal. limit proportion degree I limit stative I charactedstk \] relational I emotional Categories for modalities:: = as pect:: = beghlning just-before-beginning Ijust-after.beginning I continuous I repetitive I perfective \]just-before.perfective Ijust-after-perfective I perfecrivestate I others tense:: =past present future modal:: = negation possibility necessarity obligation I necessity I inevitability I favorability \[ sufficiency I guess I affirmative \] confidential-guess I uncertahla ffirnlative estimation guess uncertain-guess l hearsay l intention willingness I plan hope try causative secood-pelson command interrogative request I pernlission invitation third-person l causa tive \] request I passive I spon tanity \[ bene factive \[polite I respect I o ,hers manner:: =limited degree \[ extr eme-e xample l stress l exan\]plification \] parallel ladditionlselection uncertainty distinction others Fig. 2 Semantic Relations Fig. 3 Semantic Categories as preference over several semantic relations, semantic relation fillers, and remaining semantic relation fi'ames not yet filled.</Paragraph>
    </Section>
    <Section position="6" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
4.2 Knowledge
</SectionTitle>
      <Paragraph position="0"> Both comnmn.-sense knowledge and expertdmowledge are constructed using basic elements such as concepts, ,'elations and structures as well as linguistic structures. Thus the non-lingulstlc knowledge manipulated in LUTI,; is not represented in a simple data-base fl'amework but rather incorporated into the memory structure.</Paragraph>
      <Paragraph position="1"> Although re.troy language processing systems use the term &amp;quot;knowledge&amp;quot; rather vaguely, LU\[\['Itl gives a concrete form to knowledge in the sense of franmmetworks corresponding to word meanings. The current version of I,UTE defines the following types of knowledge in terms of semantic relations: 1) Concept Relation: Relations such as hyponymy, synonymy, antonymy, whole-part, and possession. One example is &amp;quot;wholepart&amp;quot; rehttion between &amp;quot;densha ( ;~ ii'-') (train)&amp;quot; and &amp;quot;made (~) (window)&amp;quot;. (A window can be a part era train.) 2) Event State Relation: Relations between two events or between an event and a state. One example is &amp;quot;subsidiary situation&amp;quot; relation that &amp;quot;nioi (~ ~ ) (smell)&amp;quot; results from &amp;quot;yaku ('l')'~ &lt; ) (grill)&amp;quot;. 3) Mete knowledge: This is used for reasoning, such as in traversing the concept networks, and checMng semantic consistency according to concept networks.</Paragraph>
    </Section>
    <Section position="7" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
4.3 Frame-Network
</SectionTitle>
      <Paragraph position="0"> All information manipulated in LUTE is represented in a uniform frameworlt, called a Frame-Network. F, ach type of {lictiouary infermarion such as semantic category, case frame, noun relation frame,  and event relation fi'ame is represented by frames with correspondlng frame names. These fi'amcs consist of subframes representing semantic relation information. Slots of a frame which represents semantic relation infermation contain information such as semantic category and cast particles stipulating the semantic relation. An idiomatic expression between a noun and a verb is represented by a co-relation fi'ame. This is the convention for sharing case slots in case Dames to yield an effective processing for case analysis and selection of word meaning. These frames are also provided for each noun.</Paragraph>
      <Paragraph position="1"> IIcuristies are defined as methods (daemons) in fl'ames. The concept relation of knowledge can be represented by inheritance and semantic relation slots of noun relation fl'ames. Event state relation is represented by event-object relation fl'ames, and expressed in a word meaning of the eorresponding noun. Using this relation fFame, semantic relations in a phrase, &amp;quot;Sakana we yaku nioi (,(rE {&amp;quot; ;t}'~ { ~ ~,) (Smell of fish grilling)&amp;quot; can be analysed. Me,a-knowledge is represented as a procedure for unifying frames to select a word meaning, inheritance mechanism, and methods in frames as well as heuristics.</Paragraph>
    </Section>
  </Section>
  <Section position="5" start_page="6271" end_page="6271" type="metho">
    <SectionTitle>
5. Extended Case Analysis
</SectionTitle>
    <Paragraph position="0"> l,',xtended Case Analysis (F, CA) builds the meaning structure of a sentence which is expressed by tim fi'amework based on ECS. The ECA integrates both syntactic and semantic analysis using Structure Patterns. Analysis proceeds in ,~t manner ill which, top down structure prediction and bottom-up structure integration are intertwined.</Paragraph>
    <Paragraph position="1"> Viewing the analysis from the standpoint of the activation of lcnowledge, an expression activates a word, a word activates a word meaning, a word meaning activates concepts, and coneel)ts activate concept relations. We will describe the prccedure for analyzing Japanese sentences in the following sections.</Paragraph>
    <Paragraph position="2"> 5.l Flow and Control in ECA It is assumed here that the morphological analysis process has already segmented a sentence into a sequence of words. The ECA procedure can be explained roughly as follows. First, the ECA predicts a sentence structure in a top-down manner using Structure Patterns. Second, it analyzes semantic structures for the predicted sentence structure using Semantic Structure Frames, which describe constraints for integrating the substructures. Finally, those substructures are integrated into a bigger structure. These procedures are performed recursively for each level of constituent construction until an integrated meaning structure is obtained for the entire sentence. When information concerning semantic structure frames or knowledge is missing, the ECA does not attempt to nmke a unique integrated meaning structure. Rather it utilizes a variety of heuristics, thus making it possible to order multiple possible meaning structures in terms of likelihood or plausibility based on a score given to each meaning strueture. A rough outline of this analysis is presented in Figure 5.</Paragraph>
    <Paragraph position="3">  tIistorieal information, including both the success and failure of the processing, is stored so that the ECA can avoid analyzing the same sequence of substructures in the backtracking process.</Paragraph>
    <Section position="1" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
5.2 Structure Pattern
</SectionTitle>
      <Paragraph position="0"> A structure pattern is a package of knowledge for predleting syntactic constructions between pairs of modifiers and modifieants among the constituent structures of a sentence. Based on this prediction, an analysis procedure is invoked to analyze their semantic structures. If this analysis succeeds, the modifier/modificant pair is integrated into a new unified structure. Structure patterns are assigned to each structure type in the ECS. An example of structure patterns for a unit sentence is shown in Figure 6. A structure pattern eenslsts of three parts: 1) the condition for applying the pattern, 2) the procedure for semantic structure analysis, and 3) newly integrated structure type. The first part describes whether this structure pattern can be applied to the structure sequence. The second part performs a semantic relation analysis of the structure sequence which satisfy the above condition.</Paragraph>
      <Paragraph position="1"> The third part describes the structure type to be produced by the above procedure. A structure pattern might be viewed as a context fi'ee gramnmr (CFG) rule augmented with a semantic relation analysis. In this case, the condition part corresponds to the right hand side of the CFG rule, the integrated structure type part corresponds to the left hand side of it, and the procedure part can be seen as a procedure to derive the left hand side from the right hand side.</Paragraph>
    </Section>
    <Section position="2" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
5.3 Semantic Strueture Analysis
</SectionTitle>
      <Paragraph position="0"> For each constituent construction predicted, the semantic relation between modifier and modifieant in the construction is analyzed using semantic relation frames. Depending on the differences in structure types of the modifierhnodifieant pair, different types of semantic relations can be analyzed. In addition, the word meanings of the word structure and the categories for the integrated structure can also be analyzed.</Paragraph>
      <Paragraph position="1"> Semantic relation analysis can be explained by the analogy of a key and key-hole. A modifieant has a number of possible key-holes, and a modifier can be regarded as the key which can match it. The procedure is to search for the best matching key hole for the key. The shapes of keys and key-holes are determined by syntactic (case particles) and semantic (semantic category) information.</Paragraph>
      <Paragraph position="2"> The score given to the integrated structure represents the degree of syntactic and semantic mismatch recognized in the integration process. It is represented by a two-dimensional vectm', whose first argument is for syntantic mismatch, and second is for semantic mismatch. At each stage of analysis, if syntactic constraint is not pattern-name: usent-pattern-1 variables: (case-instance case-particle sequence usent) structure: structure-class= usent substructures: substructure: substructure-label1 = sub1 structure-class = case patterns = (.case-instance (restrict &gt;case-particle case-particlep)) substructure: substructure-label2 = sub2 structure-class = usent patterns = (.sequence (restrict &gt;usent usentp)) semantic-analysis-function: (case-analysis subl sub2) Fig. 6 Example of Structure Pattern (Unit Sentence) The argument with the prefix symbol * can match any nanlber of elements, and the argument with the prefix symbol &gt; can match a single element.</Paragraph>
      <Paragraph position="3">  satisfied, two points are added to the syntactic mismatch score, and if it is satisfied by modal particles, one 1-mint is added to it. As for semantic eon.~traints, if they are not satisfied, two points are added to the semantic mismatch score, and if they are satisfied through inheritance of semantic categories, one point is added to it.</Paragraph>
    </Section>
    <Section position="3" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
5.4 Case Analysis
</SectionTitle>
      <Paragraph position="0"> Case analysis is the process of matching a ease instance and prototype eases in the case fl'ame and of selecting the best matched prototype case. Then, the value of the case relation between the case instance and the predicate is determined to be the case relation of the selected prototype case.</Paragraph>
      <Paragraph position="1"> A modifier element may have co-case slots. It is true that some modifiers are strongly associated with partlcular word meanings of predicate words. I&amp;quot;or example, a verb &amp;quot;hiku ( iJI &lt; )&amp;quot; has multiple meanings, and its exact meaning in a sentence is determined when it occurs simultaneously with object cases such as &amp;quot;kaze we hiku (~J{ N~ ~l &lt; ) (catch a cold)&amp;quot;, &amp;quot;jisho we hiku ( ~}~ {q~&amp;quot; ~&amp;quot; ~J\[ &lt; ) (consult a dictionary)&amp;quot; ancl &amp;quot;denwa we hiku ( 7E ;,~, ~ ~ I &lt; ) (establish a telephone service)&amp;quot;. When a modifier element definitely determines the word meaning of a modifieant element, it is not efficient to test all possible word meanings of the modificant. Therefore, if the same case slot is shared by both a modifier and a modificant element, the meaning which shares this same case slot is selected as the word meaning of both elements without analysing another possibilities.</Paragraph>
    </Section>
    <Section position="4" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
5.5 Modality analysis \[8\]
</SectionTitle>
      <Paragraph position="0"> The classification of modality information and the procedure for analysing thmn have presented in the reference thus we will describe here only the outline. Modality analysis consists of the following three modules combined with case analysis and conjunctive analysis:  (l) Pro-ease-analysis: A modality which causes a change in the case  structure is analyzed at this stage. The case frame to be assigned to the predicate is modified by utilizing the result of this analysis before starting the ease analysis. As for semantically ambiguous auxiliary verbs which are also related to the modification of the case structure, their role is only predicted at this stage, and after case analysis, the likelihood of the prediction is evaluated.</Paragraph>
      <Paragraph position="1">  (2) Post-ease-analysis: A medaiity whose analysis requires case structure information is analysed at this stage as follows : a) If the category of the modality expression is unique, this category is assigned to the nmaning structure.</Paragraph>
      <Paragraph position="2"> b) If a daemon (a procedure to resolve ambiguities using heuristics) is attached to the modality expression, it performs the following three tasks: i) disambiguating the category of the nmdality word, ii) determining the operational scope of the modality, iii) adding the implicative meaning caused by the modality word.</Paragraph>
      <Paragraph position="3"> (3) Post-conjunetive-analysls: Following the conjunctive analysis  between the subordinate clause and the main clause, this module is activated to determine whether the medality in the main clause also operates on the subordinate clause. For negation in the main clause, the transfer of negation is considered. 'resting whether or not the modifier event is subsidiary to the oceurenee of the main event is accomplished using the semantic relation frames assigned to the predicate of the main clause.</Paragraph>
    </Section>
    <Section position="5" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
5.6 Determination of Word Meaning
</SectionTitle>
      <Paragraph position="0"> Word meaning is an entry fl'mn a word to the conceptual network consisting of dictionary information and knowledge. Since a word has multiple word meanings, it is possible that the word might have multiple entries. The information available for the determination of word meaning is the accumulated situation (discourse information) and the accumulated word meanings (accumulated concepts). If no such information is available, a default value is borrowed as the most likely word meaning. In the early stage of semantic relation analysis, tentative word meanings are assumed. These word meanings may not be accurate because they have heen determined solely by the local analysis. It is possihle that some of the rejected meanings at this stage might be more adequete as the exact word meanings for a given word in the context of the entire sentence. Therefore, the system must retain all possible word meanings as candidates so that it can change the meanings after obtaining enough information to determine the exact meaning.</Paragraph>
    </Section>
    <Section position="6" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
5.7 Determination of Category
</SectionTitle>
      <Paragraph position="0"> At the st;tge of building a meaning structure for a sentence, categories for each constituent structure are also deterlnined.</Paragraph>
      <Paragraph position="1"> Categories for a structure are usually the same as the categories of the head constituent. But if a structure is exoeentrie, categories for the structure can be obtained by some operation on its constituent substructures. For example, tile category for &amp;quot;omocha no heitai ( }S g /5 ~ ~') 3~ t~) (a toy soldier)&amp;quot; is non-animate, although the category of &amp;quot;heitai (&gt;fg IN) (a soldier)&amp;quot; is hmnan (therefore, animate).</Paragraph>
      <Paragraph position="2"> In order to determine the categories of asmnantically anabigvtous structure or a exoeentrie structure, an attached procedure is invoked.</Paragraph>
      <Paragraph position="3"> For example, the Japanese noun &amp;quot;tame ( ?d &amp;)&amp;quot; is ambiguous because it has two categories, purpose and cause. To resolve this ambiguity, a daemon is invoked after the noun phrase containing &amp;quot;tame&amp;quot; is analyzed. 'Phi,.; daemon performs tile following heuristics: 1) If &amp;quot;tame&amp;quot; is followed lay both a ease particle &amp;quot;ni ( l.= )&amp;quot; and a modal particle &amp;quot;ha ( 12)&amp;quot; (that is, in ease of&amp;quot;tameuiha ( &amp; a5 l= I~)&amp;quot; form), the category is determined to be &amp;quot;purpose&amp;quot;.</Paragraph>
      <Paragraph position="4"> 2) If &amp;quot;tame'is succeeded lay an embedded sentence and the predicate shows a perfective aspect (that is, the end part of tile embedded sentence contains the auxiliary verb &amp;quot;ta ( t:)&amp;quot; or &amp;quot;teiru ( -C ~' 7o )&amp;quot;), or the semantic category of the predicate is &amp;quot;state&amp;quot;, the category is determined to be &amp;quot;cause&amp;quot;.</Paragraph>
      <Paragraph position="5">  3) Otherwise, &amp;quot;purpose&amp;quot;.</Paragraph>
      <Paragraph position="6"> 6. Transfer</Paragraph>
    </Section>
    <Section position="7" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
6.1 Transfer Functions
</SectionTitle>
      <Paragraph position="0"> Discrepancies among ECS's for different languages arise for several reasons. One is essential in nature. We believe that syntactic information should be preserved as far as possible in FCS. But semantically equivalent information is often realized differently in the syntax of different languages. Conceputual systems are also different in different language communities. These differences must be reflcctcd in BCS's.</Paragraph>
      <Paragraph position="1"> Transfer process should fill these gaps between the ECS's of two different languages. At the transfer stage from Japanese to English, structures, relations and concepts in J-ECS arc transferred into those in g-ECS. Since concepts and relations are integrated into structures, the transfer of concepts and relations is performed at the same time as the transfer of structures.</Paragraph>
    </Section>
    <Section position="8" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
6.2 Transfer of elements of ECS
</SectionTitle>
      <Paragraph position="0"> In the course of the transfer processes, ECS's in the source language are converted by reeursively traversing original structures from top nodes, and creating corresponding target structures. So, the transfer process consists of transfering components of the ECS's, i.e., concepts that make up the ECS and relations which hold among them.</Paragraph>
      <Paragraph position="1"> 13ut there are cases which don't suit this scheme well, and hence require special treatment. They are idiosyncratic to \[exical items and specific procedures have to be triggered by certain concepts included in the original structm'es. Idiosyncratic transformations include: 1) delctlon: certain structures in the source structures are deleted and no counterpart structures are embodied in target structures; for example, eomt~ound structures are transferred into primitive struetures, as in the transfer from &amp;quot;Sakana we tsuru ( ,((t ~&amp;quot; $&amp;quot;; .,.o )&amp;quot; in Japanese to &amp;quot;fish&amp;quot; in l'haglish, 2) addition: certain structures Ihat have no counterpart in the source structures are added to target structures; for example, primitive structures In'o transferred into compound structures, as in tim transfer from &amp;quot;Samidare ( .It J\] H:i)&amp;quot; in Japanese into &amp;quot;early summer rain&amp;quot; in English, and 3) modifieation: .~;ource structures are non-trivially changed in the process of transfer, as in the transfer 5'om Japanese adjective sentence &amp;quot;Jisuu ga eel ( :-~: ~ \]/~g v, )&amp;quot; into Plnglish &amp;quot;There are ...&amp;quot; sentence structure, or types of input and output are different, as in the transfer from Japanese phrase &amp;quot;... suru toM (... -4&amp;quot; Za II~'i,)&amp;quot; (&amp;quot;time&amp;quot; case instance) into the English subordinate clause construetion &amp;quot;Whel~ ...&amp;quot;.</Paragraph>
      <Paragraph position="2"> The transfer ef concepts consists of 1) transfer of semantic categories, and 2) transfer of word meanings. A transfer dictionary for a pair of languages is prepared to give information on the eorrespondence between concepts in hoth languages. An entry of the dictionary consists era triad or fi'alnes, that is, a source concept fi'ame, a target concept flame, and a mediating frame. Since concept correspondence is in general not one-to-one, there may be several target concepts given one source concept and vice versa. Mediating fi'ames can provide infm'mation on conditions to make it possible to choose auaong alternatives. Concepts that would trigger idiosyncratic procedm:es lmve the information in the dictionary in the form of transfer rules.</Paragraph>
      <Paragraph position="3"> Transfer of relations consists of transfer of four types of relations described in 3.3. Correspondence information is also placed in the transfer dictionary. But inforlnation on case relation transfer are stored as verbal concepts, since they might be specific to individual verbs or classes of verbs.</Paragraph>
    </Section>
    <Section position="9" start_page="6271" end_page="6271" type="sub_section">
      <SectionTitle>
6.3 Transfer process
</SectionTitle>
      <Paragraph position="0"> The transfer process is essentially a manipulation of fl'ame networks. A rule-based system was devised to facilitate easy specification of the complex pattern of network manipulations. Au example of the transfer rule is shown in Figure 7. Similar to structure patterns, a transfer rule consists of three parts: a matching part, execution part, and a return part. The matching part specifies the conditions under which the rule should be invoked. It also contains variables, which are bound during matching process and the information will be passed to and used in the later stage when the matching is successful. The execution part specifies the transfer of substructures and concepts, value assignment to the variables, fnrther conditional branching, and other operations. Lisp code can he invoked in this part. The return part specifies the target structure that has to be construeted and returned on the basis of tile application of the entire rule.</Paragraph>
      <Paragraph position="1"> (defrule J:USENT (if (self = (J:USENT(*verb(varj-verb)) *meaning(varj-mns))(*m da ity(varj m d))(*cases restj cases) )) (i-verb~ (J:WOR,D (*stem-pos (optional (vat j-stem-type))) )) then lexec uocal r-toO ~rest e-modif)) {LISP (cond (l-stem-type (setq r-fun #'(lambda (t-frm) (isa* t-ffm 'T:noun-verb})) (send* j-mns 'put: '$restriction r-fun)))) (j-mns-&gt; e-mns) (j-mod -&gt; e-mod) (((for-all}j-cases) -&gt; e-cases) (LISP (and j-stem-tyRo (send* j-runs 'remove: $restriction r-fun)) (setq e-modi (mapcan #'(Eambda (q) (and (isa* q 'E:Modifier-Clause) (neons q))) e-cases)) \[setq e-cases (subtract e-cases e-modif)) ) (if(LISPe-modif) then (exec (return (! E:CSENT e-csent)) where (e-csent = (E:CSENT(*main (! E:Predicatee-pred)) (*mod\]fier-clausee-modif))) (e-prod1 = (E:Predlcate( meaning e-runs) (modahtye-mod) ( cases e-cases)))) else (exec (return (\[ E:Predicate e-pred2)) , , * where (e-pred2 = (E:Predicate ( meaning e-mns) ( modality e-mod) ( cases e-cases))))))))  The frame system presented here has a elass-lnstanee hierarchy, which adopts an &amp;quot;object-oriented&amp;quot; style of implementation for the frame network manipulation in the transfer process. Transfer rules specifying how the network should he handled are written for each type of structm'es. These are converted into executable forms, and attached to class frames of the structure as methods. When the top node of the input ECS is given a &amp;quot;transfer&amp;quot; message, corresponding methods in the class frame, to the instances of which the top node belongs, will be invoked and handle the network as is specified in the original rules.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>