File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/abstr/92/c92-3137_abstr.xml
Size: 23,469 bytes
Last Modified: 2025-10-06 13:47:28
<?xml version="1.0" standalone="yes"?> <Paper uid="C92-3137"> <Title>ATTITUDE EMERGENCE - AN EFFECTIVE INTERPRETATION SCHEME FOR PERSUASIVE DISCOURSE</Title> <Section position="1" start_page="0" end_page="0" type="abstr"> <SectionTitle> ATTITUDE EMERGENCE - AN EFFECTIVE INTERPRETATION SCHEME FOR PERSUASIVE DISCOURSE </SectionTitle> <Paragraph position="0"/> </Section> <Section position="2" start_page="0" end_page="0" type="abstr"> <SectionTitle> ABSTRACT </SectionTitle> <Paragraph position="0"> Previous approaches have used a reasoning mechanism called belief percolation to determine the actual speech intent of the speaker (e.g., (Wilks and Bien 1979)).</Paragraph> <Paragraph position="1"> In this paper, a similar mechanism, called attitude emergence, is proposed as a mechanism for inferring a speaker's attitude toward the propositions in a persuasive discourse. It is sbown that in order to adequately interpret the statements in advertisements, associations of relevant semantic information, through br*dglug inferences, are to be percolated up through attitude model contexts to enhance and calibrate the interpretation of statements. A system called BUYER is being implemented to recognize speech intents through attitude emergence in the domain of food advertisements taken from Reader's Digest. An example of BUYER's processing is also presented in the paper.</Paragraph> <Paragraph position="2"> Introduction One of the most significant characteristics of persuasive discourse is that it involves the expression of people's beliefs, desires, preferences, etc. These beliefs, desires, and preferences constitute a model of mental a~titudes (or, an attitude model) which characterizes the mind of the speaker engaging in a persuasiw', discourse. An attitude model is important for figuring out what the speaker means; i.e., his speech iutent. More specifically, often when the speaker expresses his beliefs, desires or preferences in persuasive discourse, he means to induce a reaction, in the forms of comparable mental attitudes, on the part of a hearer. For example, an expression of the speaker's belief can be intended to induce such an belief in the hearer. However, in general, inferring the speech intent through attitudc model reasoning is complex. For instance, in our domain of persuasive discourse - advertisements - a major statement may be followed by minor statements, as demonstrated in the following passage.</Paragraph> <Paragraph position="3"> (1.1) Nabisco is great.</Paragraph> <Paragraph position="4"> (1.2) It is nutritious whole wheat, (1.3) low in cholesterol and saturated fat, (1.4} haz plenty of fiber and vitamin.</Paragraph> <Paragraph position="5"> Arranged in this fashion, tbe expression of the speaker's preference in (1.1) - Nabisco is great comes to be supported by statements (1.2) through (1.4).</Paragraph> <Paragraph position="6"> This makes tile acceptance of (1.1) as the heater's own much more compelling, intending to induce in the hearer the same preference expressed in (1.1). Although tills explanation sounds intuitively simple and correct, the question remains: how do statements such as (1.2) to (1.4), which are oil the surface~ &quot;disjoint&quot; expressions of the speaker's belief, come to have a real psychological impact on the hearer? Some sort of reasoning must have been employed to bridge them with (1.1) and to produce the persuasive effects.</Paragraph> <Paragraph position="7"> Previously, model-based reasoning has been investigate(\[ for many tasks, such as belief ascription and metaphor understanding (Ballim et al. 1991), logical reasoning (Dinsmore 1987), and natural language understanding in general (Faueonnier 1985). One previous approach to attitude model reasoning concentrates exactly on issues of inferring speech intents. As discussed concisely in (Wilks and Bien 1979), the statement &quot;Frank is coming tomorrow&quot; can be interpreted in many ways, depending on the context. For instance, if the hearer believes that the speaker believes that Frank is hostile to the hearer, and the hearer has uo personal knowledge about Frank, then this statement might be interpreted as a threat to the hearer.</Paragraph> <Paragraph position="8"> To account for different possible interpretations of statements like these, Wilks el al. propose an altitude percolatiou mechanism, in which a statement is pushed down to the frame of the system's belief to create the attitude context - the system's belief of the speaker's belief. Since in this more specific context, the following statements are simultaneously present I : Frank comes tomorrow and Frank is hostile to the system. Thus, tile system can infer that Frank may harm the system, which in turn, allows the system to interpret the original statement ms a threat to itself.</Paragraph> <Paragraph position="9"> In our domain of advertisement persuasive disconrse~ much fewer facts arc privately known compared to what are mutually known 2. Therefore, it is argued ~If tile system has personM knowledge otherwise about Frank, then this may affect the reasoning proces,q.</Paragraph> <Paragraph position="10"> to adhere to fashionable viewpoints.</Paragraph> <Paragraph position="11"> AC1-ES DE COLING-92, NANTES, 23-28 AOt~r 1992 9 1 1 PROC. OF COLING-92. NANTES, Auo. 23-28. 1992 that the push dowa operation, which investigates into the personal knowledge about one another, will be limited. Instead, in this paper, a more relevant mecha.</Paragraph> <Paragraph position="12"> nism, called attitude emergence, is investigated. It is a more conlprehensive treatmeTit of attitude lnodels~ nti-lizing mutually known semantic and world knowledge to convey speech intent, a.s observed in the interpretation of our earlier example. More specitically, attitude models for statements are eonstnmted, aud a~qsimilated through bridging inferences based on mntual knowledge. The semantic association resulting flora assinfilation then gets percolated up along attitude model contexts so that the proper interpretation of speech intent is recognized. This attitude emergence mechanism is being implemented in a system called BUYEI{~, which understands food advertisements taken fl'om lgeader's Digest. A corpus of 129 advertis(mmnts has been collected. Part of the ads are used R)r constructing tile system, while the rest of them are used to verify the generality of BUYI';ll.'s knowledge base. In this papm, we present an examl)le of 1111Yl,2d, processing one nf these ads.</Paragraph> <Paragraph position="13"> The basic framework of atttil;ude emergence As observed above, the recognition of speech intent in persuasive discourse is rather comj)lex. Various sorts of mutual knowledge ntay be employed in bridging the statements and bringing out the speech intents. In (Wn and Lytinen 1991), we proposed a three.step procedure of attitude emergence: Step 1: Construct tile initial altitude model (or A-model). Step 2: Assimilate the successive statements cnherently into one A-model (if possible) anti recognize the semantic a.qsociation Imtween tile models.</Paragraph> <Paragraph position="14"> Step 3: Percolate upwards &tOltg A-model context to effect attitude ehauge due to the semantic association recognized in Step 2.</Paragraph> <Paragraph position="15"> A-models are rceursive structures of infi)rmation with attitude contexts, each layer el Milch consists of an agent and an attitude he holds toward the deeper hwel information. A simple passag;e is analyzed ill (Wu and I,ytinen 1991), (2.1) Peter loves antique cars.</Paragraph> <Paragraph position="16"> (2.2) His favorite model is tile 1887 I)uryca.</Paragraph> <Paragraph position="17"> Tire evolution nf A-.models through this three-step procedure can be summarized as follows: At tile end of Step l (see Fig. 1), a,m A-model is coastructed consisting of an attitude context (Report i;pcak(~r ...), which eml)eds another attitude context * (Love Pe ter ...), which contains ~,.*l object antique.ea.k's. Note that, these linear R)rmula m'c just, short hands ik)r ulodels. We take thai, ill implmnentatinn, models are ibrmula plus indexing ;rod encapsulation, as tile boxes ill Fig. I is intended to capture: the indice,~ on agents are called S-boxes and on attitude~q A-boxes.</Paragraph> <Paragraph position="18"> l';ach attitude context creates it'~ oegn environnient which involves only entities with comparable attitude ,qtatus. In turn, simulative reasoning call produce resuits app\]icable to the attitude context where it takes place, and may sometimes affect related contexts, e.g., causing re-Evaluation of the attitude in the embedding attitude contexts. Thus, ill Step 2, while statement (2.2) is being assimilated with statement (2.1), some reasoning takes place marked as (A), (B) and tO) in Fig. 2.</Paragraph> <Paragraph position="19"> At point (A), an IS-A semantic relation is recognized between &quot;antique_cars&quot; and &quot;1887_Duryea&quot; in the semantic space whicb, ,as depicted as orthogonal to attitude space in Fig. 2, stores attitude-independent semantic information. Ill order to trigger emergence of more attitude related information, the recognition of the LqoA relation is percolated up along layers of e~ttit.ude contexts to reach tile (Report Speaker ...) con- text, where (B) and (C) occur. At points (B) and (C), ~'~ta~,emeuts (2.2) and (2.1) are found to be related; in particular, tile (Report Speaker ...) context of (2.2) is calibrated to be &quot;evidential&quot; (to (2.1)), wbile, that of (2.1) to be &quot;snl)l)orted&quot; (by (2.2)). &quot;lhat (B) and (C) occur is due to tile following world knowledge (WKI): $I.</Paragraph> <Paragraph position="20"> If the speaker provides more detailed information about a clMm (Y) in a statement (X) Then Y is &quot;supported&quot; by &quot;evidence&quot; X and becomes more believable As demonstrated by (A) - (C), semantic association emerges from embedded attitude contexts to calibrate the attitude in higher contexts - i.e., how attitude emergence happens.</Paragraph> <Paragraph position="21"> In this simple example, the attitude emergence mechanism has involved, nonetheless, a large amount of knowledge. This knowledge is briefly reviewed below. Yet, more sophisticated reasoning is required to process real world ads (see below). First, there is knowledge concerning A-model construction based on the following mapping rules: (1) Sentence types to Aboxes, e.g, a declarative sentence type maps into a belief; (2) Attitude verbs to A-boxes, e.g., &quot;loves&quot; into a preference; (3) Evaluative predicates to A-boxes, e.g., &quot;favorite&quot; into a preference; (4) Adverbs to A-models, e.g., &quot;certainly&quot; into a belief; (5) Cue phrases to Amodels, &quot;it is time that&quot; into a desire (recommendation). null Secondly, there is knowledge concerning A-model assimilation and bridging inferences. For example, in passage (2), the expression &quot;his favorite model&quot; is resolved through the following three separate bridging inference steps: 1. That &quot;his&quot; refers to tldngs pertinent to Peter. 2. That &quot;favorite&quot; is an evMuative predicate translated into a &quot;prefer&quot; attitude box.</Paragraph> <Paragraph position="22"> 3. That cars have models.</Paragraph> <Paragraph position="23"> For step (1), a focusing mechanisnr is required to locate the S-box - Peter, since a pronominal expression usually (but not always) refers to some object in the focus. For step (2), the A-model helps to guide the resolution filrther into the most relevant A-box; in other words, an A-model itself carl serve as a marker to find the most relevant A-model earlier in tile discourse. For step (3), a basic semantic association occurs to recognize pos~ sitde semantic relations. In summary, the resolution of the expression &quot;his favorite model,&quot; and similarly for all other expressions, is achieved by bridging inferences which synthesize many knowledge sources, including focusing, A-models themselves, and semantic association.</Paragraph> <Paragraph position="24"> A real world example from BUYER.</Paragraph> <Paragraph position="25"> In this section, a real world advertisement is presented to demonstrate the application of attitude emergence in processing persuasive discourse. As discussed above, a simple version of A-model construction and assimilation has to be extended to include more general world knowledge. The following ad, which BUYER has processed, demonstrates this.</Paragraph> <Paragraph position="26"> The Folgers ad.</Paragraph> <Paragraph position="27"> SI. l.s your decaffeinated ~s dark as ours? $2. Star~ with one teaspoon of both.</Paragraph> <Paragraph position="28"> $3. Hut just bec&tlse the anmunts are cquaJ doesn'~ t:lean the results w~ll he.</Paragraph> <Paragraph position="29"> $4. Mount,~t~ Grown ~blgers dark, sparkling Crystals are the dilt~reJtce.</Paragraph> <Paragraph position="30"> S6. So dark a3~d rich, shouldn't you switch? In tile process of understanding this ad, tim system has to tigure out many tbings, for example: ls S1 a question or a prompt fur suggesting an action (for tile hearer to perform)? Is $2, given tile proper interpretation of $1, an order or a recommendation; Does $3 affect the status of tile attii.ude expressed in 817 and so on. In order to answer these questions concerning speech intcuts, tile attltude model of each statement h~ to go through more involved calibration and enhancement tban the simple version presented in the previous section. First, the reading of statement 5'I is ambiguous. It could mean that the speaker wants the hearer to inform him as to whetber the bearer's decaffeinated is as dark a~s ours. Or, it can have another reading: the speaker wants the hearer to know whether the hearer's decaffeinatcd is ms dark as ours.</Paragraph> <Paragraph position="31"> The latter reading is inferred by the following world knowledge (WK2)~: If the advertiser already knows everything about his products (which is reasonable to assume), Then a questio~ concerning the product is actually all intention to iu.\[orm.</Paragraph> <Paragraph position="32"> The two possible attitude models for the two readings of $1 are depicted in Fig. 3. Note that the two variables el and el' stand for tile different events specified by (Inform-whether Hearer ...) and (Know-whether Hearer ...), respectively. The two events are indexed by their event types, as demonstrated by the ovals in the boxes in Fig. 3. Then, when $2 is processed, from its sentence type (imperative), it is inferred that its atti- null association begins to emerge when the events e2, specified as &quot;start witb one teaspoon of both,&quot; and el or el' (see Fig. 3) are being assimilated. The coherence reasoning component of BUYER. (Wu and Lytinen 1990) is able to recognize the following Enable coherence relation: null That tile hearer starts with one temspoon of both kinds of coffee can enable that hc knows which coffee is better. null That is, the action e2suggested in $2 is an e~:perirnent to find out something. The choice between el and el ~ is now clear, due to the following world knowledge (WE3): If an agent has a goal to find out something about X, Then he can perform an experiment with X.</Paragraph> <Paragraph position="33"> Since eL' - (Know-whetl)er ttearer ...) -- is acquired as a goal for the hearer according to Reading 2, el' and hence, Reading 2 is determined as the speech intent.</Paragraph> <Paragraph position="34"> Then, when $3 is processed, it logically means: It is )lot the case that Pl implies Q1.</Paragraph> <Paragraph position="35"> where P1 stands for - the amounts are equal; Ql the results are equal. The cormnon sense logical reasoning employed in constructing the attitude model of $3 proceeds ms follows: assume P1 is a fact/observation, should we assmne QI or ~ Ql according PFI? If Q1 is assumed, then it produces: P1 impliesQt, which wonkl be contradictory. So, the only alternative is to choose Q1. The result is then the attitude model shown in Fig. 4. Following attitude percolation, the attitude model of Fig. 4 is pushed down into the one in Fig. 3 for t?~eading 2, creating the attitude context of (Want Speaker (Believe Hearer ...)). At this point, BUYER is able to reason that Pl - the amounts are equal - is a fact, by resolving &quot;the amounts&quot; to &quot;the amounts of coffee used in e27' Given that the conditional PF1 has a satisfying antecedent, the conseqnent ~ QI (or &quot;the results are not eqnal&quot;) is derived as a fact. Note that, similar to how &quot;tile amounts&quot; is resolved, &quot;the results&quot; would be resolved ms &quot;the results in the experiments with the two coffees.&quot; Next, when $4 is processed, by pushing down and resolving &quot;the difference&quot; to &quot;the difference between the resnlts in the experimellt,&quot; it is recognized tl~at $4 is supl)orting the implicit speech intent made in $3 -. 53: The speaker claims that the results of Y ar~florent. , $5: Tile speaker molivates the use S~: t~Ot feooxpepa0kOr~na~ to~eKrl~0~. ~ fcofrFl~ cl~mo0ffeo, dnawing =ppert $4: The apeaker gives evidence supporting the claim.</Paragraph> <Paragraph position="36"> $1 : The speaker wants the hearer to Know X.</Paragraph> <Paragraph position="37"> their attitude models.</Paragraph> <Paragraph position="38"> the speaker wants the hearer to believe that tbe results of the experiments are not equal. This is due to the following world knowledge (WK4): If the speaker gives the physical cause of a consequence statement, Then the consequence statement becomes more believable. null Thus, the intended belief that tim results are not equal is further enhanced. Finally, $5, like 83, is not a literal conditional statement. It logically means: P~ implies should?(-, Q2) where P7 is that Folgers is so dark and rich and Q2, switch to Folgers. However, the intended meaning is, obviously - switch to Folgers. The derivation hinges on the following &quot;dogma&quot; about &quot;abnormal vs. norreal states&quot;: (1) Unfamiliar external states may be abnormal; (2) If unknown external states are indeed abnormal, people query about them using &quot;should X?'; (3) Abnormal states are to be corrected. Due to (1) (3), the intended meaning can be derived, since ~ Q2 is abnormal and to be corrected; in addition, Pz is also a fact. Fig. 5 summarizes tim speech intents reasoned by attitude emergence for the Folgers ad: Related work Work on belief percolation ((Wilks and Bien 1979), (Wilk~ and Bien 1983), (Wilks and Ballim 1987), (Hallira et al. 1991)) has strongly inspired our work. flowever, n~lost of this work concentrates on one single operation of attitude/belief percolation .- the &quot;push down&quot; operation. Although this operation is important for investigative reasoning and assimilating attitude models, effects on attitude models themselves due to attitude percolation are more important for our domain of persnasive disconrse. Thus, attitude emergence stands as a more relevant mechanism to reason about persuasive speech intent. Moreover, the proposed thretr-step pr~ cedure for computing attitude emergence proves to be a general framework for recognizing speech intents.</Paragraph> <Paragraph position="39"> The mapping rules proposed in (Hinkelman and Allen 1989), as well as those in (Gerlach and Sprenger 1988), are similar to the attitude model construction rules, while deeper reasoning may underlie some of AclT.s t)E COL1NG-92, NA/VIq!S, 23-28 AOt';r 1992 9 l 4 I'ROC. Ol: COLING-92. NANTES. AUG. 23-28, 1992 their rules, e.g., the interpretation of should?('~Q~) as Q2, as we have done to ours. Ill (Hiukelman and Allen 1989), they also proposed plan-recognition to further identify the speech intent. However, we believe that in persuasive discourse, identifying speech intent through A-models can be done more locally using coherence and bridging inferences. In this sense, our approach is closer to those proposed in (Cohen 1987) and (Mann and Thompson 1988), while (Cohen 1987) considered only support relations and (Mann and Thompson 1988) remained as a descriptive theory, and both did not consider A-models as essential lot inferring speech intent.</Paragraph> <Paragraph position="40"> A-models also arc somewhat similar to model-theoretical approaches to semantics. While theories of the more formal kind -- e.g, Discourse Representalional Theory (DRT) (Kamps 1981) -- and of the nrore cognitive - e.g., Mental Spaces (Fauconnier 1985) - emphasize the fundamental issues of reference and presupposition, attitude emergence sees application of model reasoning to recognize speech intents. These also demonstrate that mental attitudes serve as only one (though important) way to organize information.</Paragraph> <Paragraph position="41"> There are other ways information should be organized.</Paragraph> <Paragraph position="42"> I,br example, our formulation of conditionals (for $3) is organized not according to attitudes, but principles studied in DRT and mental spaces.</Paragraph> <Paragraph position="43"> Conclusion and future work In this paper, a mechanism called attitude emergence is discussed. The basic framework of attitude emergence, which consists of attitude model construction, assimilation, and effects propagation, was first proposed in (Wu and Lytinen 1991) with limited operations. The mechanism is filrther inrproved aud extended to recognize more indirect speech in persuasive discourse, by adding other common sense and logical reasoning. The generality of attitude emergence is demonstrated by a real world ad which BUYER has proce~ed. BUYER is the computer implementation of attitude emergence and is implentented as a rule-based system which currently has 348 rules organized in 1O problem-solving modules. These problem-solving modules are organized in a way that rules are both forwardand backward-chained, depending tim deductive and abduetive nature of the rules, respectively, and allows efficient backtracking.</Paragraph> <Paragraph position="44"> One future work of attitude emergence lies on tile further systematization on the dynamics of attitude models. Only the force aspect of a statement is present in the current formulation. A tidier formulation of attitude dynamics should include both force and counter force, reflecting the enforcement and the resistance toward an expressed attitude. For example, in Folgers ad, the &quot;counter force&quot; induced by $2 -- the inertia of the hearer not to be told what to do - can he overcorned by the (attracting) force expressed in $1 - the speaker wants the hearer to know something important - and the force due to the common knowledge that the experiment urged ill $2 can enable the attainment of such knowledge. Relating statements to psychological forces arc steps toward explaining the psychological reality of persuasive force and pressure. Along this line, it is found that the work on &quot;force dynamics&quot; proposed in (Tahny 1988) is highly relevant. We are currently looking into the relation between the two.</Paragraph> </Section> class="xml-element"></Paper>