File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/85/p85-1024_metho.xml
Size: 28,449 bytes
Last Modified: 2025-10-06 14:11:47
<?xml version="1.0" standalone="yes"?> <Paper uid="P85-1024"> <Title>A PRAGMATIC~BASED APPROACH TO UNDERSTANDING INTERS~NTENTIAL ~LIPSI~</Title> <Section position="4" start_page="188" end_page="188" type="metho"> <SectionTitle> REQUISITE KNCWLEDG E </SectionTitle> <Paragraph position="0"> A speaker can felicitously employ intersententlal ellipsis only Lf he believes his utterance will be properly understood. The motivation for this work is the hypothesis that speaker and hearer mutually believe that certain knowledge has been acquired during the course of the dialogue and that this factual knowledge along with other processing knowledge will be used to deduce the speaker,s intentions. We claim that the requisite factual knowledge includes the speaker,s inferred task-related plan, the speaker's inferred beliefs, and the anticipated discourse Eoala of the speaker; We claim that the requisite processing knowledge includes plan recognltlon strategies and focuslng techniques.</Paragraph> </Section> <Section position="5" start_page="188" end_page="189" type="metho"> <SectionTitle> 1. Task-Related Plan </SectionTitle> <Paragraph position="0"> In a cooperative information-seeking dAelogue, the ln~ormation-provider is expected to infer the ir~ors~ation-seeker, s underlying task-related plan an the dialogue pro~-eases. At any point An the dialo~e, ZS (the information-seeker) believes that soae subset of this plan has been coemunAmated to IP (the in~ormation-provider); therefore Y~ feeAa Juatl.rled in ~ormuAating utterances under the assumption that IP will use this inferred task model to interpret utterances, includIDg elliptleLL frasmente.</Paragraph> <Paragraph position="1"> An example will illustrate the importance of IS's inferred task-related plan in interpreting ellipsis. In the following, IS is conslderi~ purchase of a home mentioned earlier in the dialo~ue: null IS: &quot;What elementary school do children in Rolling Hills attend?&quot; ZP: &quot;They attend Castle Elementary.&quot; IS: &quot;Any nearby seim clubs?&quot; An informal poll indicates that most people interpret the last utterance as a request for swim clubs near the property under consideration in Rolling Hills and that the reason for such an interpretation is their inference that IS is investigating recreational facilities that might be used if IS were to purchase the home. However, if we substitute the frasment * An~ nearby day-care centers?&quot; for the last utterance in the dialogue, then interpretation depen~ upon whether one believes IS wants hls/her children to be bused, or perhaps even walk, to day-care directly from school.</Paragraph> </Section> <Section position="6" start_page="189" end_page="189" type="metho"> <SectionTitle> 2. Shared Beliefs </SectionTitle> <Paragraph position="0"> Shared beliefs of facts, beliefs which the listener believes speaker and iistecer mutually hold, are a second component of factual knowledge required for processing intersentential elliptical fra6ments. These shared beliefs either represent presueed a priori knowledge of the domain, such as a pres~ptlon that dialogue participants in a unAvereity domain know that each course has a teacher, or beliefs derived from the dialogue itself. An e~ple of the latter occurs i~ IP tells IS that C3360 is a 5 credit hour course; IS may not himself believe that C3360 is a 5 credit hour course, but as a result of IP's utterance, he does believe it is mutually believed that IP believes this.</Paragraph> <Paragraph position="1"> Understanding utterances requires that we identify the speaker's discourse goal in making the utterance. Shared beliefs, often called mutual beliefs, form a part of communicated knowledge used to interpret utterances and identify discourse goals in a cooperative dlalogue. The following e~a~le illustrates how IP' s beliefs about IS influence usderstan~Ing.</Paragraph> <Paragraph position="2"> IS: &quot;Who is teaching C~O0?&quot; IP: &quot;Dr. Brown is teaching C.~O0.&quot; IS: &quot;At ni~t?&quot; The frasmentar~ utterance &quot;At ni~t?&quot; is a request to know whether CS~O0 is meeting at night. Hc~ever, if one precedes the above utterances with a quer~ whose rms~onse informs IS that CS~O0 meets only at ni~t, then the last utterance, * At ni~t? = becomes an objection and request for corroboration or e~lanatlon. The reason for this difference in interpretation is the difference in beliefs regarding IS at the time the elliptical fragment is uttered. In the latter case, IP believes it As mutually believed that IS already knows IP' s beliefs regarcling when C/~O0 meets, so a request for that informatlon is not felicitous and a different intention or discourse goal is attributed to L~.</Paragraph> <Paragraph position="3"> Allen and Perrault(1980) used mutual beliefs in their work on indirect speech acts and sug~sted their use in clarification and correction dlalogues. ~idner(1983) models user beliefs about system capabilities in her work on recognlzlng speaker intention in utterances.</Paragraph> </Section> <Section position="7" start_page="189" end_page="190" type="metho"> <SectionTitle> 3. Anticipated Discourse Goals </SectionTitle> <Paragraph position="0"> The speaker' s anticipated discourse goals form a third compocent of factual knowledge required for processing elliptical frasmenta. The dlalogue precedlng an elliptical utterance may sugEest discourse goals for the speaker; these sugEested discourse gcals become shared knowledge between speaker and hearer. As a result, the listener is on the lookout for the speaker to pursue these anticipated discourse goals and inter~ ~rets utterances accordingly.</Paragraph> <Paragraph position="1"> Consider for example the following dialogue: IP: &quot;Have you taken C3105 or C3170?&quot; I~: wit the Unlversity of Delaware?&quot; IP: &quot;No, anywhere.&quot; IS: &quot;Yes, at Penn State.&quot; In this example, IP's inlt~al query produces a strong anticipation that IS will pursue the discourse 8oal of provldlng the requested i~formatlon. There/ore subsequent utterances are interpreted with the expectation that IS will eventually address this 8oal. IS's first utterance is interpreted as ~u-sulng a discourse Eoal of seeking clarification of the question posed by IP; IS' s last utterance ansMers the initial query posed by IP. However discourse expectatlons do not persist forever with intervening utterances.</Paragraph> <Paragraph position="2"> . Processing ~owledp P1 an- recognl tlon strategies and focusing techniques are necessary components of processing knowledge for interpreting intersententlal eillpsis. Plan-recognltion strategies are essential I- order to In/er a model of the speaker's underlying task-related plan and focusing techniqces are necessary in order to identIDi that portion of the underlying plan to which a frasmentar7 utterance refers.</Paragraph> <Paragraph position="3"> Focusing mechanAas have been employed by Gross(1977) in identifying the referents of definite noun phrases, by Robinson(1981) in interpreting verb p~vases, by ~ner( 1981 ) in anaphora resolution, by CarberrT(1983) in plan inference, and by McKeown(19fl~) in natural lan&uage generat~on. null</Paragraph> </Section> <Section position="8" start_page="190" end_page="190" type="metho"> <SectionTitle> FRAmeWORK FOR PROCESSING ELLIPSLS </SectionTitle> <Paragraph position="0"> If an utterance is parsed as a sentence fragment, ellipsis processing begins. A model of any preceding dialogue contains a context tree (Carberry, 1983) corresponding to IS's inferred underlying task-related plan, a space containing IS's anticipated discourse goals, and a belief model representing IS's inferred beliefs.</Paragraph> <Paragraph position="1"> Our framework is a top-down strategy which uses the informatlon-seeker' s anticipated discourse goals to guide interpretation of the fragment and relate it to the underlying task-related plan. The discourse component first analyzes the top element of the discourse stack and suggests potential discourse goals which IS might be expected to pursue. The plan analysis component uses the context tree and the belief model to suggest possible associations of the elliptical fragment with aspects of IS's inferred task-related plan. If multiple associations are suggested, the evaluation component applies focusing strategies to select the interpretation believed intended by the speaker --- namely, that most appropriate to the current focus of attention in the dialogue. The discourse component then uses the results produced by the analysis component to determine if the fragment accomplishes the proposed discourse goal; if so, it interprets the fragment relevant to the identified discourse goal.</Paragraph> </Section> <Section position="9" start_page="190" end_page="190" type="metho"> <SectionTitle> PLAN-ANALYSIS COMPONENT </SectionTitle> <Paragraph position="0"> I. Association of Fragments The plan-analysls component is responsible for associating an elliptical fragment with a term or conjunction of propositions in Is's underlying task-related plan. The analysis component determines, based upon the .current focus of attention, the particular aspect of the plan highlighted by IS's fragment and the discourse goal rules infer hcw IS intends the fra@Rent to be interpreted.</Paragraph> <Paragraph position="1"> This paper will discuss three classes of elliptical fragments; a description of how other fragments are associated with plan elements is provided in (Carberry, 1985).</Paragraph> <Paragraph position="2"> A constant fragment can only associate with terms whose semantic type is the same or a superset of the semantic type of the constant. Furthermore, each term has a limited set of valid instantlations within the existing plan. A constant associates with a term only if IP's beliefs indicate that IS might believe that the uttered constant is one of the te.,-m's valid instantiations. For example, if a plan contains the proposition Starting-Date( AI-CONF, JAN/5) the elliptical fragment</Paragraph> </Section> <Section position="10" start_page="190" end_page="190" type="metho"> <SectionTitle> * February 2?&quot; </SectionTitle> <Paragraph position="0"> wall associate w~th this proposition only if IP believes I3 might believe that the starting date for the AS conference is in February.</Paragraph> <Paragraph position="1"> Recourse to such a belief model is necessary in order to allow for Yes-No questions to which the answer is &quot;No&quot; and yet eliminate potential associations which a human listener would reCOgnize as unlikely. Although this discarding of possible associations does not occur often in interpreting elliptical fragments, actual human dialogues indicate that it is a real phenomenon.</Paragraph> <Paragraph position="2"> (Sidner(1981) employs a similar strategy in her work on anaphora resolution. A co-specifler proposed by the focusing rules must be confirmed by an inference machine; if any contradications are detected, other co-specifiers are suggested. ) A propositional fragment can be of two types.</Paragraph> <Paragraph position="3"> The first contains a proposition whose name is the same as the name of a proposition in the plan domain. The second type is a more general propositional fragment which cannot be associated with a specific plan-based proposition until after analyzing the relevant propositions appearing in IS's plan. The semantic representations of the&quot; The latter indicates that the name of the specific plan proposition is as yet unknown but that one of its parameters must associate with the constant Sml th.</Paragraph> <Paragraph position="4"> A proposition of the first type associates with a proposition of the same name if the parameters of the propositions associate. A proposition of the second type associates with any proposition whose ~arameters include terms associating with the known parameters of the propositional fragment. null The semantic representation of a term such as &quot;The meeting time?&quot; is a variable term _~me : &MTG- TMES Such a term associates with terms of the same semantic type in IS's plan. Note that the exlsting plan may contain constant instantiatlons in place of former variaOles. A term fragment still associates with such constant terms.</Paragraph> </Section> <Section position="11" start_page="190" end_page="191" type="metho"> <SectionTitle> 2. Results of Plan-Analysis Component </SectionTitle> <Paragraph position="0"> The plan-analysis component constructs a conjunction of propositions PLPREDS and/or a term PLTERM representing that aspect of the informatlon-seeker' s plan highlighted by the elliptical fragment; STERM and SPREDS are produced by substituting into PLTERM and PLPREDS the terms in IS's fragment for the terms with which they are associated in IS's plan.</Paragraph> <Paragraph position="1"> It appears that h,-,ans retain as much of the established context as possible in interpreting intersententlal ellipsis. Carbonell(1983) demonstrated this phemonenon in an informal poll in which users were found to interpret the fraRment in the followlng dialogue as retaining the fixed media specification: &quot;What is the size of the 3 largest single port fixed media disks?&quot; &quot;disks with two ports?&quot; We have noted the same phenomenon in a student advisement domain.</Paragraph> <Paragraph position="2"> Thus when an elliptical fragment associates with a portion of the task-related plan or an expansion of one of its actions, the context establlshed by the preceding dlalogue must be used to replace information deleted from this streamlined, frae~mentary utterance. The set of ACTIVE nodes in the context model form a stack of plans, the toP-most of whlca is the current focused plan; each of these plans is the expanslon of an action appearing in the plan Immediately beneath it in this stack. These ACTIVE nodes represent the established Elobal context within w~ich the fragmentary utterance occurs, and the propositions appeaclng along this path contain information missing frca the sentence fragment but ;~'esumed understood by the speaker.</Paragraph> <Paragraph position="3"> If the elliptical fragment ls a proposition, the analysis component produces a conjunction of propositions 3PREI~ representing that aspect ot the plan hi~hii~ted bY IS's el!iptlcal fra~ent. EXAM~E- I If the elliptical fragment is a constant, term, or term with attached propositions, the analysis component produces a term STERM associated with the constant or term in the fraRment as well as a con-Junction of propositions SPREDS. SPREDS consists of all propositions along the paths from the root of the context tree to the nodes at which an element of the frasment is associated with a plan element, as well as all propositions appearing along the previous ACTIVE path. The former represent the new context derived from IS's frs4mentary utterance whereas the latter retain the previously established global context.</Paragraph> </Section> <Section position="12" start_page="191" end_page="192" type="metho"> <SectionTitle> 3. E~mple </SectionTitle> <Paragraph position="0"> This example illustrates how the plan-analysis component determines that aspect of IS's plan hi~llg~ted by an elliptical fragment. It also shows how the established context is mainrained in interpreting ellipsis.</Paragraph> <Paragraph position="1"> IS: &quot;Is C3360 offered in Fall 1985?&quot; IP: &quot;Yes.&quot; IS: sod any sections meet on Monday?&quot; IP: &quot;One section of CS360 meets on Monday at ~PM and another section meets on Monday at 7PM. &quot; IS: &quot;The text?&quot; A portlon 0PS I~'s inferred task-related plan prior to the elliptical fragment is shown in glgure I. Nodes along the ACTIVE path are marked by asterlsk~. null The semantic representation of the fragment &quot;The text?&quot; will be the variable term _book: &TEXTS This term associates with the term _txt : &TEXTS appearing at the node for the action Learn- Text ( IS, txt: &TEXTS ) such that Use s(_ss: &SECTIONS,_txt : &TEXTS ) The propositions along the active path are These propositions maintain the established context that we are talking about the sections of C3360 that meet on Monday in the Fall of 1985. The path from the root of the context model to the node at which the elliptical fragment associates with a term in the plan produces the additional pro pc sl tl on Uses (_ss : &SECT IONS,_book: &TEXTS ) The analysis component returns the con~unctlon of these propositions along with STERM, in this case _book: &TEXTS The semantics of this interpretation is that IS is drawing attention to the term STERM such that the con~unctlon of propositions SPREDS is satisfied --- namely, the textbook used in sections of C3360 that meet on Monday in the Fall of 1985.</Paragraph> </Section> <Section position="13" start_page="192" end_page="192" type="metho"> <SectionTitle> EVALUATION COMPONENT </SectionTitle> <Paragraph position="0"> The analysis component proposes a set of potential associations of the elliptical fragment with elements of IS' s underlying task-related plan. The evaluation component employs focusing strategies to select what it believes to be the interpretation intended by 13 --- namely, that interpretation most relevant to the current focus of attention in the dialogue.</Paragraph> <Paragraph position="1"> We employ the notion of focus domains in order to group finely grained actions and associated plans into more general related structures. A focus domain consists of a set of actions, one of which is an ancestor of all other actions in the focus domain and is called the root of the focus domain. If as action is a member of a focus domain and that action is not the root action of another focus domain, then all the actions contalnad in the plan associated with the first action are also members of the focus domain.</Paragraph> <Paragraph position="2"> (This is similar to Grosz's focus spaces and the notion of an object being in implicit focus.) The use of focus domains allows the groupin8 together of those actions that appear to be at approximately the sa~me level of Impllcit focus when a plan is explicitly focused. For example, the actions of learnlr~ from a particular teacher, learning the material in a given text, and attend-Ing class will all reside at the same focus level within the expanded plan for earning credit in a course. The action of going to the cashler's office to pay one's tuition also appears within this expanded plan; however it will reside at a different focus level since it does not come to mind nearly so readily when one thinks about taking a course.</Paragraph> <Paragraph position="3"> The following are two of seven focusing rules used to select the association deemed most relevant to the existing plan context.</Paragraph> <Paragraph position="4"> \[F1\] Within the current focus space, prefer assoclatlons which occur within the current focused plan.</Paragraph> <Paragraph position="5"> IF2\] Within the current focus space and current focused plan, prefer associations within the actions to achieve the most recently considered action.</Paragraph> </Section> <Section position="14" start_page="192" end_page="192" type="metho"> <SectionTitle> DISCOURSE GOALS </SectionTitle> <Paragraph position="0"> We have analyzed dialogues from several different domains and have identified eleven discourse goals which occur during information-seeking dialogues and which may be accomplished via elliptical fragments. Three exemplary discourse goals are \[;\] Obtaln-In/ormatlon: IS requests Ir.formatlon relevant to constructing the underlying task-related plan or relevant to formulating an answer to a question posed by IP.</Paragraph> <Paragraph position="1"> \[2\] Obtaln-Corroboration: IS expresses surprise regarding some proposition P and requests elaboration upon and justification of it.</Paragraph> <Paragraph position="2"> \[33 Seek-Clarify-questlon: IS requests information relevant to clarifying a question posed by ZP.</Paragraph> </Section> <Section position="15" start_page="192" end_page="193" type="metho"> <SectionTitle> ANTICIPATED DISCOURSE GOALS </SectionTitle> <Paragraph position="0"> When IS m~es an utterance, he is attempting to accomplls~ a discourse goal ; this discourse goal may in turn predict other suDsequent discourse goals for IS. For e~ple, if I~ asks a question, one anticipates that IS may want to expand upon his question. Similarly, utterances made by IP suggest dlsoourse goals for LS. These Aatlcipated Discourse Goals provide very strong expectations for IS and may often be accomplished implicitly as well as explicitly.</Paragraph> <Paragraph position="1"> The discourse ~als of the previous section also serve as anticipated discourse goals. Three additional anticipated discourse goals appear tO play a major role in determining how elliptical fragments are interpreted. One such anticipated discourse ~al is: Accept-Questlon: IP has posed a question to IS; IS must now accept the question either explicitly, implicitly, or indicate that he does not as yet accept it.</Paragraph> <Paragraph position="2"> Normally dialogue participants accept such questions implicitly by proceding to answer the question or to seek information relevant to formulating an answer. However IS may refuse to accept the question posed by IP because he does not understand It (perhaps he is unable to identify some of the entities mentioned in the question) or because he is surprised by it. This leads to discourse goals such as seeking confirmation, seeking the identity of an entity, seeking clarification of the posed question, or expressing surprise at the question.</Paragraph> </Section> <Section position="16" start_page="193" end_page="193" type="metho"> <SectionTitle> THE DISCOURSE STACK </SectionTitle> <Paragraph position="0"> The discourse stack contains anticipated discourse goals which IS is expected to pursue.</Paragraph> <Paragraph position="1"> Anticipated discourse goals are pushed onto or popped from the stack as a result of utterances made by IS and IP. We have identified a set of stack processing rules which hold for simple utterances. Three examples of such stack process-Ing rules are: \[SP1\]When IP asks a question of IS, Answer-Question and Accept-Questlon are pushed onto the discourse stack.</Paragraph> <Paragraph position="2"> \[SP2\]When IS poses a question to IP, Expand-Question is pushed onto the discourse stack. Once IP begins answering the question, the stack is popped up to and including the Expand-Questlon discourse goal.</Paragraph> <Paragraph position="3"> \[SP3\]When IS's utterance does not pursue a goal sugEested by the top entry on the discourse stack, this entry is popped from the stack.</Paragraph> <Paragraph position="4"> The motivation for these rules is the following. When IP asks a question of IS, IS is first expected to accept the question, either implicitly or expllcltly, and then answer the question. Upon posing a question to ~P, IS is expected to expand upon this question with subsequent utterances or wait u~tll IP produces an answer to the question. Alt~oug~ the strongest expectations are that IS will pursue a goal suggested by the top element of the discourse stack, this anticipated discourse goal can be passed over, at which point it no longer sug~sts expectations for utterances.</Paragraph> </Section> <Section position="17" start_page="193" end_page="193" type="metho"> <SectionTitle> DISCOURSE INTERPRETATIOM COMPOM~T </SectionTitle> <Paragraph position="0"> The discourse component employs discourse expectation rules and discourse goal rules. The discourse expectation rules use the discourse stack to suggest possible discourse goal s for L~ and activate the associated discourse goal rules.</Paragraph> <Paragraph position="1"> These disnourse goal rules ttse the plan-analysis component to help determine the best interpretation of the fra~entar7 utterance relevant to the sug~sted discourse goal. If a discourse goal rule succeeds in producing an interpretation, then the discourse component identifies that discourse goal and its associated interpretation as its understanding of the utterance.</Paragraph> <Paragraph position="2"> I. Discourse Expectation Rules The top element of the discourse stack activates the discourse expectation rule with which it is associated; this rule in turn suggests discourse goals which the information-seeker' s utterance may pursue and activates these discourse goal rules. The following is an example of a discourse expectation rule: \[DE1\]If the top element of the discourse stack is Answer-Question, then I. Apply discourse goal rule DG-Answer-Quest to determine if the elliptical fragment is being used to accomplish the discourse goal of answering the question.</Paragraph> <Paragraph position="3"> 2. If no interpretation is produced, apply rule S-Suggest-Answer-Questlon to determine if the elliptical fragment is being used to accomplish the discourse goal of suggesting an answer to the question.</Paragraph> <Paragraph position="4"> 3. If no interpretation is produced, apply discourse goal rule DG-Obtaln-Info to determine if the elliptical fragment is being used to accomplish the discourse goal of seeking information in order to construct an answer to the posed question.</Paragraph> <Paragraph position="5"> Once IS understands the question posed to him, IP's strongest expectation is that IS will answer the question; therefore first preference is given to interpretations which accomplis~ this goal. If IS does not immediately answer the question, then we expect a cooperative dialogue participant to work towards answering the question. This entails gathering information about the underlying task-related plan in order to construct a response.</Paragraph> </Section> <Section position="18" start_page="193" end_page="194" type="metho"> <SectionTitle> 2. Discourse Goal Rules </SectionTitle> <Paragraph position="0"> Discourse goal rules determine if an elllptlcal fragment accomplishes the associated discourse goal and, if so, produce the appropriate interpretation of the fragment. These discourse goal rules use the plan-analysls component to help determine the best interpretation of the frasmentary utterance relevant to the suggested discourse goal. However these interpretations are not actual representations of surface speech acts; instead they generally indicate elements of the plan whose values the speaker is querying or specifying. In many respects, this provides a better &quot;understanding&quot; of the utterance since it describes what the speaker is trying to accompli~. null The following is an example of a rule associated with a discourse goal suggested by the stack entry Accept-Response; the latter is pushed onto the discourse stack when IP responds to a question posed by IS.</Paragraph> <Paragraph position="1"> Obtain-Corrob The discourse component calls the plan-analysis component to associate the elliptical fragment with a term STERM or a conjunction of propositions SPREDS in IS's underlying task-related plan. If IP believes it is mutually believed that IS already knows IP's beliefs about the value of the term STERM or the truth of the propositions $PREDS, then identify the elliptical fragment as accomplishing the discourse ~al of expressing surprise at the preceding response; in partlcular, IS is surprised at the known values of STEP=M or SPREDS in li@~t of the new informet.lon provided by IP' s preceding response and the known aspect queried by IS's fragment. null The followin8 is one of several rules associated with the discourse ~al Answer-Question. J~Ct&quot; Answer- Oues t--~.</Paragraph> <Paragraph position="2"> If the elliptical fragment terminates with a period, then the discourse component calls the plan-analysls component to associate the elliptical frasment with a conjunction of propositions SPEEDS in IS's underlying task-related plan. If successful, interpret the elliptical fragment as answerlr~ &quot;Yes&quot;, with the restriction that the propositions SPREDS be satlsfi~d in the underlyin~ .i ~n.</Paragraph> </Section> class="xml-element"></Paper>