File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/86/c86-1130_metho.xml
Size: 32,164 bytes
Last Modified: 2025-10-06 14:11:54
<?xml version="1.0" standalone="yes"?> <Paper uid="C86-1130"> <Title>Knowledge Structures for Natural Language Generatlon ~</Title> <Section position="3" start_page="0" end_page="556" type="metho"> <SectionTitle> 2 Ace Fundamentals </SectionTitle> <Paragraph position="0"> I have suggested that the development of extensible and adaptable natural language systems depends on a knowledge representation framework within which generalizatlons are effectively exploited. This is the primary goal of the Ace framework. The starting point of Ace was an implementation of a knowledge representation called KODIAK \[21\], which was extended to include explicit structured relationships between language and meaning. This section presents the basic knowledge representation principles behind Ace, and provides an example of how conceptual knowledge is used to relate knowledge about selling to knowledge about gi~ng.</Paragraph> <Section position="1" start_page="0" end_page="554" type="sub_section"> <SectionTitle> 2.1 Basic Principles </SectionTitle> <Paragraph position="0"> Many knowledge representation systems, however different they appear superficially, may be shown to have the same SUNIX is a trademark of AT & T Bell Laboratories formal expressive or inferential power. This discussion centers not on the question of formal power but on the nature of the knowledge which must be expressed. The Ace knowledge representation provides a framework for expressing essential linguistic knowledge in a form suitable for encoding within a representational formalism.</Paragraph> <Paragraph position="1"> The following principles guide the encoding of knowledge important in the generation task: o Principle 1. Inheritance of Conceptual Relations.</Paragraph> <Paragraph position="2"> Concepts in memory are organized into a hierarchy of categories, in which more specific concepts inherit &quot;features&quot; from more general concepts. This inheritance is a representational tool which has been employed throughout the history of Artificial Intelligence (e.f.\[18,19,2,3\]). The question of what exactly is inherited, however, can be answered in a variety of ways. Ace takes advantage of structured inheritance, (of. \[3\]), in which concepts linked to a particular structure may inherit from super-categories of that structure. For example, knowledge about the seller of a sellin 9 action may be inherited from knowledge about the giver of a giving action.</Paragraph> <Paragraph position="3"> *, Principle ~. Proliferation of Conceptual Categories.</Paragraph> <Paragraph position="4"> Individual concepts are themselves categories, and any concept about which there is particular knowledge is considered to form a category. Thus categories proliferate: Probably, there are far more conceptual categories than there are lexical items in the system. For example, it will be shown later in this section that it is reasonable to postulate a concept specifically for the action of paying money in exchange for merchandise, although there is no lexical item corresponding to this concept. The lexical term &quot;pay&quot; is associated with a more general concept, that of providing money in exchange for virtually anything. The lexical term &quot;give&quot; may be associated with a general giving concept, but giving to charity, giving an idea, and giving a chance are distinct concepts with distinct linguistic manifestations. For example, the use of the verb &quot;give&quot; without object or indirect object as in &quot;Bill gave&quot; and &quot;I gave at the office&quot; is a linguistic phenomenon which appears almost exclusively when referring to charitable giving.</Paragraph> <Paragraph position="5"> e Principle 3. Explicit Referential Relationships.</Paragraph> <Paragraph position="6"> There are a range of conceptual relationships important in language use which are not easily described as factual or ontological relationships. The one which is considered here is the view relationship, which helps to determine how concepts may be used in expressi.ng other concepts. The concepts of giving and taking may be related to the concept of a transfer-event, but the instantiation of the abstract giving and taking concepts cannot be factually inferred from the instantiation of transfer-event. For example, &quot;John gave five dollars to charity&quot; does not imply that a charitable organization took the five dollars from John. &quot;Mary took the money from John&quot; does not imply that John gave Mary the money. In many circumstances, however, the same event may be described using &quot;give&quot; or &quot;take&quot;. For example, (1) &quot;John gave Mary five dollars for the book&quot; may imply (2) &quot;Mary took five dollars from John for the book&quot;. Representing giving and tak- ing as views of transfer-event permits the encoding of knowledge about describing transfer-events without re~luiring a given event to be classified as giving or taking. These views may thus represent the knowledge that &quot;John took <x> from Mary&quot; and &quot;Mary gave John <x>&quot; might be used to describe the same event. Such views will be shown to be useful in determining how linguistic structures are used to refer to events.</Paragraph> <Paragraph position="7"> The next section describes the basic elements of the hier- archical framework of Ace.</Paragraph> </Section> <Section position="2" start_page="554" end_page="554" type="sub_section"> <SectionTitle> 2.2 Structured Asuociatlons in Ace </SectionTitle> <Paragraph position="0"> Ace makes use of a notation in which there are two types of entities: objects and structured associations2 A structured association is a relation among two or more objects which also relates corresponding objects associated with the related objects.</Paragraph> <Paragraph position="1"> The most common structured associations in Ace, taken from the KODIAK representation, 4 are the DOMINATE, or &quot;D&quot;, relation, which associates a subcategory with its parent category, and the MANIFEST or &quot;m&quot; relation, which associates a category with an aspectual or role. This hierarchical system is analogous to isa-links and slots in other similar representation systems; the motivation behind KODIAK was to preserve the ideas behind frame-based representations while clarifying the semantics of a &quot;slot&quot;. For a comparison of KODIAK with other research, see Wilensky (forthcoming).</Paragraph> <Paragraph position="2"> The term ROLE-PLAY, also taken from KODIAK, is used to indicate corresponding concepts across structured associations. For example, the assertion, (DOMINKI'E action selling with (ROLE-PLAY actor seller)) indicates that selling is a subcategory of action, with seller playing the role of actor. A graphical representation of this relation, with the ROLE-PLAY implicit, is illustrated in fig- null Structured associations with RObE-PLAYs are the basic mechanism for organizing knowledge m Ace. The next section describes how these associations are used to represent basic knowledge about buying and selling.</Paragraph> </Section> <Section position="3" start_page="554" end_page="555" type="sub_section"> <SectionTitle> 2.3 The Commercial Transaction Example </SectionTitle> <Paragraph position="0"> I have proposed that generalizing about linguistic constructs such as the dative form in &quot;John gave Mary a dollar&quot;, &quot;John told Mary a story&quot;, and &quot;John sold Mary a book&quot;, seems to depend on the representation of concepts such as giving, telling, and selling. This section presents the foundation for the encoding of selling in Ace.</Paragraph> <Paragraph position="1"> Consider the concept of the commercial transaction \[7\].</Paragraph> <Paragraph position="2"> The commercial-transaction represents an event in which a merchandise object is exchanged for legal tender. The essential knowledge about this event may be represented by classifying the commercial-transaction as a complex-event, composed of at least two simpler events, ct-merchandise..transfer and or-tender-transfer. Each of these two sub-events is a kind of transfer-event, and is thus used to associate roles of the commercial-transaction with roles of transfer-event. This knowledge is captured in figure 2.</Paragraph> <Paragraph position="3"> Figure 2 illustrates the important knowledge that the merchant receives the tender fl'om the customer, and the cus- tomer receives the merchandise from the merchant. Con- cepts such as merchant, cu,.itomer, merchandise, and tender are aspectuals of the commercial-transaction; that is, they &quot;This term, and the idea of using general structured associations as a language processing tool. are due to Wile.sky.</Paragraph> <Paragraph position="4"> are specific concepts whose meaning is undetachable from the commercial-transaction event. However, much of the knowledge about these concepts, such as the recipient and source roles, is inherited from other concepts. As in other frame-like systems \[19,2\], this organization allows roles of a concept to be inherited in this manner. The ROLE-PLAY relationship in Ace, however, permits more than this simple form of inheritance: It allows for the semantics of aspectuals to be defined in terms of other aspectuals. For example, the meaning of the merchant aspectual of the commercial-transaction here is represented in part by the ROLE-PLAY relation which links this aspectual to the source of the d-merchandise-transfer and that which links it to the recipient of the st-tender-transfer.</Paragraph> <Paragraph position="5"> The assertions above form an im:port ant core of knowledge in the way language is used to describe such events. For example, it will be shown in section 4 that the knowledge that merchandise and tender play object roles is linked to knowledge about transitive verb forms, so that phrases such as &quot;bought a book&quot; and &quot;paid five dollars&quot; conform to a general rule. The next section discusses how concepts such as buying and selling, used to refer to the commercial-transaction concept, are represented in Ace.</Paragraph> </Section> <Section position="4" start_page="555" end_page="556" type="sub_section"> <SectionTitle> 2.4 Actions as VIEWs of Events </SectionTitle> <Paragraph position="0"> I have proposed that verbs such as &quot;give&quot; and &quot;take&quot; refer to the actions giving and taking, and thus refer indirectly to the general transfer-event concept. The motivation for this analysis is to facilitate the representation of knowledge about the roles which giver and taker play, thereby enabling &quot;John gave Mary a book&quot; and &quot;Mary took a book from John&quot; to describe indirectly the same event, as &quot;All gave Frazier a punch&quot;, and &quot;Frazier took a punch fl'om Ali&quot; may indirectly describe the same event. The commercial-transaction event is generally described using the verbs &quot;buy&quot;, &quot;sell&quot;, and &quot;pay&quot;. &quot;Sell&quot; and '~pay ~ behave similarly to the verb &quot;give&quot;; &quot;buy&quot;, behaves more llke &quot;take&quot;. For example, &quot;John sold Mary a book&quot;, and &quot;Mary paid five dollars for the book&quot; both use the dative form, and &quot;John bought the book from Mary&quot; exhibits a structure identical to &quot;John took the book from Mary&quot;. The representation of the concepts buying and selling in Ace relates these concepts to giving and taking so that knowledge about expressing giving and taking may be used also for buying and selling.</Paragraph> <Paragraph position="1"> The concepts giving and taking in Ace are related to the transfer-event concept by a structured association called a VIEW.</Paragraph> <Paragraph position="2"> Inspired by the notion of a view in earlier knowledge representations \[17,2\], the Ace VIEW is applied to metaphorical and analogical relationships, similar to those described in \[16,8\]. VIEWs are used to represent knowledge about concepts which may be used in expressing other concepts.</Paragraph> <Paragraph position="3"> The Ace network in figure 3 represents the basic knowledge about giving, taking, buying, and selling. In this hierarchy, the structured association view1 between transfer-event and giv- ing DOMINATEs the structured association view3 between c t-merchandise-transfer and selling, and view2between transfer event and taking DOMINATES view$ between st-merchandises transfer and buying.</Paragraph> <Paragraph position="4"> The representation in figure 3 demonstrates on a small scale how the hierarchical arrangement of VIEWs is used in the encoding of structured associations. Structured associa-.</Paragraph> <Paragraph position="5"> tions such as view1 between transfer-event and giving DOM~ INATE other more specific relations, such as view3. Note that this makes the explicit representation of ROLE-PLAY relations for view3 unnecessary, as the relationship between merchant and seller in view3 is specified by the relationship between source and giver in view1.</Paragraph> <Paragraph position="6"> The representation of the selling concept is a simple example of how Ace encodes abstractions which may be used in language processing. The abstraction here is the relationship between a general category giving and a general category transfer-event. There are two ways in which this abstraction may be used: (1) A more specific association may be represented as a subcategory of the abstract association. This is the case in the selling example presented here. In this case, knowledge about the abstract association may be used in applying the specific association, thus knowledge about expressing an abstract concept may be used in expressing a more specific concept. This allows much of the same knowledge to be used for phrases involving &quot;giving&quot; and &quot;selling&quot;. (2) A concept which is associated by another VIEW with the abstract concept may then also be expressed using the abstract VIEW. This is the case with expressions such as &quot;give a punch&quot; (cf. section 4.3), which takes advantage of the abstract action as transfer-event view in combination with the transfer-event as giving VIEW.</Paragraph> <Paragraph position="7"> The next two sections discuss the application of the Ace framework to the representation of linguistic knowledge and to the representation of the knowledge which associates linguistic and conceptual structures.</Paragraph> </Section> </Section> <Section position="4" start_page="556" end_page="557" type="metho"> <SectionTitle> 3 Basic Grammatical Knowledge </SectionTitle> <Paragraph position="0"> The principles outlined in section 2.1 motivate a representation in which knowledge is dispersed throughout a hierarchy, with a greater number of structures, each containing more limited information. Linguistic knowledge in Ace is organized into a hierarchy which incorporates this type of organization.</Paragraph> <Paragraph position="1"> In fact, the same knowledge representation language is used to encode both linguistic and conceptual knowledge in Ace.</Paragraph> <Paragraph position="2"> The linguistic hierarchy provides for a simple set of basic linguistic templates, with little redundancy and relative ease of extension. The following principles of linguistic representation are suggested: Princ@h, $. Inheritance of Linguistic Features.</Paragraph> <Paragraph position="3"> Sets of features which are common to a certain class of templates need not be specified independently for each template in the class. Thus, if there is a set of features shared among passive sentences~ or among prepositional phrases, these features belong by default to any template in the class. This eliminates the need for fully specifying the structure of phrases which have specialized properties or meaning* o Principle 5. Proliferation of Linguistic Categories.</Paragraph> <Paragraph position="4"> In order to take advantage of the inheritance of features, there must be a wide range of classes of iingulstic templates which share sets oi features. Often these categories depart from the traditional syntactic classifications. Requiring that a template bca member of a unique category in the case of a gerund or nominalization can prove difficult, as these may inherit cerdeg rain attributes fl'om verbs and certain attributes from nouns Thus any template may inherit features, including structural descnptmns, from multiple categorms.</Paragraph> <Paragraph position="5"> Categories are arranged hierarchically, so each category inherits from all its ancestors in the hierarchy.</Paragraph> <Paragraph position="6"> o Principle 6. Distinguishing Grammatical Relations from Grammatical Patterns. A great deal of linguistic information seems associated with structural relationships between linguistic constituents which are dependent neither on their order in a surface structure nor on the precise nature of the structure in which they appear. For example, the relation between subject and verb retains its linguistic features regardless of how the subject and verb appear in any surface structure: The agreement between subject and verb in ~John was given the book by Mary&quot; is the same as in aWas John given the book by Mary?&quot; as is the conceptual recipient role which John plays. Such information does not pertain to a particular surface structure, but to any surface structure in which a noun phrase and verb are in the subject-verb relation. In &quot;John kissed Mary on the cheek&quot; and &quot;The kiss on the cheek pleased Mary&quot;, the role of %n the cheek&quot; as it relates to &quot;kiss&quot; is independent of whether the prepositional phrase is part of a verb phrase or noun phrase. In general, structural linguistic relationships are not limited to those which are directly linked to constituent order, and thus a more general facility than a syntactic pattern is required to represent these relationships.</Paragraph> <Paragraph position="7"> o Principle 7. Uniformity of Representation.</Paragraph> <Paragraph position="8"> Linguistic knowledge is knowledge, and thus cart be encoded using the same representational framework as conceptual knowledge. The same structured association~ used in the conceptual hierarchy can be used in the linguistic hierarchy, u Having such uniformity of representation has the practical vahm of facilitating the interaction of conceptual and linguistic structures.</Paragraph> <Paragraph position="9"> SThe use of a knowledge representation language to encode syntactic knowledge for file purpose of semantic interpretation ha.~ been praco riced with KL-ONE \[20\] and its successors, also favoring uniformity of' representatiom Such t;ystcms have not been used, to my knowledge, to encode associations between conceptual and linguistic knowledge.</Paragraph> <Paragraph position="10"> The discussion which follows demonstrates how linguistic knowledge may be encoded using the framework described in the previous section, and discusses the effect of property inheritance on linguistic knowledge representation.</Paragraph> <Section position="1" start_page="556" end_page="557" type="sub_section"> <SectionTitle> 3.1 Multiple Inheritance in the Ace Lin- guistic Hierarchy </SectionTitle> <Paragraph position="0"> This section shows how the structured associations of Ace, and particularly the capacity for multiple inheritance, are used to encode some of the linguistic knowledge used in the construction of simple sentences.</Paragraph> <Paragraph position="1"> ~$.1.1 Verb phrase~ i~ Ace Verb phrases provide a good example of the use of a linguistic hierarchy because they exhibit a variety of surface forms while obeying certain regularities. One type of verb phrase is the dative-vp, a verb-phrase made up of a constituent dvp-indir, which includes the verb and noun phrase corresponding to the indirect object, followed by the nonn phrase corresponding to the direct object. The treatment of the dvpoindir as a separate constituent is done to facilitate the handling of other dative forms* Figure 4 shows how knowledge about the dative verb phrase pattern is encoded in Ace, as well as how this dative-vp is positioned in the verb phrase hierarchy. The pattern dvp-pattern represents the ordering of the constituents of the verb phrasej while t'he relation dvp-indir is used to represent the relationship between the dative verb and indirect object. Section 4 will show how this relation is associated with conceptual knowledgedeg By allowing aspectuals which represent patterns and patdeg tern constituents to play multiple roles, the representation of linguistic knowledge as shown in figure 4 shows how knowl.edge about infinitives, gerunds, and verb phrases is distributed in the Ace hierarchy. The various verb phrase patterns fall beneath the verb-phrase template, as do the gerund phrase, infinitive phrase, and finite, verb phrase nodes, in order to produce a finite verb ~hrasel a node lower ill the hierarchy must be instantiated, this hmrarclfical organization permits the gerund phrase and infinitive phrase to have the same linguiqtic structure as the verb phrase, modulo the fore1 of the verb part. An instantiated verb-phrase in Ace thns inherii, s most of it,~ internal structure from one category, for example dative-vp, and its external behavior from another, for examdeg pie, finite-verb-phrase. The verb~phrase category !tself plays no external syntactic role---there is no pattern in which a condeg stituenlJ belongs to the verb-.ph,'ase category and to no lower category~ although theoretically there could be. The effectiyc organization of information ~,bout verb phrases stems directly from the application of the basic knowledge x~presentatioa principles of Ace ~o linguistic knowledge.</Paragraph> <Paragraph position="2"> This section has shown how a hierarchical representation is used to encode linguistic relations. The next section concentrates on how the representation of explicit referential relationships links this linguistic knowledge to conceptual knowledge. null</Paragraph> </Section> </Section> <Section position="5" start_page="557" end_page="558" type="metho"> <SectionTitle> 4 Associating Language and Mean- ing </SectionTitle> <Paragraph position="0"> Section 2.1 presented the foundations of the Ace framework and its application to meaning representation, proposing that concepts be hierarchically organlzed, linked together via structured associations. Section 3 described how linguistic knowledge can also be hierarchically organized within this framework, and how features can thus be inherited through linguistic categories. The idea of a linguistic relation was proposed, to distinguish structural relationships from ordering relationships in grammatical constructs. Naturally, the knowledge required to produce correct and appropriate utterances inc\],udes both of these classes in addition to the links which DIUO l;ne ClasSes ~oge~ner.</Paragraph> <Section position="1" start_page="557" end_page="557" type="sub_section"> <SectionTitle> 4.1 Basic Principles </SectionTitle> <Paragraph position="0"> The goal of taking advantage of explicit referential knowledge, discussed in section 2.1, along with the framework presented in the previous sections, suggests two principles directed towards the association of linguistic and conceptual knowledge: * Representation Principle 8, Correspondence of Linguis- tic and Conceptual Structures. Linguistic structures, such as lexical terms, linguistic categories, and grammatical structures, are directly assoclated with conceptual categories. General linguistic categories in Ace, such as verb-indir-relation, correspond to general conceptual categories, such as transfer- event.</Paragraph> <Paragraph position="1"> Specific lexical terms, such as &quot;buy&quot; and &quot;sell', are linked to more specific concepts, such as buying and selling. Grammatical structures, such as the modifier- noun relation, are associated with conceptual relations, such as MANIFEST.</Paragraph> <Paragraph position="2"> * Representation Principle 9. Association of Linguistic Features tuith Conceptual Attributes. The structured association permits the relation of linistlc aspectuals with conceptual aspectuals via ROLE-AY. Linguistic features, such as dvp-pattern and ivp- verb as described in section 3 are represented as aspectunis in Ace, as their status depends on the template of which they are a part. The association of these features with conceptual attributes goes along with the association of the template with a concept. For example, the indirect object feature iobj is an aspectual of verb-indir-relation. The linguistic feature iobj is linked to the conceptual attribute recipient, an aspectual of the transfer-event concept. The direct-object feature obj, an aspectual of verb-obj-relation~ is linked to the conceptualobject concept, an aspeetual of the simple- event concept. Thus linguistic features have conceptual correlates.</Paragraph> <Paragraph position="3"> The next section describes how these principles are realized in the association of language and meaning in Ace.</Paragraph> </Section> <Section position="2" start_page="557" end_page="557" type="sub_section"> <SectionTitle> 4.2 Linking Linguistic and Conceptual Struc- tures Using REF </SectionTitle> <Paragraph position="0"> The main tool for representing relationships between linguistic structures and conceptual structures in Ace is a structured association called REF. The REF association, designating &quot;referential&quot; relationships, is similar to VIEW, except that it joins language to concepts instead of concepts to concepts.</Paragraph> <Paragraph position="1"> The linguistic knowledge presented earlier has included information about how verbs and their objects or indirect objects may appear in surface structure. The knowledge ussential to build these structures, however, is contained in the correspondence between linguistic relations and conceptual entities. This information is presented in figure 5.</Paragraph> <Paragraph position="2"> The diagrams in figure 5 illustrate how the syntactic structure of the dative verb phrase is associated with its conceptual structure. The verb part and noun phrase in the ivp-pattern in the top diagram belong to the verb-indir-relation, which associates with the indirect object the concept of recipient.</Paragraph> <Paragraph position="3"> This diagram presents a slightly abbreviated version of the Ace representation given in section 3, as ivp-verb and ivp-np are associated only indirectly with the verb-indir-relation via the ivp-relation aspectual.</Paragraph> <Paragraph position="4"> The etructuredassoeiation between the verb-obj-relation and the simple-event concept in the lower diagram of Figure 5 links the object of the verb in the dative verb phrase to the object of the simple event. In this association, as in the association of the verb-indir-relation with the transfer-event, the verb part dvp-verb is associated via ROLE-PLAY with the event itself, rather than with any aspectual of the event.</Paragraph> <Paragraph position="5"> Like the pattern-concept pair \[1 l\]or the unification grammar template \[13,1\], REF is a means of associating linguistic structure with conceptual structure. The template, however, is replaced with an explicit structural link in the knowledge network. This makes it easier to perform the knowledl~e-driven aspects of generation because no querying or complex matching is necessary. The use of the REF association also facilitates incremental generation by encoding knowledge about referential relationships as structured associations at various levels in the Ace hierarchy: The construction of a complete sentence involves the combination of structures derived from a number of REF associations, each of which refines those structures already active, e</Paragraph> </Section> <Section position="3" start_page="557" end_page="558" type="sub_section"> <SectionTitle> 4.3 Knowledge About Specialized Construe </SectionTitle> <Paragraph position="0"> The examples given in the previous section are simple illustrations of the use of associations between language and meaning at a variety of levels. These levels become especially apparent in the representation of knowledge about specialized constructs, whose meaning can be only partially represented as associations from more general linguistic structures.</Paragraph> <Paragraph position="1"> ~Those familiar with KL-ONE and other similar representation lan- guag~ will observe that the Ace representation tends to avoid matching by assuming that the concept being generated from is assigned to a spe- cific category. Thus some of the work done by template matching in systems such as PHRED is done during the classification of a concept in Ace. This is consistent with the Proliferation of Conceptual Categories .principle: the generator need not obtain conceptual information that is more specific than that contained in the category in which a concept has been classified.</Paragraph> <Paragraph position="2"> The means in which specialized knowledge is encoded varies according to the particular construct. The &quot;give a hug&quot; expression is interesting because there is no single syntactic structure which can be identified with the specialized interpretation, yet intuitively the specialized meaning seems tied to the use of the verb &quot;give&quot; in conjunction with the object &quot;hug&quot;. While the metaphorical connection between the hug- ging action and the giving action is dependent on the &quot;acting upon is giving&quot; metaphor, this &quot;hugging is hug-giving&quot; metaphor must also be associated with the particular lexical items &quot;give&quot; and &quot;hug&quot;. Figure 6 shows how both objectives may be accomplished: The link between hug-giving and hug-transfer is labeled view1&quot; to indicate that it is DOMINATEd by the structured association between giving and transfer-event.</Paragraph> <Paragraph position="3"> This association, view1, relates the source of the transfer-event to the giver or actor of the giving. By inheritance and ROLE-PLAY, viewI'associates the giver of the hug-giving action with the source of the hug-transfer event.</Paragraph> <Paragraph position="4"> The views viewPS and view3 represent metaphorical associations that actions may be VIEWed as transfer-events from the actor to the object. View3 indicates the correspondence between the object of an action or event and the recipient of the transfer, and between the event and the object of the transfer. View2 represents the relationship between source and actor. The association between the hug-transfer event and the hugging action, labeled viewg,3&quot; allows the inheritance of the knowledge that the source of the hug-transfer corresponds to the actor of the hugging action, that the object of the hug-transfer corresponds to the hugging action itself, and that the recipient of the hug-transfer corresponds to the object of the hugging.</Paragraph> <Paragraph position="5"> The view2,3' association is DOMINATEd by both view2 and view3 and thus inherits their ROLE-PLAYs.</Paragraph> <Paragraph position="6"> Knowledge about specialized constructs, such as &quot;giving a hug&quot;, makes use of abstract structured associations between language and meaning just as knowledge about selling makes use of knowledge about giving. In this way the Ace representation is used to take advantage of generalizations in the</Paragraph> </Section> </Section> class="xml-element"></Paper>