File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/81/j81-4001_metho.xml
Size: 57,388 bytes
Last Modified: 2025-10-06 14:11:22
<?xml version="1.0" standalone="yes"?> <Paper uid="J81-4001"> <Title>Focusing for Interpretation of Pronouns I</Title> <Section position="5" start_page="0" end_page="0" type="metho"> <SectionTitle> 3. Focus for Pronoun Interpretation </SectionTitle> <Paragraph position="0"> A simple discourse can be used to illustrate how pronouns indicate what the speaker is talking about in the discourse. In the sample below, the speaker mentions two dogs and tells us something about each.</Paragraph> <Paragraph position="1"> D2-1 I have two dogs.</Paragraph> <Paragraph position="2"> 2 (The) one is a poodle; 3 the other is a cocker spaniel.</Paragraph> <Paragraph position="3"> 4 The poodle has some weird habits.</Paragraph> <Paragraph position="4"> 5 He eats plastic flowers and likes to sleep in a paper bag.</Paragraph> <Paragraph position="5"> 6 It's a real problem keeping him away from plastic flowers.</Paragraph> <Paragraph position="6"> 7 The cocker is pretty normal, 8 and he's a good watch dog.</Paragraph> <Paragraph position="7"> 9 I like having them as pets.</Paragraph> <Paragraph position="8"> The speaker uses the pronouns &quot;he&quot; and &quot;him&quot; to indicate that the poodle is the actor of eating flowers and the object of an action of keeping. The speaker mentions his second dog with &quot;the other&quot; and then uses the pronoun &quot;he&quot; only in predicate adjective and predicate nominative constructions without reference to any events. Initially the speaker focuses attention on both dogs and then turns his attention to each for a part of the discourse. The process by which the speaker uses language to indicate his focus is called the focusing process. The items in focus are those that are talked about for a part of the discourse. Items in focus can be used in two ways, as actor focus and as discourse focus. The actor focus is a discourse item that is predicated as the agent in some event, so for example, the poodle is the agent in eating flowers, while the discourse focus is, roughly speaking, an item the speaker wishes to make several predications about. 4 The focusing process, when explained from the viewpoint of a hearer, can be described as a process of tracking the speaker's loci as they change over the discourse. A hearer does not have privileged information about what is in a particular speaker's head, so the hearer must decide what the speaker is talking about on the basis of what the speaker uses as initial referring expressions and subsequent co-specifying anaphoric expressions. The hearer follows a focus and checks to see if the anaphoric expressions which the speaker uses either co-specify with the hearer's representation of that focus or specify a representation 4 This description is not a definition of discourse focus. The discourse focus is defined by the effects of several focusing algorithms; for details, see Sidner 1979.</Paragraph> <Paragraph position="9"> 220 American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 Candace L. Sidner Focusing for Interpretation of Pronouns related to it. The hearer is said to be tracking the speaker's focus because she or he can determine what is being talked about only after the speaker has said something. Focus, as it is used here, is akin to Grosz's notion \[1977\] of immediate focus.</Paragraph> <Paragraph position="10"> A process model of focusing and focus tracking consists of three distinct processors. The first chooses foci based on what the speaker initially says. The algorithm for this choice depends on many phenomena - see Sidner 1979 for details. Then an interpreter (the pronoun interpreter) uses these foci and a set of rules of pronoun interpretation (hereafter &quot;pi-rules&quot;) to interpret the anaphoric expressions in the discourse. This interpreter, like a human hearer, must keep in mind whatever other newly mentioned elements the speaker has introduced, since sometimes an anaphor may co-specify with one of those instead of the elements in focus. A third process updates the loci by decisions that depend on anaphoric interpretations chosen by the pronoun interpreter. During this last phase, the updating process moves one of the loci to a new element of the discourse, if some anaphor co-specified with that new element while no anaphor co-specified with the phrase already in focus. The three processes taken together sketch a simple model of focus tracking; the model appears to behave like its human counterpart in the way it interprets anaphors and in the instances in So far, the process chosen, they are used which it fails to &quot;understand.&quot; model looks circular. Foci are to determine how anaphors co-specify with the loci and then the co-specifiers are used to determine what's in focus. In fact, the model is not circular, but its steps are cyclic. The processor cycles through the three processes for each sentence in the discourse. This cycling differs from logical circularity because it depends on new information presented over time, the time of each sentence of the discourse. null For example, reconsider the first few sentences of D2, given previously. Initially the speaker mentions two dogs, which become the discourse focus, and then he extends the discussion of them using &quot;one...the other&quot; anaphors. The actor focus is the speaker. Using a definite noun phrase anaphor &quot;the poodle,&quot; the speaker turns his attention to the that dog, and it becomes the discourse focus and the actor focus. Using another definite noun phrase anaphor &quot;the cocker,&quot; the speaker changes the discourse focus to the cocker. The speaker's concluding sentence expands the discourse focus back to both dogs with the use of &quot;them.&quot; In Sidner 1979 a machine for choosing and updating the discourse focus and actor focus is given. The machine chooses items in the discourse to serve as &quot;expected&quot; foci after the first sentence of a discourse and uses the interpretation of pronouns as well as non-pronoun anaphors to determine whether its expected choices were correct. The machine updates the discourse and actor focus after each sentence and changes foci when the anaphoric expressions no longer co-specify with the item in focus. This simple machine tracks the foci from the hearer's point of view and shows how the hearer can recognize foci and changes of loci. In the remaining discussion, it is assumed that the focus machine can determine a discourse and an actor focus. Our attention is directed at the following concerns. How can these two foci be used to interpret discourse pronouns? What rules are used by the pronoun interpreter? How do these rules make use of the constraints on the theory of pronoun interpretation discussed earlier in this paper? The focusing theory of pronoun interpretation can be outlined as follows. At any time in the discourse after the first sentence, there are loci that are the prime candidates for co-specifying with a pronoun.</Paragraph> <Paragraph position="11"> Also available is a list of alternate candidates, called potential foci, for each focus. Unless the focus candidate is ruled oflt by certain criteria (to be discussed below), the pronoun interpreter uses it to determine the specification of the pronoun. Most of the discussion in this paper concerns the criteria that must be encoded in the rules for choosing among the foci as well as the criteria for rejecting a focus in favor of one of the potential foci.</Paragraph> <Paragraph position="12"> The proposal made here contains two implicit processing assumptions, (1) serial processing, and (2) end-of-sentence processing. By &quot;serial processing&quot;, I mean that the interpreter checks a focus as a candidate in interpreting the pronoun, and then if that focus is unacceptable, checks alternate candidates in turn. By &quot;end-of-sentence processing&quot;, I mean that pronouns are not interpreted until the entire sentence has been syntactically and semantically interpreted. Both of these criteria could be given up without undermining the focusing theory. One could envision processing in parallel by checking the foci and alternates and then determining the pronoun's specification from an ordering of all those candidates that meet the criteria of choice. To interpret pronouns before the end of the sentence, the interpreter could decide using available information and then review its choice as more of the sentence is processed. These two implicit processing assumptions have been made because they simplify the account of focus and because they reflect an implemented version of one focus system. Further research will indicate whether these assumptions are too strong - if so, the focusing theory may be re-tested under parallel and mid-sentence interpretation assumptions.</Paragraph> <Paragraph position="13"> 4. Using Focus for Pronoun Interpretation Rules The pronouns in the example discourse in the preceding section can be interpreted with a simple rule: American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 221 Candace L. Sidner Focusing for Interpretation of Pronouns RI: Choose the discourse focus as the co-specifier of the pronoun. But if the pronoun appears in the agent position of the verb case frame structure, then choose the actor focus.</Paragraph> <Paragraph position="14"> R1 is a naive formulation and fails to predict accurately over a wide range of phenomena. It can be revised to include criteria from syntax, semantics and pragmatics, as well as criteria about discourse characteristics. In the next several pages, I present criteria that make use of all four sources of knowledge and incorporate them into R1 to form a series of pi-rules; these rules make use of the discourse and actor foci, the potential loci, and the processing of the focus machine.</Paragraph> <Paragraph position="15"> Syntax, semantics and pragmatics can be included in an initial way by the modification R2: R2: If a pronoun appears in a verb case frame relation other than agent, choose the discourse focus as co-specifier unless any of the syntactic, semantic and pragmatic knowledge constraints rule out the choice.</Paragraph> <Paragraph position="16"> If the pronoun appears in agent position, choose the actor focus as co-specifier in the same way.</Paragraph> <Paragraph position="17"> Ruling out a co-specifier on the basis of syntactic and semantic constraints is accomplished by computing the various syntactic relationships and restrictions (such as Lasnik's disjoint reference rules) and by use of semantic selectional restrictions on case frame categories. How one uses general knowledge constraints is not so obvious; one wants to avoid the problems of control on inference mentioned previously.</Paragraph> <Paragraph position="18"> The focus rule above, although only a skeleton of the full rules needed, contains the basis for control of inferences. Under the method of rule R2, inference is no longer used to find a binding for the pronoun acting as a variable by forward and backward chaining. Instead inference is a constraint-checking process.</Paragraph> <Paragraph position="19"> The context up to the sentence under interpretation is integrated into memory; when a co-specifier is chosen for the pronoun, inferring serves only to find a contradiction in the database. The database will also include an interpreted form of the sentence with the pronoun, with the pronoun replaced by its specification as predicted from the phrase in focus. Only when a contradiction is found, is the suggested specification given up in favor of another choice. The loci of the discourse can be additionally helpful in database inference because only that part of the database that concerns what is in focus needs to be explored for contradictions. Some research on truth maintenance systems \[Doyle 1978, McAllester 1978\] has experimented with constraint-checking and developed algorithms for efficiently finding and undoing contradictions; however, no one has considered how to explore only certain &quot;sub-sections&quot; of a database for contradictions. On this account of inferring and pronoun interpretation, the inference machine must still infer propositions and reach contradictions. However, this method reduces the search needed to make sense of the new sentence because specific choices for the pronouns are given; when a contradiction is reached, a new choice is made rather than either blindly binding the pronoun to some other object or blindly searching for some other proposition to change, so that the contradiction is eliminated.</Paragraph> <Paragraph position="20"> When a suggested co-specifier for a pronoun must be given up, the pronoun interpreter must use the potential foci as possible co-specifiers. However, the interpreter's actual choices require consideration of several matters, and before any rules can be stated, several motivating cases must be presented.</Paragraph> <Paragraph position="21"> D3-1 Alfred and Zohar liked to play baseball.</Paragraph> <Paragraph position="22"> 2 They played it everyday after school before dinner.</Paragraph> <Paragraph position="23"> 3 After their game, Alfred and Zohar had ice cream cones.</Paragraph> <Paragraph position="24"> 4 The boys thought they tasted really good.</Paragraph> <Paragraph position="25"> 5 Alfred always had the vanilla super scooper, 6 while Zohar tried the flavor of the day cone.</Paragraph> <Paragraph position="26"> 7 After the cones had been eaten, 8 the boys went home to study.</Paragraph> <Paragraph position="27"> In D3, Alfred and Zohar are the initial actor focus while baseball is the initial discourse focus. D3-2 contains two pronouns, &quot;they&quot; and &quot;it&quot; which, according to R2, co-specify respectively with Alfred and Zohar, and baseball. D3-3 uses &quot;their,&quot; which co-specifies with Alfred and Zohar, but is not accounted for by rule R2. Furthermore &quot;they&quot; in D3-4 does not co-specify with baseball but with ice cream cones.</Paragraph> <Paragraph position="28"> What has happened? Suppose in addition to the ongoing actor and discourse focus, the hearer can consider temporarily any new entities mentioned in the last sentence that the hearer has heard. These entities, the potential foci, are dropped out of processing use if the speaker fails to mention them a second time; such alternatives are elements the speaker may want to say more about, but their importance to the speaker cannot be determined from one sentence. Thus in D3-2, foci include the event of playing, and the times &quot;everyday&quot;, &quot;before dinner,&quot; and &quot;after school&quot;. None of these potentials survives long into the discourse as D3-3 fails to pick up on any of them. D3-3 in turn introduces some other potential loci, and one of them, ice cream cones, is discussed in D3-4; notice also that D3-4 fails to mention baseball in any way.</Paragraph> <Paragraph position="29"> 222 American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 Candace L. Sidner Focusing for Interpretation of Pronouns R2 must be extended so that it uses the potential foci whenever criteria from syntax, semantics or pragmatic knowledge rule out the current actor or discourse focus. Thus since &quot;they&quot; in D3-4 cannot co-specify with baseball (on both syntactic 5 and semantic 6 grounds), a potential focus is chosen. Potential foci are ordered according to their thematic relation 7 in a sentence, with semantic case objects first, and agents last. The first potential focus that meets all the constraints is chosen as the co-specifier; in D3, ice cream cones is the first acceptable potential focus that meets all the necessary constraints as a co-specifier for &quot;they.&quot; Use of this modified pronoun rule follows hand-in-hand with the focus machine discussed previously. The machine updates its discourse model after each sentence by tracking, among other things, pronoun use. When a pronoun is used to co-specify with a phrase that is a potential focus, and no phrase co-specifies the current focus, either the discourse focus or actor focus moves to that potential focus. Which of the two foci moves depends on whether the pronoun fills the agent case in the verb frame, and in the case of multiple agent cases, whether the ongoing actor focus is re-mentioned. For example, after D3-4, the discourse focus changes to ice cream cones because &quot;they&quot; co-specifies with the ice cream cones; the boys remain the actor focus, since &quot;they&quot; is not an agent case for &quot;taste&quot; and since the boys were already the actor focus.</Paragraph> <Paragraph position="30"> So far pi-rules take into account the movement of focus and constraints on syntax, semantics and pragmatics. However, some of the semantic and pragmatic criteria must be expanded beyond the simple case frame semantics and representation of noun phrases given earlier.</Paragraph> <Paragraph position="31"> As the reader may have concluded, the interaction between actor and discourse loci is a complex one; to supplement the case frame semantics, some functional notion of theme (in the sense of functionalists such as Halliday 1967) is needed. For example, the proper co-specifier for the pronoun in D4-3 cannot be chosen with R2 and only simple case frame relations.</Paragraph> <Paragraph position="32"> D4-1 I haven't seen Jeff for several days.</Paragraph> <Paragraph position="33"> Although Carl is the actor focus after D4-2, and &quot;he&quot; in D4-3 is the actor case in the embedded sentence, the proper choice for the co-specifier is Jeff. Howev5 since &quot;they&quot; is a plural pronoun and baseball is singular, 6 since the discourse items filling the object case of taste should be tastable items, 7 This type of ordering is motivated by the determination of an initial focus. See Sidner 1979 for details.</Paragraph> <Paragraph position="34"> er, with simple case frame semantics, the interpreter must consider &quot;Carl&quot; as the co-specifier and then fail to rule it out (because no syntactic, semantic or knowledge constraints can eliminate it).</Paragraph> <Paragraph position="35"> I have designed the pi-rules to use a semantics that marks verbs like &quot;thinking&quot; or &quot;talking&quot; with who the thinking or talking was about. D4-3 would indicate that the speaker thinks about X, that X went to the Cape with Linda. With this semantics, the interpreter follows a rule to prefer the discourse focus as the co-specifier of any pronoun filling the theme position in such a verb. Since the actor focus is associated with the agent case, use of such a theme-based rule is consistent with the framework. With such a rule, Jeff is chosen as the co-specifier of &quot;he,&quot; not because Carl couldn't have gone to the Cape with Linda, but because the speaker is talking about Jeff and his thoughts about Jeff. In essence this approach takes the discourse focus as primary, the discourse focus being what the speaker is talking about so far, while the actor focus is the locus of information about actions in the discourse.</Paragraph> <Paragraph position="36"> The theme-focus rule does not indicate what to do when the discourse focus and actor focus are both animate, have the same gender, number and person, and are both established during the same sentence of the discourse. People sometimes have difficulty choosing interpretations in such circumstances. In D5-2a below, &quot;he&quot; co-specifies with &quot;John&quot; (the actor focus) but if D5-2b followed D5-1, &quot;he&quot; may co-specify with either John or Mike (the discourse focus). D5-1 John called up Mike yesterday.</Paragraph> <Paragraph position="37"> 2 a He wanted to discuss his physics homework.</Paragraph> <Paragraph position="38"> b He was studying for his driver's test.</Paragraph> <Paragraph position="39"> In these cases, native speakers report that the co-specifier for the pronoun is ambiguous. If the pronoun fills an agent case, the actor is preferred, but this preference is not a strong one. It appears that in such cases the ambiguity may not be easily resolved unless additional information about the two foci is known that stipulates that the sentence is true of only one.</Paragraph> <Paragraph position="40"> Potential foci can be sub-categorized as either potential discourse loci or as potential actor foci. A potential actor is a noun phrase which specifies a data-base element marked as animate and which does not occur in agent position. In most sentences, the noun phrase in agent position contains a descriptive word or name in the head, and specifies a database element; it becomes the actor focus. But when the noun phrase in agent position is a pronoun, it may co-specify with either the actor focus (if one exists), or a potential actor. Ambiguities occur when an actor and one potential actor are both present in a previous sentence and when the discourse focus is a non-actor entity.</Paragraph> <Paragraph position="41"> An example is given below.</Paragraph> <Paragraph position="42"> American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 223 Candace L. Sidner Focusing for Interpretation of Pronouns Consider the examples where s5 follows each of s6, s7, s8 and s9.</Paragraph> <Paragraph position="43"> s5 He knows a lot about high energy physics.</Paragraph> <Paragraph position="44"> s6 Prof. Darby will tell Monty about the neutron experiment.</Paragraph> <Paragraph position="45"> s7 Prof. Darby will lecture Monty on the neutron experiment.</Paragraph> <Paragraph position="46"> s8 Prof. Darby will help Monty with the neutron experiment.</Paragraph> <Paragraph position="47"> s9 Prof. Darby will teach Monty about the neutron experiment.</Paragraph> <Paragraph position="48"> Some native speakers find all of these sentence pairs ambiguous, while some native speakers find only the pair s6 followed by s5 ambiguous. These examples are surprisingly similar to D5. How do some speakers decide that &quot;he&quot; co-specifies with Monty or Prof. Darby? It appears that they make a comparison and choose between the actor focus and the potential actor on the basis of evidence for their preferred interpretation. When that evidence is not forthcoming, informants are confused. Such a behavior suggests that the inference mechanism should be able to judge preferences between a given actor and one potential actor. A computational system that makes such judgments must have a very rich knowledge base (e.g., to know that Monty is a male name, and that professors may be male) and must be able to infer which actor is preferable from that base. A computational framework for carrying out such subtle judgments is still beyond the state of the art, although Marcus 1980 has proposed a semantic choice mechanism that must also weigh evidence for prepositional phrase attachment; his parser, when attaching prepositional phrases, asks the semantic processor about its preferences for where to attach the phrases.</Paragraph> <Paragraph position="49"> In summary, the interpreter can use the following condition for these ambiguities.</Paragraph> </Section> <Section position="6" start_page="0" end_page="0" type="metho"> <SectionTitle> POTENTIAL ACTOR AMBIGUITY CONDI- </SectionTitle> <Paragraph position="0"> TION: Whenever a pronoun may co-specify the actor focus, and a single potential actor exists, expect a possible ambiguity. To resolve, 1. If there is evidence supporting the actor focus as the co-specifier, but not the potential actor, then the actor focus is the co-specifier.</Paragraph> <Paragraph position="1"> 2. When evidence supports the potential actor but not the actor focus, select the potential actor as the co-specifier.</Paragraph> <Paragraph position="2"> 3. However, if there is evidence for both, select the actor focus but indicate ambiguity.</Paragraph> <Paragraph position="3"> A summary of a full set of pronoun rules is given in the appendix to this paper. These rules represent what can be said about pronoun interpretation in the absence of any additional information in knowledge representation beyond that suggested in the discussion of co-specification. To interpret certain pronouns, such as those where a co-specifying phrase does not precede the pronoun in the discourse, as in D1, we must consider how knowledge is structured and represented.</Paragraph> </Section> <Section position="7" start_page="0" end_page="0" type="metho"> <SectionTitle> 5. Focus and Knowledge Representation </SectionTitle> <Paragraph position="0"> Focusing theory with the syntactic and semantic representations discussed initially does not include an account of the representation of sentence pairs such as D6 where the sentence is ambiguous due to scope of quantifiers.</Paragraph> <Paragraph position="1"> D6-1 Wendy showed each girl Bruce knows a cat.</Paragraph> <Paragraph position="2"> 2 a She had found it at Farmer John's.</Paragraph> <Paragraph position="3"> b They were all from the same litter.</Paragraph> <Paragraph position="4"> At present the focusing rules predict only that &quot;a cat&quot; is the expected discourse focus, but they say nothing about the scope relations for representing the semantics of the phrase as part of D6-1. Without scope relations, D6-2b is ruled out by the number agreement criteria when in fact most speakers say that &quot;they&quot; co-specifies with the set of cats that may be evoked in D6-1. Webber 1978 not only argues in detail for representing scope relations in the mechanisms for interpreting anaphors, but also gives rules for determining scope in a representation of phrases that may be cospecifiers. null On Webber's analysis, D6-1 will have two representations for &quot;a cat&quot; and for &quot;each girl Bruce knows.&quot; The one for &quot;a cat&quot; can be paraphrased as: 1. RI: the cat associated with D6-1 such that Wendy showed it to each girl Bruce knows.</Paragraph> <Paragraph position="5"> 2. R2: the set of cats, the members of which are associated with D6-1 such that Wendy showed (one of) them to each girl Bruce knows.</Paragraph> <Paragraph position="6"> Webber has suggested what the representation must be, and what remains to be determined is when it is used. Let us suppose that D6-1 is ambiguous,8 and no syntactic or semantic processing of it adjudicates the two readings R1 and R2 for &quot;a cat.&quot; When the pronoun interpreter seeks to co-specify &quot;it&quot; in D6-2a with the discourse focus, both readings will be available. The set reading R2 may be eliminated immediately because of constraints that the co-specifier represent a singleton, so R1 is left. In contrast, for D6-2b the reading R1 will be ruled out since &quot;they&quot; requires a plural co-specifier. This account both explains how the pronouns may be understood, and also is consistent with Van Lehn's findings \[1978\] that people do 8 A question, often raised by Martin (see, for example, Martin 1979), is whether a sentence that is ambiguous among several readings must be represented by several different structures, one for each reading. He offers a semantic representation that preserves ambiguity until some processor demands a refinement. Whether this approach or an alternative representation containing both readings is best is still an open question.</Paragraph> <Paragraph position="7"> 224 American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 Candace L. Sidner Focusing for Interpretation of Pronouns not normally disambiguate certain ambiguous quantifier scopes during sentence understanding for sentences such as D6-1. It is compatible with Van Lehn's findings because alternative interpretations of scope are not considered until additional discourse material beyond the single sentence is presented.</Paragraph> <Paragraph position="8"> Webber's rules also allow the phrase &quot;each girl Bruce knows&quot; to be interpreted as a prototype, with the result that &quot;a cat&quot; is also. Most speakers find this reading very odd, and one can ask how such a reading is eliminated. Possibly it is never generated, and Webber's rules need modification. Alternatively it is produced, and then is ruled out, either in understanding D6-1 because showing prototypic cats is bizarre, or because in interpreting &quot;it&quot; for D6-2a, the inference mechanism balks at Wendy having found a prototypic cat at Farmer Brown's. I think that such readings never occur in the first place, simply because most speakers, who do not report this reading themselves, have difficulty understanding the reading when they are told about it.</Paragraph> <Paragraph position="9"> Another case of semantic ambiguity, similar to the one in D6, is illustrated in D7.</Paragraph> <Paragraph position="10"> D7-1 Sally wanted to buy a vegomatic.</Paragraph> <Paragraph position="11"> 2 She had seen it advertised on TV.</Paragraph> <Paragraph position="12"> &quot;A vegomatic&quot; may be interpreted specifically, to mean that there is one particular vegomatic or nonspecifically, to mean that it is one of the many vegomatics. 9 The focusing rules do not distinguish between the two after D7-1 because, like D6-1, D7-1 is ambiguous, and neither interpretation can be chosen with certainty. When &quot;it&quot; is resolved for co-specification in D7-2, the inference mechanism must decide that Sally does not want the very one used in the advertisement on TV. &quot;A vegomatic,&quot; whether understood as specific or non-specific, specifies a different representation than &quot;it&quot; does. Therefore the pronoun's specification as a specific vegomatic must be generated from the ambiguous use.</Paragraph> <Paragraph position="13"> Suppose, for a moment, that D7-1 is interpreted so that a representation that maintains ambiguity is available. When the pronoun interpreter processes a subsequent sentence with a pronoun, it need only rule out readings if the inference machine discounts as contradictory one of the readings (Sally didn't want to buy the very one she saw on TV). If no reading is ruled out, the co-specifier would remain ambiguous, so that both the indefinite phrase and the pronoun would have 9 The terms &quot;non-specific&quot; and &quot;specific&quot; are traditional semantic expressions that bear no relation to &quot;specify&quot; and &quot;specification.&quot; A non-specific reading of &quot;a dog&quot; would be interpreted to produce a representation of an instance of the prototypic dog; what is represented is a dog which has the characteristics of the prototypic dog - e.g., an animal with four legs, a tail, medium size, brown, friendly, barks, and the like.</Paragraph> <Paragraph position="14"> ambiguous co-specifications. As the next example shows, there is some evidence for this behavior.</Paragraph> <Paragraph position="15"> Consider the case shown in D8.</Paragraph> <Paragraph position="16"> D8-1 Sally bought a vegomatic that had a broken cutting blade.</Paragraph> <Paragraph position="17"> 2 She had seen it advertised on TV.</Paragraph> <Paragraph position="18"> &quot;A vegomatic that had a broken cutting blade&quot; in the context of D8-1 usually means some particular vegomatic that Sally bought. However, &quot;it&quot; is ambiguous among the vegomatic Sally bought (the broken one), some vegomatic (possibly not broken), and a vegomatic that is an instance of prototypic vegomatic. Thus &quot;it&quot; is three ways ambiguous.</Paragraph> <Paragraph position="19"> To understand D8-2, the pronoun interpreter does not distinguish among the three readings, since it accesses the one provided by the specification in D8-1, which is the specific reading. To find the specification of &quot;it,&quot; the inference mechanism must discover that it is slightly odd (1) for Sally to have seen the vegomatic with a broken blade which she bought being advertised on TV, and (2) for Sally to see any broken vegomatics on TV, and (3) for Sally to have seen the very one she bought on TV. Then if no other choices for co-specification are available, the specification of vegomatic from D8-1 must be used to generate an appropriate specification for &quot;it&quot;. Since only unbroken ones not bought by Sally are appropriate, the specification of &quot;it&quot; must be generated using only part of the phrase from D8-1.</Paragraph> <Paragraph position="20"> This example seems problematic because it places much weight on the inference machine to decide that the reading is odd. However, this is likely to be just where the weight of the decision ought to be; many native speakers find D8 slightly bizarre because their first reading is that Sally had seen the vegomatic with the broken blade advertised on TV. In fact, it appears that when a specific indefinite noun phrase such as &quot;a vegomatie&quot; is introduced, and the speaker wants to turn attention to the non-specific reading, a plural pronoun is used as shown below: sl0 She had seen them advertised on TV.</Paragraph> <Paragraph position="21"> The plural non-specific reading as in sl0 is mentioned in the pronoun rules found in the appendix, but the generation of a specification as in D8-2 is not.</Paragraph> <Paragraph position="22"> Examples such as D8 are perplexing for another reason; they are examples of what I call, following Fahlman 1977, the &quot;copy phenomenon.&quot; The ambiguity centers around the fact that there can be many copies of an abstract prototype. Automobiles, computer programs, airplane flights and money are other common cases of entities that exhibit the copy phenomenon. In D9, the interpretation of &quot;it&quot; depends on whether the speaker is referring to a particular flight or the normal Sunday flight, a copy of which American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 225 Candace L. Sidner Focusing for Interpretation of Pronouns occurred on &quot;this Sunday&quot; because of the use of &quot;usually&quot;.</Paragraph> <Paragraph position="23"> D9-1 TWA 384 was so bumpy this Sunday I almost got sick.</Paragraph> <Paragraph position="24"> 2 It usually is a very smooth flight.</Paragraph> <Paragraph position="25"> Note that the &quot;it&quot; cannot co-specify with the particular flight on &quot;this Sunday&quot;. However, it is possible that the speaker used &quot;TWA 384&quot; to refer to a particular flight; if this is so, the speaker mixed the specific and non-specific interpretations for the co-specifier of &quot;it&quot;. Just as in D8, a specification for the pronoun must be generated -- in this case, a non-specific one from the specific reading.</Paragraph> <Paragraph position="26"> Another characteristic anaphora is the bound variable case described by Partee \[1978, 1972\]. In D10 below, &quot;him&quot; co-specifies with Archibald, while if the reflexive &quot;himself&quot; were used, it would involve a variable bound to the quantifier from &quot;every man.&quot; D10-1 Archibald sat down on the floor.</Paragraph> <Paragraph position="27"> 2 Every man put a screen in front of him.</Paragraph> <Paragraph position="28"> In linguistic theory, bound variables are assumed to be represented in sentence semantics; when used in conjunction with syntactic disjoint reference rules, pronouns within the scope of the quantifier can be distinguished from non-scoped ones. Since the pronoun interpreter takes account of these conditions, it can easily choose a proper co-specifier for &quot;him&quot; in D10 in terms of the focus, but for &quot;himself&quot; it will recognize the bound relation to &quot;every man.&quot; It is crucial to these cases that the representation of the interpretation of a sentence includes scope of quantification, especially when the scope is unambiguous.</Paragraph> </Section> <Section position="8" start_page="0" end_page="0" type="metho"> <SectionTitle> 6. Focus Restrictions on Co-specification </SectionTitle> <Paragraph position="0"> There are other restrictions on co-specification that result from the processing of the focus machine. The focus machine includes a stack on which old foci are stored when the focus changes. In addition to co-specifications with current actor and discourse foci, a speaker may use a pronoun to co-specify a discourse element that was once in focus but is no longer; Grosz 1977 described and illustrated this behavior for anaphoric noun phrases in task-oriented dialogues.</Paragraph> <Paragraph position="1"> A pi-rule that selects candidates from the focus stack can capture this behavior. However, the rule must be further constrained. An anaphor that is intended to co-specify with a stacked focus must not be acceptable as a co-specifier with either the foci or potential loci. An example from a literary text10 illustrates how.</Paragraph> <Paragraph position="2"> Was that old lady evil, the one Saul and I had seen sitting on the porch? I had dreamed about her. When the trolley car took me and Saul past her house again this morning, she was gone. Evil, it had a queer sound to it in English. null \[Here the narrative moves on to an incident in a school classroom. A discussion between the speaker and a male teacher ensues for five paragraphs. Then the following paragraph begins:\] She had worn an old brown coat and a green scarf over her head.</Paragraph> <Paragraph position="3"> In this example, &quot;she&quot; co-specifies with the old lady discussed previously. If Potok had told of a discussion between the speaker and a female teacher, it would no longer be possible to tell that &quot;she&quot; was co-specifying with the old woman. While interpreting the reading of &quot;she&quot; as teacher might be a bit surprising because the teacher's clothing was not relevant to the previous conversation, no inference can rule out that reading because teachers may wear old brown coats. Hence the pronoun interpreter must reflect these facts, and it does so with the stacked focus constraint.</Paragraph> <Paragraph position="4"> The stacked focus constraint is not stated directly within the pi-rules. Instead it is implicit in their function. The condition is as follows: A pronoun cannot be used to co-specify with a stacked focus when a current focus is an acceptable co-specification since that current focus will be taken as the interpretation and the stacked focus will never come into consideration. The stacked focus constraint is a consequence of the movement of focus in the focus machinery.</Paragraph> <Paragraph position="5"> The stacked focus constraint, however, may be overridden. Grosz (see Deutsch 1975, 1974) has identified several examples, involving pumps and bolting operations, that show that a pronoun may co-specify with the stacked focus even when intervening material contains possible co-specifiers. Some complicated set of inferences about what can and cannot be bolted to what, or what can and cannot be loosened might be able to rule out the intervening possible cospecifications. However there appears to be too little delay in understanding for people who read her excerpts (there is no means of determining whether the original speaker and hearer experienced any delay in understanding) to suggest that they are ruling out multiple possibilities in interpreting the pronouns, it Hence one may conclude that the speaker and hearer are taking advantage of their knowledge of the task to provide a discourse context in which the focusing machinery can be applied.</Paragraph> <Paragraph position="6"> How many such discourse interpretation mechanisms exist? While this paper does not address this question directly, some speculation is possible on the logical laboratory. I have not done so, but the results of such experimentation would be revealing.</Paragraph> <Paragraph position="7"> 226 American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 Candace L. Sidner Focusing for Interpretation of Pronouns basis of research that has been reported elsewhere (see Sidner 1979, Robinson 1981). In general, it appears that discourses permitting violations of the stacked focus constraint must contain an implicit structure of task completion that guides the hearer to a context in which the foci for that context may be re-used. Without this structure the hearer cannot decide that the speaker intended for the pronoun to co-specify with something other than the representation of the object currently under discussion.</Paragraph> <Paragraph position="8"> 7. Pronouns Which Have No Co-specifiers The previous discussion has assumed that a pronoun is always preceded by a co-specifying phrase.</Paragraph> <Paragraph position="9"> However, this is not always the case, and a complete theory of pronoun interpretation must address cases where the co-specifying phrase appears after the pronoun, and where no co-specifier exists, but the discussion implies a specification for the pronoun.</Paragraph> <Paragraph position="10"> Pronouns used with their co-specifiers appearing after the occurrence of the pronoun have been called backward anaphora in the linguistic literature; I refer to them as forward co-specifiers. Two such examples, sll and s12, are given below.</Paragraph> <Paragraph position="11"> sl 1 If he comes before the show, give John these tickets and send him to the theatre.</Paragraph> <Paragraph position="12"> s12 Near him, Dan saw a snake.</Paragraph> <Paragraph position="13"> In general the pronoun co-specifies with some noun phrase interpretation, but the phrase is placed forward in the discourse. The types of sentences in which this behavior can occur are limited. In general it seems to be permitted for fronted sentential prepositional phrases (as in s12), subordinate clauses fronted on another sentence (as in sll), and for sentences containing co-ordinating conjunctions, t2 However, it is excluded, as far as I can tell, in the following cases: 13 s13 * I heard about her job from Mary.</Paragraph> <Paragraph position="14"> s14 * I spoke about him with John's wife.</Paragraph> <Paragraph position="15"> Extensive research in linguistics on forward co-specifiers (Solan contains a good review) gives reliable evidence that structural constraints govern it; in particular, syntactic rules can be stated that determine when forward co-specifiers are not permitted. The most recent formulation, by Solan, called the backward anaphora restriction, fails on the cases below, 12 Solan 1978 cites the example: s15 Penelope grabbed his cane and beat Peter with it.</Paragraph> <Paragraph position="16"> 13 There is some disagreement on s13; Solan claims it is acceptable. All the native speakers I have asked said they interpreted the pronoun as &quot;referring to Mary&quot; only because there were no other usual choices and because you could hear about a person's job from that person. Since all the people I asked informally told me it was a strange sentence for them, I am assuming that it is deviant.</Paragraph> <Paragraph position="17"> but some working modification of it may yet be forthcoming. null s16 In her room Mary saw a ghost.</Paragraph> <Paragraph position="18"> s17 I heard about Mary's job from her.</Paragraph> <Paragraph position="19"> Whatever the best formulation of the syntactic rules for forward co-specifiers, they are preferable only in initial sentences of a discourse. For example, when sll occurs in mid-discourse, if a speaker has been talking about Henry, and just begun mention of Charles, native speakers will interpret &quot;he&quot; as co-specifying with Henry, or Charles (if Henry can be ruled out on basis of some special pragmatic knowledge). The pi-rules using focus behave in exactly this way. They will permit a forward co-specifier only if Henry and Charles can be ruled out by syntactic, semantic and world knowledge criteria. Were sll to occur when Lydia was in focus, the forward co-specifier would be possible, and pi-rules mirror this behavior.</Paragraph> <Paragraph position="20"> When faced with a pronoun that has no preceding co-specifier and is not a forward co-specifier, the pronoun interpreter relies on a condition that is called the missing co-specifier condition. In the remainder of this section, I describe that condition. The pi-rules include a rule for recognizing that a pronoun is missing its co-specifier, but they do not offer an interpretation for such pronouns.</Paragraph> <Paragraph position="21"> In each of the cases below, the pronoun specifies some cognitive element that is related to one of the entities mentioned in either the previous sentence or the same sentence. These examples 14 are different from the non-specific prototypic readings of pronouns discussed earlier because no phrase which can be used as a generator exists.</Paragraph> <Paragraph position="22"> Dll-1 I saw Mr. Smith the other day; you know, she died last year.</Paragraph> <Paragraph position="23"> when I get together with the young guys to play, I can hardly get it over the net.</Paragraph> <Paragraph position="24"> With the exception of D11-1, most speaker-hearers are able to say which is the intended specification of the pronoun in the cases above. D11-1 can be understood 14 The examples given here are from several sources; the first three are from Postal 1969, the fourth from Chafe 1975, the fifth from dialogues collected for the PAL system \[Sidner 1979\], and the last was spoken by a lecturer at a presentation I attended. American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 227 Candace L, Sidner Focusing for Interpretation of Pronouns if the hearer is informed that Mr. Smith had a wife.</Paragraph> <Paragraph position="25"> However, some of these, especially 1 and 2, are so odd for most hearers that at first they fail to comprehend the pronoun. Hearers are divided on the acceptability of 3, and most hearers find 4 and 5 acceptable. Furthermore, such examples, as far as I can tell, do not occur naturally in written samples.</Paragraph> <Paragraph position="26"> This paper does not give an account of just how such cases are understood. However, the focusing approach provides some basic structure that may be useful in generating an explanation for such situations. In all the multi-sentence cases, the pronoun specifies something which is closely associated with the focus.</Paragraph> <Paragraph position="27"> What is problematic is the fact that some speakers seem unable to understand a pronoun which specifies a database element that, while related to the item in focus, represents something that no longer exists, such as John's parents in light of John's orphanhood.</Paragraph> <Paragraph position="28"> Whatever the manner in which hearers recover specifications for such pronouns, some principles are needed which govern why some uses of pronouns are acceptable and others are not.</Paragraph> <Paragraph position="29"> 8. The Problem of Parallelism The pi-rules give incorrect predictions for certain uses of pronouns, uses that are difficult to define.</Paragraph> <Paragraph position="30"> Intuitively, they may be characterized as occurring when there is a parallel structure between sentences of a discourse/5 In many of these cases the pi-rules predict the wrong co-specifier. To understand what is meant by parallel structure, two simple cases, one in which the pi-rules do predict correctly, and another in which they fail, are discussed. In D12, the pronoun co-specifies with the mud pack, as the pi-rules would predict. The parallelism of these sentences is reflected in the semantics of &quot;put on&quot; and &quot;pull off&quot; as well as in the similarity of the syntactic structure of the two sentences, each being in imperative mood.</Paragraph> <Paragraph position="31"> D12-1 Put the mud pack on your face.</Paragraph> <Paragraph position="32"> 2 After 5 minutes, pull it off.</Paragraph> <Paragraph position="33"> The pi-rules predict the proper co-specifier in D12 because the thematic relations of the verb follow the similarity of structure. However, in D13 below, the pronoun &quot;it&quot; co-specifies with rose and not with the green Whitierleaf (the pi-rule choice). The initial focus after the first sentence is Whitierleaf, but the parallel syntactic structure of the sentences seems to govern a different choice of co-specifier. To summarize, between similarity of structure and the pi-rules, similarity is preferred as a means of choosing a co15 Hobbs 1979 defines a parallel relation between sentences sO and S1 of a discourse as occurring when propositions P0 and PI, which follow from SO and S1 respectively, have identical predicates, and arguments that are similar (p. 76). This concept of a parallel relation seems related to my intuitive characterization, but as defined does not capture the cases I discuss.</Paragraph> <Paragraph position="34"> specifier, so when each gives a different prediction, similarity of structure must be used.</Paragraph> <Paragraph position="35"> D13-1 The green Whitierleaf is most commonly found near the wild rose.</Paragraph> <Paragraph position="36"> 2 The wild violet is found near it too.</Paragraph> <Paragraph position="37"> At first glance it appears that the pi-rules could be &quot;fixed&quot; by simply observing that the initial focus is wrong and that a potential focus should be chosen.</Paragraph> <Paragraph position="38"> However, no such option is available, for such a &quot;fix&quot; requires that the inference machine reject the initial focus. To do so, the inference mechanism needs some knowledge about the world that indicates the unacceptability. For D13 no such knowledge could possibly be forthcoming since all the flora involved are found near one another. There is no knowledge to the effect that violets are found near wild roses and not near Whitierleafs. t6 Another example of parallel structures is shown in D14. The parallel structures again are reflected in the similarity of the syntactic forms as well as the semantics of &quot;most&quot; and &quot;mine&quot;. After D14-1, the initial focus is the car radiator that is associated with each car of &quot;most cars.&quot; Using the focusing rules, the pronoun interpreter will take &quot;it&quot; to co-specify with that radiator. But this prediction is incorrect; &quot;it&quot; co-specifies with the radiator of the speaker's car/7 D14-1 On most cars the radiator has a free bolt hook.</Paragraph> <Paragraph position="39"> 2 But on mine, it has a floating bolt hook.</Paragraph> <Paragraph position="40"> The use of &quot;it&quot; here is similar to the instance of a prototype for &quot;it&quot; in D8. The two discourse examples differ because D14-2 has an underlying semantic form that parallels D14-1. D14-1 specifies a universal set of cars and says something about one of the parts for those cars; D14-2 specifies a set of one thing, the speaker's car, and says something about a part of it; the speaker's car is related to the universal car by instantiation. Thus &quot;it&quot; in D14-2 is not pointing to some instance of the prototypic radiator; it co-specifies with the radiator of the speaker's car, but &quot;it&quot; is related intensionally to the &quot;radiator&quot; in D141. The similarity in the underlying semantics of D14-1 and D14-2 must be used in interpreting the pronoun uses.</Paragraph> <Paragraph position="41"> One might wish to construct some special-purpose mechanism that looks for similarities in structure between two sentences. This method is doomed for two reasons. First, parallelism exists in many aspects of language, and it happens at arbitrary levels of struc16 In certain cases a special audience may have different responses to the parallelism above. For example, botanists who know what flowers are near others might behave differently. But even special audiences must sometimes use general techniques. Such is the case in the D13 example, because Whitierleafs exist only in my imagination.</Paragraph> <Paragraph position="42"> 17 I thank R.C. Moore for suggesting this example.</Paragraph> <Paragraph position="43"> 228 American Journal of Computational Linguistics, Volume 7, Number 4, October-December 1981 Candace L. Sidner Focusing for Interpretation of Pronouns ture rather than just syntactically. Second, at any given level, the problem of recognition of parallelism has plagued computational models of language since such models were first suggested. For example, parsing of English sentences containing conjunction is as yet an unsolved problem. Methods tried, such as those of Woods 1973 in LUNAR, fail because of overgeneralization. Proper computational recognition of parallelism is still beyond the state of the art.</Paragraph> <Paragraph position="44"> The fact that interpretation of parallelism has failed for other aspects of computational models of language only indicates that the problem is a deep one. The example below is especially surprising because it demonstrates the use of parallel constructions that may be found between whole paragraphs in a discourse. The interpretation of &quot;the schedule,&quot; used anaphorically in D15-7, is not ambiguous between &quot;SOL,&quot; which is a kind of schedule, and the transmission schedule; readers recognize that the anaphor is unambiguous presumably because the process described in lines 5-7 parallels the one in lines 2-4. Whatever the proper account of parallelism for pronominal anaphora, it must also be generalizable to account for this kind of example, t8 D15-1 The SOL is searched for an entry for the subscriber.</Paragraph> <Paragraph position="45"> 2 If one is found, the subscriber's relative transmission time is computed according to formula-1.</Paragraph> </Section> <Section position="9" start_page="0" end_page="0" type="metho"> <SectionTitle> 3 The subscriber's clock transmission time </SectionTitle> <Paragraph position="0"> is computed according to formula-2.</Paragraph> </Section> <Section position="10" start_page="0" end_page="0" type="metho"> <SectionTitle> 4 When the transmission time has been </SectionTitle> <Paragraph position="0"> computed, it is inserted as the primary entry in a transmission schedule.</Paragraph> <Paragraph position="1"> 5 For each RATS entry, the RATS's relative transmission time is computed according to formula-l, 6 and the RATS's clock transmission time is computed according to formula-2.</Paragraph> </Section> <Section position="11" start_page="0" end_page="0" type="metho"> <SectionTitle> 7 The RATS transmission times are entered </SectionTitle> <Paragraph position="0"> into the schedule.</Paragraph> <Paragraph position="1"> One possible consequence of these observations could be that the focus mechanism should be abandoned in favor of some as yet unspecified mechanism that is able to determine parallel relations among sets of sentences in a discourse. However, methods for interpreting pronouns from parallel sentences and paragraphs offer no constructive way of interpreting the pronouns in most of the examples presented in this paper. Many cases of co-specification occur where there is no similarity of structure other than the com18 For easier understanding, the reader must know that the SOL has both subscriber and RATS entries. This example comes from Balzer et al. 1977, &quot;Information in Program Specification,&quot; Proceedings of the Fifth International Joint Conference on Artificial Intelligence, p. 394.</Paragraph> <Paragraph position="2"> mon subject-verb-object pattern typical of English sentences. Since what is being talked about appears in many constituent positions in sentences of a discourse, the S-V-O pattern is too gross a level to specify similarity. Hence, while parallelism is needed to deal with a certain set of cases for which the pi-rules predict incorrectly, the pi-rules are effective for many other cases of co-specification where parallelism would not be helpful. One may conclude that focus mechanisms account for one aspect of pragmatic anaphora, and that some different mechanism is needed to encode similarities in structure that sometimes occur in discourse. This paper does not give an account of such a mechanism. Rather, the examples above provide some additional observations about the nature of parallelism in interpreting pronouns in natural languages.</Paragraph> </Section> class="xml-element"></Paper>