File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/90/p90-1010_metho.xml
Size: 20,423 bytes
Last Modified: 2025-10-06 14:12:37
<?xml version="1.0" standalone="yes"?> <Paper uid="P90-1010"> <Title>Mixed Initiative in Dialogue: An Investigation into Discourse Segmentation</Title> <Section position="3" start_page="70" end_page="70" type="metho"> <SectionTitle> 2 Rules for the Allocation </SectionTitle> <Paragraph position="0"> and Transfer of Control We use the framework for the allocation and transfer of control of Whittaker and Stenton\[WS88\]. The analysis is based on a classification of utterances into 4 types 5. These are:</Paragraph> </Section> <Section position="4" start_page="70" end_page="71" type="metho"> <SectionTitle> * UTTERANCE TYPES -- ASSERTIONS: Declarative utterances used </SectionTitle> <Paragraph position="0"> to state facts. Yes and No in response to a question were classified as assertions on the basis that they are supplying information. null -- COMMANDS: Utterances intended to instigate action. Generally imperative form, but could be indirect such as My suggestion would be that you do .....</Paragraph> <Paragraph position="1"> -QUESTIONS: Utterances which are intended to elicit information, including indirect forms such as I was wondering whether I should ....</Paragraph> <Paragraph position="2"> -- PROMPTS: Utterances which did not express propositional content, such as Yeah, Okay, Uh-huh ....</Paragraph> <Paragraph position="3"> Note that prompts are in direct contrast to the other options that a participant has available at any point in the discourse. By indicating that the speaker does not want the floor, prompts function on a number of levels, including the expression of understanding or agreement\[Sch82\].</Paragraph> <Paragraph position="4"> The rules for the allocation of control are based on the utterance type classification and allow a dialogue to be divided into segments that correspond to which speaker is the controller of the segment.</Paragraph> </Section> <Section position="5" start_page="71" end_page="71" type="metho"> <SectionTitle> * CONTROL RULES UTTERANCE ASSERTION COMMAND QUESTION </SectionTitle> <Paragraph position="0"> The definition of controller can be seen to correspond to the intuitions behind the term INITI-</Paragraph> </Section> <Section position="6" start_page="71" end_page="71" type="metho"> <SectionTitle> ATING CONVERSATIONAL PARTICIPANT (ICP), who </SectionTitle> <Paragraph position="0"> is defined as the initiator of a given discourse segment\[GS86\]. The OTHER CONVERSATIONAL PARTICIPANT(S), OCP, may speak some utterances in a segment, but the DISCOURSE SEGMENT PUR-POSE, must be the purpose of the ICP. The control rules place a segment boundary whenever the roles of the participants (ICP or OCP) change. For example: null Abdication Example E: &quot;And they are, in your gen youql find that they've relo-Cated into the labelled common area&quot; (ASSERT - E control) C: &quot;That's right.&quot; (PROMPT - E control) E: &quot;Yeah&quot; (PROMPT - E abdicates control) CONTROL SHIFT TO C --C: &quot;I've got two in there. There are two of them.&quot; (ASSERT - C control) E: &quot;Right&quot; (PROMPT - C control) C: &quot;And there's another one which is % RESA&quot; (ASSERT - C control) E: &quot;OK urn&quot; (PROMPT - C control) C: &quot;VS&quot; (ASSERT- C control) E: &quot;Right&quot; (PROMPT - C control) C: &quot;Mm&quot; (PROMPT - C abdicates control) CONTROL SHIFT TO E ----E: &quot;Right and you haven't got - I assume you haven't got local labelled common with those labels&quot; (QUESTION - E control) Whittaker and Stenton also performed a post-hoe analysis of the segment boundaries that are defined by the control rules. The boundaries fell into one of three types: * CONTROL SHIFT TYPES - ABDICATION: Okay, go on.</Paragraph> <Paragraph position="1"> - REPETITION/SUMMARY: That would be my recommendation and that will ensure that you get a logically integral set of files. -INTERRUPTION: It is something new though urn.</Paragraph> <Paragraph position="2"> ABDICATIONS 6 correspond to those cases where the controller produces a prompt as the last utterance of the segment. The class REPETI-TION/SUMMARY corresponds to the controller producing a redundant utterance. The utterance is either an exact repetition of previous propositional content, or a summary that realizes a proposition, P, which could have been inferred from what came before. Thus orderly control shifts occur when the controller explicitly indicates that s/he wishes to relinquish control. What unifies ABDICATIONS and REPETITION/SUMMARIES is that the controller supplies no new propositional content. The remaining class, INTERRUPTIONS, characterize shifts occurring when the noncontroller displays initiative by seizing control. This class is more general than other definitions of Interruptions. It properly contains cross-speaker interruptions that involve topic shift, similar to the true-interruptions of Grosz and Sidner\[GS86\], as well as clarification subdialogues\[Sid83, LA90\].</Paragraph> <Paragraph position="3"> This classification suggests that the transfer of control is often a collaborative phenomenon. Since a noncontroller(OCP), has the option of seizing control at any juncture in discourse, it would seem that controllers(ICPs), are in control because the noncontroller allows it. These observations address problems raised by Grosz and Sidner, namely how ICPs signal and OCPs recognize segment boundaries. The claim is that shifts of control often do not occur until the controller indicates the end of a discourse segment by abdicating or producing a repetition/summary.</Paragraph> </Section> <Section position="7" start_page="71" end_page="72" type="metho"> <SectionTitle> 3 Control Segmentation and Anaphora </SectionTitle> <Paragraph position="0"> To determine the relationship between the derived control segments and ATTENTIONAL STATE we looked at the distribution of anaphora with respect to the control segments in the ADs. All data were analysed statistically by X 2 and all differences cited are significant at the 0.05 level. We looked at all anaphors (excluding first and second person), and grouped them into 4 classes.</Paragraph> <Paragraph position="1"> * Classes of Anaphors - 3RD PERSON: it, they, them, their, she, he, her, him, his -- ONE/SOME, one of them, one of those, a new one, that one, the other one, some - DEICTIC: Noun phrases, e.g. this, that, this NP, that NP, those NP, these NP - EVENT: Verb Phrases, Sentences, Seg null ments, e.g. this, that, it The class DEICTIC refers to deictic references to material introduced by noun phrases, whereas the class EVENT refers to material introduced clausally.</Paragraph> <Section position="1" start_page="72" end_page="72" type="sub_section"> <SectionTitle> 3.1 Hierarchical Relationships </SectionTitle> <Paragraph position="0"> The first phenomenon we noted was that the anaphora distribution indicated that some segments are hierarchically related to others 7. This was especially apparent in cases where one discourse participant interrupted briefly, then immediately passed control back to the other.</Paragraph> <Paragraph position="1"> Interrupt/Abdicate 1 A: ... the only way I could do that was to take a to take a one third down and to take back a mortgage (ASSERTION)</Paragraph> </Section> </Section> <Section position="8" start_page="72" end_page="73" type="metho"> <SectionTitle> -INTERRUPT SHIFT TO B--- </SectionTitle> <Paragraph position="0"> 2. B: When you talk about one third put a number on it (QUESTION) 3. A: uh 15 thou (ASSERTION, but response) 4. B: go ahead (PROMPT) ----ABDICATE SHIFT BACK TO .4.5. A: and then I'm a mortgage baz.k for 36 The following example illustrates the same point. Interrupt/Abdicate 2 1. A: The maximum amount ... will be $400 on THEIR tax return. (ASSERTION) INTERRUPT SHIFT TO B 7Similar phenomena has been noted by many researchers in discourse including\[Gro77, Hob79, Sid79, PHg0\]. 2. B: 400 for the whole year? (QUESTION) 3. A: yeah it'll be 20% (ASSERTION, but response) 4. B: um hm (PROMPT) -----ABDICATE SHIFT BACK TO A5. A: now if indeed THEY pay the $2000 to your wife .... The control segments as defined would treat both of these cases as composed of 3 different segments. But this ignores the fact that utterances (1) and (5) have closely related propositional content in the first example, and that the plural pronoun straddles the central subsegment with the same referents being picked out by they and their in the second example. Thus we allowed for hierarchical segments by treating the interruptions of 2-4 as subsegments, and utterances 1 and 5 as related parts of the parent segments. All interruptions were treated as embeddings in this way. However the relationship of the segment after the interruption to the segment before must be determined on independent grounds such as topic or intentional structure.</Paragraph> <Section position="1" start_page="72" end_page="73" type="sub_section"> <SectionTitle> 3.2 Distribution </SectionTitle> <Paragraph position="0"> Once we extended the control framework to allow for the embedding of interrupts, we coded every anaphor with respect to whether its antecedent lay outside or within the current segment. These are labelled X (cross segment boundary antecedent) NX (no cross segment boundary), in Figure 1. In addition we break these down as to which type of control shift occurred at the previous segment boundary.</Paragraph> <Paragraph position="1"> We also looked at the distribution of anaphora in the Support ADs and found similar results.</Paragraph> <Paragraph position="2"> For both dialogues, the distribution of anaphors varies according to which type of control shift occurred at the previous segment boundary. When we look at the different types of anaphora, we find that third person and one anaphors cross bound- null aries extremely rarely, but the event anaphors and the deictic pronouns demonstrate a different pattern. What does this mean? The fact that anaphora is more likely to cross segment boundaries following interruptions than for summaries or abdications is consistent with the control principles. With both summaries and abdications the speaker gives an explicit signal that s/he wishes to relinquish control. In contrast, interruptions are the unprompted attempts of the listener to seize control, often having to do with some 'problem' with the controller's utterance. Therefore, interruptions are much more likely to be within topic. But why should deixis and event anaphors behave differently from the other anaphors? Deixis serves to pick out objects that cannot be selected by the use of standard anaphora, i.e. we should expect the referents for deixis to be outside immediate focus and hence more likely to be outside the current segment\[Web86\]. The picture is more complex for event anaphora, which seems to serve a number of different functions in the dialogue. It is used to talk about the past events that lead up to the current situation, I did THAT in order to move the place. It is also used to refer to sets of propositions of the preceding discourse, Now THAT'S a little background (cf \[Web88\]). The most prevalent usei however, was to refer to future events or actions, THAT would be the move that I would make - but you have to do IT the same day.</Paragraph> </Section> </Section> <Section position="9" start_page="73" end_page="73" type="metho"> <SectionTitle> SUMMARY EXAMPLE </SectionTitle> <Paragraph position="0"> A: As far as you are concerned THAT could cost you more .... what's your tax bracket? (QUESTION) B: Well I'm on pension Harry and my wife hasn't worked at all and ..(ASSERT/RESP) A: No reason at all why you can't do THAT. (ASSERTION) ---SUMMARY 3HIFT to B ....</Paragraph> <Paragraph position="1"> 13: See my comment was if we should throw even the $2000 into an IRA or something for her. (ASSERTION) --REPETITION SHIFT to A.</Paragraph> <Paragraph position="2"> A: You could do THAT too. (ASSERTION) Since the task in the ADs is to develop a plan, speakers use event anaphora as concise references to the plans they have just negotiated and to discuss the status and quality of plans that have been suggested. Thus the frequent cross-speaker references to future events and actions correspond to phases of plan negotiation\[PHW82\]. More importantly these references are closely related to the control structure. The example above illustrates the clustering of event anaphora at segment boundaries. One discourse participant uses an anaphor to summarize a plan, but when the other participant evaluates this plan there may be a control shift and any reference to the plan will necessarily cross a control boundary. The distribution of event anaphora bears this out, since 23/25 references to future actions are within 2 utterances of a segment boundary (See the example above). More significantly every instance of event anaphora crossing a segment boundary occurs when the speaker is talking about future events or actions.</Paragraph> <Paragraph position="3"> We also looked at the TODs for instances of anaphora being used to describe a future act in the way that we observed in the ADs. However, over the 938 turns in the TODs, there were only 18 instances of event anaphora, because in the main there were few occasions when it was necessary to talk about the plan. The financial ADs had 45 event anaphors in 474 utterances.</Paragraph> </Section> <Section position="10" start_page="73" end_page="74" type="metho"> <SectionTitle> 4 Control and Collaborative </SectionTitle> <Paragraph position="0"> To explore the relationship of control to planning, we compare the TODs with both types of ADs (financial and support). We would expect these dialogues to differ in terms of initiative. In the ADs, the objective is to develop a collaborative plan through a series of conversational exchanges. Both discourse participants believe that the expert has knowledge about the domain, but only has partial information about the situation. They also believe that the advisee must contribute both the problem description and also constraints as to how the problem can be solved. This information must be exchanged, so that the mutual beliefs necessary to develop the collaborative plan are established in the conversation\[Jos82\]. The situation is different in the TODs. Both participants here believe at the outset that the expert has sufficient information about the situation and complete and correct knowledge about how to execute the Task. Since the apprentice has no need to assert information to change the expert's beliefs or to ask questions to verify the expert's beliefs or to issue commands, we should not expect the apprentice to have control. S/he is merely present to execute the actions indicated by the knowledgeable participant.</Paragraph> <Paragraph position="1"> The differences in the beliefs and knowledge states of the participants can be interpreted in the terms of the collaborative planning principles of Whittaker and Stenton\[WS88\]. We generalize the principles of INFORMATION QUALITY and PLAN QUALITY, which predict when an interrupt should occur.</Paragraph> <Paragraph position="2"> * INFORMATION QUALITY: The listener must believe that the information that the speaker has provided is true, unambiguous and relevant to the mutual goal. This corresponds to the two rules: (A1) TRUTH: If the listener believes a fact P and believes that fact to be relevant and either believes that the speaker believes not P or that the speaker does not know P then interrupt; (A2)AMBIGUITY: If the listener believes that the speaker's assertion is relevant but ambiguous then interrupt.</Paragraph> <Paragraph position="3"> * PLAN QUALITY: The listener must believe that the action proposed by the speaker is a part of an adequate plan to achieve the mutual goal and the action must also be comprehensible to the listener. The two rules to express this are: (B1)EFFECTIVENESS: If the listener believes P and either believes that P presents an obstacle to the proposed plan or believes that P * is part of the proposed plan that has already been satisfied, then interrupt; (B2) AMBIGU-ITY: If the listener believes that an assertion about the proposed plan is ambiguous, then interrupt.</Paragraph> <Paragraph position="4"> These principles indirectly proyide a means to ensure mutual belief. Since a participant must interrupt if any condition for an interrupt holds, then lack of interruption signals that there is no discrepancy in mutual beliefs. If there is such a discrepancy, the interruption is a necessary contribution to a collaborative plan, not a distraction from the joint activity.</Paragraph> <Paragraph position="5"> We compare ADs to TODs with respect to how Three things are striking about this data. As we predicted, the distribution of control between expert and client is completely different in the ADs and the TODs. The expert has control for around 90% of utterances in the TODs whereas control is shared almost equally in the ADs. Secondly, contrary to our expectations, we did find some instances of shifts in the TODs. Thirdly, the distribution of interruptions and summaries differs across dialogue types. How can the collaborative planning principles highlight the differences we observe? There seem to be two reasons why shifts occur in the TODs. First, many interruptions in the TODs result from the apprentice seizing control just to indicate that there is a temporary problem and that plan execution should be delayed.</Paragraph> <Paragraph position="6"> TASK INTERRUPT 1, A is the Instructor A: It's hard to get on (ASSERTION)</Paragraph> </Section> <Section position="11" start_page="74" end_page="74" type="metho"> <SectionTitle> -----INTERRUPT SHIFT TO B </SectionTitle> <Paragraph position="0"/> </Section> <Section position="12" start_page="74" end_page="75" type="metho"> <SectionTitle> -ABDICATE SHIFT TO A-- </SectionTitle> <Paragraph position="0"> A: All right. Now there's a little blue cap ..</Paragraph> <Paragraph position="1"> Second, control was exchanged when the execution of the task started to go awry.</Paragraph> <Paragraph position="2"> TASK INTERRUPT 2, A is the Instructor A: And then the elbow goes over that ... the big end of the elbow. (COMMAND)</Paragraph> </Section> <Section position="13" start_page="75" end_page="75" type="metho"> <SectionTitle> ---INTERRUPT SHIFT TO B~ </SectionTitle> <Paragraph position="0"> B: You said that it didn't fit tight, but it doesn't fit tight at all, okay ... (ASSERTION) A: Okay (PROMPT) B: Let me try THIS - oo1~ - again(ASSERTION) The problem with the physical situation indicates to the apprentice that the relevant beliefs are no longer shared. The Instructor is not in possession of critical information such as the current state of the apprentice's pump. This necessitates an information exchange to resynchronize mutual beliefs, so that the rest of the plan &quot;~ ~,v be successfully executed. However, since control is explicitly allocated tothe instructor in TODs, there is no reason for that participant to believe that the other has any contribution to make. Thus there are fewer attempts by the instructor to coordinate activity, such as by using summaries to synchronize mutual beliefs. Therefore, if the apprentice needs to make a contribution, s/he must do so via interruption, explaining why there are many more interruptions in these dialogues. 9 In addition, the majority of Interruptions (73%) are initiated by apprentices, in contrast to the ADs in which only 29% are produced by the Clients.</Paragraph> <Paragraph position="1"> Summaries are more frequent in ADs. In the ADs both participants believe that a plan cannot be constructed without contributions from both of them.</Paragraph> <Paragraph position="2"> Abdications and summaries are devices which allow these contributions to be coordinated and participants use these devices to explicitly set up opportunities for one another to make a contribution, and to ensure mutual bellefs The increased frequency of summaries in the ADs may result from the fact that the participants start with discrepant mutual beliefs about the situation and that establishing and maintaining mutual beliefs is a key part of the ADs.</Paragraph> </Section> class="xml-element"></Paper>