File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/79/p79-1009_metho.xml
Size: 27,815 bytes
Last Modified: 2025-10-06 14:11:17
<?xml version="1.0" standalone="yes"?> <Paper uid="P79-1009"> <Title>Taxonomy, Descriptions, and Individuals in Natural Language Understanding</Title> <Section position="2" start_page="0" end_page="33" type="metho"> <SectionTitle> 1. THE TASK AND THE SYSTEM </SectionTitle> <Paragraph position="0"> Generally speaking, we want to provide a natural interface to a subsystem that knows how to present conceptual information intelligently (on a bit-map display) -- in this case the Augmented Transition Network (ATN) grammar from bae LUNAR system \[5\]. The information presentation subsystem allows flexible specification of coordinate system mappings, including rectangular windows, from parts of the ATN onto a sequence of &quot;view surfaces&quot;. Object types can be assigned arbitrary presentation forms (graphic or alphanumeric), which can be modified in particular cases. Parts of the grammar are displayed according to standing orders and special requests about shape and projection.</Paragraph> <Paragraph position="1"> Our task is to command and control the intelligent graphics subsystem through natural language. For example, a sample dialogue with the system might include this sequence of utterances: (I) Show me the clause level network.</Paragraph> <Paragraph position="2"> \[System displays states and arcs of the S/ network\] (2) Show me S/NP.</Paragraph> <Paragraph position="3"> \[System highlights state S/NP\] preverbal states\] (4) No. I want to be able to see S/AUX.</Paragraph> <Paragraph position="4"> \[System &quot;backs off&quot; display so as to include state S/AUK\] At the same time, we would like to ask factual questions about the states, arcs, etc. of the ATN (e.g. &quot;What are the conditions on this <user points> arc?&quot;). Ouestions and commands addressed to the system typically (I) make use of elements of the preceding dialogue, (2) can be expressed indirectly so that the surface form does not reflect the real intent, and (3) given our graphical presentation system, can make reference to a shared non-linguistic context. The issues of anaphora, (indirect) speech acts, and deixis are thus of principal concern. The natural language system is organized as illustrated in Figure I a. The user sits at a bit-map terminal</Paragraph> <Paragraph position="6"> (highlighting types of knowledge involved).</Paragraph> <Paragraph position="7"> equipped with a keyboard and a pointing device. Typed input from the keyboard (possibly interspersed with coordinates from the pointing device) is analyzed by a version of the RU_~S System \[2\] ~ an ATN-based incremental parser that is closely coupled with a &quot;case-frame dictionary&quot;. In our system, this dictionary is embodied in a syntactic taxonomy represented in KLONE. The parser produces a KLONE representation of the syntactic structure of an utterance. Incrementally along with its production, this syntactic structure triggers the creation of an interpretation. The interpretation structure -- the literal (sentential) semantic content of the utterance -- is then processed by a discourse expert that attempts to determine what was really meant.</Paragraph> <Paragraph position="8"> In this process, anaphoric expressions must be resolved and indirect speech acts recognized. Finally, on the basis of what is determined to be the intended ~orce of (3) Focus in on the preverbal constituents.</Paragraph> <Paragraph position="9"> \[System shifts scale and centers the display on the a Dashed elements of the figure are proposed but not yet implemented. the utterance, the discourse component decides how the system should respond. It plans its own speech or display actions, and passes them off to the language generation component (not yet implemented) or display expert. Some of these operations will be discussed in more detail in Section 3.</Paragraph> </Section> <Section position="3" start_page="33" end_page="34" type="metho"> <SectionTitle> 2. THE REPRESENTATION LANGUAGE </SectionTitle> <Paragraph position="0"> Before we look at details of the system's use Of KLONE, we briefly sketch out some of its cogent features.</Paragraph> <Paragraph position="1"> )CLONE is a unifom language for the explicit representation of natural language conceptual information based on the idea of structured inheritance networks \[3\]. The principal representational elements of ~ONE are Concepts, of which there are two major types -- Generic and Individual. Generic Concepts are arranged in an inheritance structure, expressing long-term generic knowledge as a taxonomy a. A single Generic Concept is a description template, from which individual descriptions (in the form of Individual Concepts) are formed. Generic Concepts can be built as specializations of other Generic Concepts, to which they are attached by inheritance Cables. These Cables form the backbone of the network (a Generic Concept can have many &quot;superConcepts&quot; as well as many &quot;subConcepts&quot;). They carry structured descriptions from a Concept to its subConcepts.</Paragraph> <Paragraph position="2"> KLONE Concepts are highly structured objects. A subConoept inherits a structured definition from its parent aa and can modify it in a number of structurally consistent ways. The main elements of the structure are Roles, which express relationships between a Concept and other closely assooiatnd Concepts (i.e. its properties, parts, etc.). Roles themselves have structure, including desoriptlons of potential fillers eee, modality lnfomation, and names aaee. There are basically two kinds of Roles in )O.ONE: RoleSets and IRoles. RoleSets have potentially many fillers e~.g. the officer Role aeaea of a particular COMPANY would be filled once for each officer). A RoleSet has as part of its internal structure a restriction on the number of possible fillers it can have in any particular instance.</Paragraph> <Paragraph position="3"> A RoleSet on an Individual Concept stands for the particular set of fillers for that particular concept.</Paragraph> <Paragraph position="4"> An IRole (for Instance Role) appears on an Individual Concept to express the binding of a particular value to the Role it plays in that Concept. (There would be exactly one IRole for each officer slot of a particular company, resardless of the actual number of people playing those roles.) There are several inter-Role relationships in KLONE, which relate the Roles of a Concept to those of s sdperConcept. Such relationships are carried in the inheritance Cables mentioned earlier. They include - restriction (of filler description and number); e.g.</Paragraph> <Paragraph position="5"> that a particular kind of COMPANY will have exactly three officers, all ot whom must be over ~5; this is a relationship between RoleSets, in which the more restricted RoleSet has all of the properties of the one it restricts, with its own local restrictions added conjunctively; - differentiation (of a Role into subRoles); e.g.</Paragraph> <Paragraph position="6"> differentiating the officers of a COMPANY into president, vice-president, etc.; this is also a relationship between two RoleSets carrying inheritance -- the more specific Roles inherit all properties of the parent Role except for the number restriction; - particularization (of a RoleSet for an Individual Concept); e.g. the officers of BBN are all COLLEGE-GRADUATEs; - satisfaction (binding of a particular filler description into a particular Role in an Individual Concept); e.g. the president of BBN is STEVE-LEW: this iS the relationship between an IRole and its parent RoleSet.</Paragraph> <Paragraph position="7"> Figure 2 illustrates the use of Cables and the structure t The network is a partial ordering with a topmost element -- the Concept of an INDIVIDUAL -- below which all other Concepts appear. There is no &quot;least&quot; element in the net, whose fringe is composed of Individual Concepts not related to each other.</Paragraph> <Paragraph position="8"> e, This inheritance implies inter alia that, if STATE is a subConcept of ATN-CONSTITUENT, then any particular state is by definition also an ATN constituent.</Paragraph> <Paragraph position="9"> * ee These limitations on the fom of particular fillers are called &quot;Value Restrictions&quot; (V/R's). If more than one V/R is applicable at a given Role, the restrictions are taken conjunctively.</Paragraph> <Paragraph position="10"> * ,ae Names are not used by the system in any way. They are merely conveniences for the user.</Paragraph> <Paragraph position="11"> ,mess In the text that follow, Roles will be indicated as underlined names and Concepts will be indicated by all upper case expressions.</Paragraph> <Paragraph position="12"> of Concepts in a piece of the KLONE taxonC/fay for the ATN grammar, In this figure, Concepts are presented as ellipses (Individual Concepts are shaded), Roles as small squares (IRoles are filled in), and Cables as double-lined arrovJ. The most general Concept, ATN-CONSTITUENT, has two subConcepts -- STATE and ARC. These each inherit the general properties of ATN constituents, namely, each is known to have a displayForm associated with it. The subnetwork below ARC expresses the classification of the various types of arcs in the ATN and how their conceptual structures vary. For example, a CONNECTING-ARC has a nextState (the state in which the transition leaves the parsing process), while for POP-ARCs the term is not meaningful (i.e. there is no nextState Role). Links that connect the Roles of more specific Concepts with corresponding Roles in their parent Concepts are considered to travel through the appropriate Cables. Finally, the structure of an Individual Concept is illustrated by CATARC#0117. Each IRole expresses the filling of a Role inherited from the hierarchy above -- because CATARC#0117 is a CAT-ARC, it has a category; because it is also a CONNECTING-ARC, it has a nextState, etc.</Paragraph> <Paragraph position="13"> The structure of a Concept is completed by its set of Structural Descriptions (SD's). These express how the Roles of the Concept interrelate via the use of parameterized versions (&quot;ParalndividJals&quot;) of other Concepts in the network to describe quantified relations between the ultimate fillers of the Concept's Roles.</Paragraph> <Paragraph position="14"> The quantification is expressed in terms of set mappings between the RoleSet3 of a C~ncept, thereby quantifying over their sets of fillers. In addition to quantified relations between potential R~le fi\]lers, simple relations like subset and get equality can be expressed with a special kind of SD ~:alled a &quot;RoleValueMap&quot; (e.g. the relation that &quot;the object of the precondition of a SEE is the same as the object ~f its effect&quot;). SD's are inherited through cable~ and are particularized in a manner similar to that of Roles.</Paragraph> <Paragraph position="15"> There is one important feature of KLONE that I would like to point out, although it is not yet used in the natural language system. The language carefully distinguishes between purely descriptional structure and assertions about coreference, existence, etc. All of the structure mentioned above (Concepts, Roles, SD's and Cables) is definitional. A separate construct called a Nexus is a LJsed as a locus of coreference for Individual Concepts. One expresses coreference of description relative t~ a Context by placing a Nexus in that Context and attaching to it Individual Concepts considered to be coreferential. AI\] assertions are made relative to a Context, and thus do not affect the (descriptive) taxonomy of' generic knowledge. We anticipate that Nexuses will be important in reasoning about particulars, answering questions (especially in deciding the appropriate form for an answer), and resolving anaphoric expressions, and that Contexts will be of use in reasoning about hypotheticals, beliefs, and wants.</Paragraph> <Paragraph position="16"> The final feature of KLONE relevant to our particular application is the ahility to attach procedures and data to structures in the network. The attached procedure mechanism is implemented in a very general way. Procedures are attached to k'LONE entities by &quot;interpretive hooks&quot; (ihooks), which specify the set of situations in which they are to be triggered. An interpreter function operating on a KLONE entity causes the invocation of all procedures inherited by or directly attached to that entity by thooks whose situations match the intent of that f.~nction. Situations include things like &quot;Individuate&quot;, &quot;Modify&quot;, &quot;Create&quot;, &quot;Remove&quot;, etc. In addition to a general situation, an ihook specifies when in the executinn of the interpreter function it is to be invoked (PRE-, POST-, or WHEN-).</Paragraph> </Section> <Section position="4" start_page="34" end_page="36" type="metho"> <SectionTitle> 3. USE OF KLONE IN THE NATURAL LANGUAGE SYSTEM </SectionTitle> <Paragraph position="0"> The previous section described the features of KLONE in general terms. Here we illustrate how they facilitate the performance of our natural language system. (Figure I above sketched the places within the system of the variou~ KLONE knowledge bases discussed here.) We will discuss the use of a syntactic taxonomy to constrain parsing and index semantic interpretation rules, and structures used in the syntactic/discourse interface to express the literal semantic content of an utterance.</Paragraph> <Paragraph position="1"> The parser uses KLONE to describe potential syntactic structures. A taxonomy of syntactic constituent descriptions, with C~ncepts like PHRASE, NOUN-PHRASE, LOCATION-PP, and PERSON-WORD, is used to express how phrases are built from their constituents. The taxonomy also serves as a discrimination net, allowing common features of constituent types to be expressed in a single place, and distinguishing features to cause branching into separate subnets.</Paragraph> <Paragraph position="2"> Two benefits accrue from this organization of knowledge.</Paragraph> <Paragraph position="3"> First, shallow semantic constraints are expressed in the Roles and SD's of Concepts like LOCATION-PP. For example, the prepObject )f a LOCATION-PP must be a PLACE-NOUN. A description of &quot;on AI&quot; (as in &quot;book on AI&quot;) as a LOCATION-PP c~Id not be constructed since AI does not satisfy the value restriction for the head role. Such constraints help rule out mislead in 8 parse paths, in the manner ~f a 3emantic grammar \[4\], by refusing to construct semantically anomalous constituent descriptions. In conj~..tion with the general (ATN) grammar of English, this is a powerful guidance mechanism which helps parsing proceed close to deterministically \[2).</Paragraph> <Paragraph position="4"> Second, the syntactic taxonomy serves as a structure on which to hang semantic projection rules. Since the taxonomy is an inheritance structure, the description of a given syntactic constituent inherits all semantic interpretation rules appropriate for each of the more general constituent types that it specializes, and can have its own special-purpose rules as well. In the example above, simply by virtue of its placement in the taxonomy, the Concept for &quot;on AI&quot; would inherit rules relevant to PP's in general and to SUBJECT-PP's in particular, but not those appropriate to LOCATION-PP's.</Paragraph> <Paragraph position="5"> Interpretation per se is achieved using the attached procedure facility, with semantic projection rules expressed as functions attached to Roles of the syntactic Concepts. The functions specify how to translate pieces of syntactic structure into &quot;deeper&quot; Concepts and Roles. For example, the subject of a SHOW-PHRASE might map into the a~ent of a DISPLAY action.</Paragraph> <Paragraph position="6"> The mapping rules are triggered automatically by the KLONE interpreter. This is facilitated by the interpreter's &quot;pushing down&quot; a Concept to the most specific place it can be considered to belong in the taxonomy (using only &quot;analytic&quot;, definitional constraints). Figure 3 illustrates schematically the way a Concept can descend to the most specific level implied by its internal description. The Concept being added to the network is an NP whose head is &quot;ARC&quot; and whose modifier is &quot;PUSH&quot; (NP@OO23). It is initially considered a direct (Generic) subConoept of the Concept for its basic syntactic type (NP). Its Role structure, however, implies that it in fact belongs in a more restricted subclass of NP's, that is, TYPED-ARC-NP (an NP whose head is an ARC-NOUN and whose modifier is an ARC-TYPE-WORD). The interpreter, on the basis of only definitional constraints expressed in the network, places the new Concept below its &quot;most specific subsumer&quot; -- the proper place for it in the taxonomy. The process proceeds incrementally, with each new piece of the constituent possibly causing further descent. In this case, NP@O023 would initially only have its head Role specified, and on that basis, it would be placed under ARC-NP (which is &quot;an NP whose head is an ARC-NOUN&quot;). Then the parser would add the modifier specification, causing the Concept's descent to the resting place shown in the right half of Figure 3. When the constituent whose description is being added to the network is &quot;popped&quot; in the parser, its IOL.ONE descriptiom is indtvidueted -- causing the invocation of all &quot;WHEN-Individuated&quot; attached procedures inherited through superconcept Cables. These procedures cause an interpretation for the constituent to be built on the basis of the interpretations of component parts of the syntactic description.</Paragraph> <Paragraph position="7"> This IAteral semantic interpretation of a phrase -- also a KLONE structure -- is the &quot;input&quot; to the discourse component. An important element of this interface between the syntactic processor and the discourse component is that the parser/interpreter commits itself only to information explicitly present In the input phrase, and leaves all inference about quantifier scope, etc. to the discourse expert. Two kinds of representational structures support this. The Concept O3\[T (for &quot;determined set&quot;) is used extensively to capture sets implicit in noun phrases and clauses. ~EYs use the inherent multiplicity of RoleSets to group together several entities under a single Concept, and associate determiners (deCinlte/indeflnite, quantifiers, etc.) with such a set of entities. A DSET can express the characteristics of a set of entities without enumerating them explicitly, or even indicating how many members the set is expected to have. RoleYalueMaps a11ow ,constraints between DSETs to be expressed in a general way -- a RoleValueMsp expresses a subset or equallty relation between two RoleSets. Such relations can be constructed without knowlng in advance the csrdinallty of the sets or any of their members.</Paragraph> <Paragraph position="8"> Figure 4 illustrates the use of these structures to express the intent of the sentence, &quot;Show me states S/NP, S/AUX, and S/DCL &quot;e. DSET#O035 represents the interpretation of the noun phrase, &quot;the states ~/HP, S/AUX, and ~/DCL&quot;. The generic DSET Concept has two Roles, mamb~r and determiner. The member Role can be filled multiply, and therein lies the &quot;settedness&quot; of the \[\]SET. \[~ET#O035 has a particularized version of the * RoleSets in this figure are drawn as squares with circles around them. RoleSets with filled-in circles are a special kind of particularized RoleSet that can occur only in Individual Concepts. The RoleValueMap is pictured as a diamond.</Paragraph> <Paragraph position="9"> &quot;Show me states S/NP, S/AUX, and S/DCL&quot;.</Paragraph> <Paragraph position="10"> member Role: Role R1 represents the set oC three states mentioned in the noun phrase, as a group. Thus, the Value Restriction of R1, STATE, applies to each member.</Paragraph> <Paragraph position="11"> The three 1Roles of DSETIO035, connected by &quot;Satisfies&quot; links to the particularized member RoleSat, indicate that the particular states are the members of the set e.</Paragraph> <Paragraph position="12"> The other DSET in the figure, r~ETmO037, represents the clause-level structure of the sentence. The clause has been interpreted into something like &quot;the user has performed what looks on the surface to be a request for the system to show the user some set oC states&quot;. This captures several kinds of indeterminacy: (1) that the sentence may only be a request at the surface level (&quot;Don't you know that pl&s can't fly?&quot; looks like a request to inform), (2) that there is more than one way to effect a &quot;show n (&quot;show n could mean redraw the entire display, change it slightly to include a new object, or simply highlight an existing one), (3) that it is not clear how many operations are actually being requested (showir~ three objects could take one, two, or three actions). TherefOre, the interpretation uses Generic Concepts to describe the kind of events appearing in the surface form of the sentence and makes no ccmmitment to the number of them requested. The only commitment to &quot;quantiflcetionel&quot; information ls expressed by the Role-ValueMap. Its two pointers, X (pointin& to the member Role of nSET#O035) and yea (pointing to the object of * The Value Restriction. STATE, is redundant here, since the members of this particular set were explicitly specified (and are known to be states). In other cases, the information is more useful. For example, no 1Roles would be constructed by the parser if the sentence were &quot;Are there three states?&quot;; only one would be constructed in &quot;Show me state S/NP and its two nearest neighbors&quot;. On the other hand, no Value Restriction would be directly present on Role R1 if the noun phrase were just &quot;S/NP. S/AUX, and S/DCL&quot;.</Paragraph> <Paragraph position="13"> ee Y= is a chained pointer acing first through the member Role of ~SET~O037, then throu6h the act Role of S-RPSQUEST~O038, and finally to the o~-ent Role of SHOWeO035. It is considered to refer to the set of ZRoles expressing the objects of all SHOW events ultimately S-REQUESTed, when it is determined exactly how many there are to be (i.e. when the 1Roles of the requested act), indicate that the ultimate set of things to be shown, no matter how many particular SHOW events take place, must be the same as the set of members in the noun phrase DSET (namely, the three states).</Paragraph> <Paragraph position="14"> As mentioned, semantic interpretation invokes the discourse expert, This program looks to a plan that it is hypothesizing its user to be following in order to interpret indirect speech acts. Following \[1\], the speech acts REQUEST, INFORM, INFORMREF, and INFORMIF are defined as producing certain effects by means of the heater's recognition of the speaker's intention to produce these effects. Indirect speech act recognition proceeds by inferring what the user wants the system to think is his/her plan. Plan-recognition involves making inferences of the form, &quot;the user did this action in order to produce that effect, which s/he wanted to enable him/her to do this (next) action&quot;.</Paragraph> <Paragraph position="15"> Making inferences at the level of &quot;intended plan recognition&quot; is begun by analyzing the user's utterance as a &quot;surface&quot; speech act (SURFACE-REQUEST or SURFACE-INFORM) indicating what the utterance &quot;looks like&quot;. By performing plan-recognition inferences whose :plausibility is ascertained by using mutual beliefs, the system can, for instance, reason that what looked to be an INFORM of the user's goal is actually a REQUEST to include some portion of the ATN into the display. Thus, the second clause of the utterance, &quot;No; I want to be able to see S/AUX,&quot; is analyzed as a REQUEST to INCLUDE S/AUX by the following chain of plan-recognition inferences: The system believes (1) the user has performed a SURFACE-INFORM of his/her goal; thus (2) the user intends for the system to believe that the user wants to be able to see S/AUX. Since this requires that S/AUX be visible, (3) the user intends for the system to believe that the user wants the system to plan an action to make S/AUX visible. Because the &quot;No&quot; leads to an expectation that the user might want to modify the display, the system plans to INCLUDE S/AUX in the existing display, rather than DISPLAY S/AUX alone.</Paragraph> <Paragraph position="16"> (q) Hence, the user intends for the system to believe that user wants the system to INCLUDE S/AUX.</Paragraph> <Paragraph position="17"> (5) The user has performed a REQUEST to INCLUDE.</Paragraph> <Paragraph position="18"> The system responds by planning that action.</Paragraph> <Paragraph position="19"> In addition to using Contexts to hold descriptions of beliefs and wants, the plan-recognition process makes extensive use of RoleValueMaps and ~SETs (see Figure 4).</Paragraph> <Paragraph position="20"> Plan-recognition inferences proceed using Just the clause-level structur~ and pay no attention to the particulars of the noun phrase interpretations. The system creates new BSETs for intermediate sets and equates them to previous ones by RoleValueMaps, as, for example, when it decides to do a SHOW whose object is to be the same as whatever was to be visible. At the end of plan-recognltion the system may need to trace through the constructed RoleValuaMaps to find all sets equivalent to a given one. For instance, when it determines that it needs to know which set of things to display, highlight, or include, it treats the equated RoleValueMaps as a set of rewrite rules, traces back to the original noun phrase DSET, and then tries to finds the referent of that DSET a.</Paragraph> <Paragraph position="21"> DSET#OO37 are finally specified). Thus, if there are ultimately two SHOWs, one of one state and the other of two, the Y pointer implicitly refers to the set of all three states shown.</Paragraph> <Paragraph position="22"> e The system only finds referents when necessary. This depends on the user's speech acts and the system's needs in understanding and complying vith them. Thus, it is Finally, not only are parse structures and semantic interpretations represented in KLONE, but the data base -- the ATN being discussed -- is as well (see Figure 2 above). Further, descriptions of how to display the ATN, and general descriptions of coordinate mappings and other display information are represented too. Commands to the display expert are expressed as Concepts involving actions like SHOW, CENTER, etc. whose &quot;arguments&quot; are descriptions of desired shapes, etc. Derivations of particular display forms from generic descriptions, or from mapping changes, are carried out by the attached procedure mechanism. Finally, once the particular shapes are decided upon, drawing is achieved by invoking &quot;how to draw&quot; procedures attached to display form Concepts. Once again, the taxone~mic nature of the structured inheritance net allows domain structure to be expressed in a natural and useful way.</Paragraph> </Section> class="xml-element"></Paper>