<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2196">
  <Title>l)iscourse and Deliberation: Testing a Collaborative Strategy</Title>
  <Section position="6" start_page="1207" end_page="1210" type="concl">
    <SectionTitle>
4 Results: Explicit Warrant
</SectionTitle>
    <Paragraph position="0"> This section discusses the results of compm'ing the Explicit-Wmranl discourse strategy with the All-Implicit discotuse slrategy to determine when each slralegy is BENEH(:IAI,. We test 4 factors outlined in figure 1 : when the wal'rlull is salient or nol, when the w~u'falll is required for the task or not, when the cosls of retrieval and communication vary, and when retrieval is indeterufinate.</Paragraph>
    <Paragraph position="1"> Dilli~rences in performmlce between the Explicit-Warrallt slrategy and tile All-hnplicit slrategy ~ue shown via a I)IFFI2RI!NCE I'LOT such as ligme 3. In figure 3 pcrform~mce differences are plolled on the Y-axis and AWM seltings are shown on the X-axis. If the plot is above file dotted line for 2 or more AWM settings, then the Explicit-Warrant strategy may be IIENt{FI(:IAI, depending on whether the differences are signilic,'mt by the KS lest. Each point represents the difference in the means of 100 runs of each stralegy at a l)mticul~u&amp;quot; AWM selling. Those plots summarize the results of 1800 simulated dialogues: 100 lbr each AWM setting lot each stralegy.</Paragraph>
    <Paragraph position="2">  lion costs c~ul dominate other costs in dialogues. Strategy i is two Explicit-Warrant agents ,'rod strategy 2 is two All-hnplicit agents: Task = Stmld,'u'd, commcost = 10, infcost = 0, retcost = 0 in compm'ison with tile All-hnplicit strategy, if relrieval fi'om memory is fi'ee (KS 3,4,5 &gt; .19, p &lt; .05). This is because making the wammt salient displaces information about other pieces of furniture when agents m'e attention-limited. In the St,'uld~u'd t&amp;sk, agents m'en't required to sh,'ue beliefs about the value of a proposed, so remembering what pieces they have is more importmlt than remembering their value.</Paragraph>
    <Paragraph position="3"> However, figure 4 shows that Explicit-Wm'rm~t is benelici~d when retrieval is one tenth tile cost of communication :rod inference. By AWM v,'dues of 3, performance  wilh Explicit-W~u'rant is belier than All-Implicit because lhe beliefs necess~n'y for deliberation are made salienl with each proposal (KS lk)r AWM of 3 and above &gt; .23, p &lt; .01). At AWM parameter settings el' 16, where agenls have lhe ability to search all their beliefs lk)r warrants, the saving in processing time is substantial. Again at the lowest AWM seltings, the slrategy is not beneficial because it displaces information about other pieces fronl AWM. However in figure 4, in conlr&amp;st wilh ligure 3, retrieval has an associated cost. Thus Iho savings in relriowtl balance out wilh the loss of raw score so that tile strategy is nol I\]I!TRIMENTAI. ()ther experiments show that even when the relative cost of retrieved is .0001, that Explicit-Wanant is still benelicial at AWM settings of I 1 ~md 16 (KS Ik/r 11,16 &gt; .23, p &lt; .01).</Paragraph>
    <Paragraph position="4"> Explicit Warrant is detrimental if Communication is Expensive If we ch~mge the relative cosls of the dillerent processes in the siluation, we change whether a strategy is benelicial. Figure 5 shows that if connnnnication cost is 10, ~md inlerence and rolrieval ~u'e li'ee, then the Explicit-Wlu'i'~nll strategy is DI,ITRIMI\]N'IAL (KS for AWM 1 to 5 &gt; .23, p&lt; .01). This is because the Explicit-Warr~mt slralegy increases the number of ntter~mces required to perform Ihe task; it doubles the number of messages in every proposal. If communication is expensive compared to retrieval, communication cost can dominate the other benelits.</Paragraph>
    <Paragraph position="5"> l!;xplicit Warrant Achieves a High Level of</Paragraph>
    <Section position="1" start_page="1209" end_page="1210" type="sub_section">
      <SectionTitle>
Agreement
</SectionTitle>
      <Paragraph position="0"> If we change lhe dolinition of success in the ta:sk, we change whether a slrategy is benelicial. When the l&amp;sk is Zero-Nouiilatching-Beliefs, the Explicit-W~u'ranl strategy is beneficial oven if retrieval is fiee (KS &gt; .23 for AWM ll'onl 2 lo 11, p &lt; .01)The warranl inl\]Jrnlation that is redundantly provided is exactly tilt inlk)rmation that is needed in order to achieve inatching beliel\s about Ihe warranls for intended actions. Tile strategy virtually gu~u~nllees thai the agenls will agree on the re&amp;sons l(/l' carrying onl a particular course of action. The fact that relrieval is indclcrminate produces this effect; a simihit resnll is oblained when wm'r~mls are required and relriewll costs someihing.</Paragraph>
      <Paragraph position="1"> To my great surprise, Ihe benelicial effect of Explicit-W~uralll for the Zero-NonMatching-Beliefs task is so robust thal even if communication cost is 10 and reirieval and inference are fl+ee, Explicil-Warrant is better than AII-hnplicit at AWM of 3 *.. 11 (KS &gt; .23, p &lt; .0l). See ligure 6. In other words, even when every extra WARRANT message incurs a penalty of 10 poinls, if the task is Zero-NonMatching-Beliefs, agents using Explicit-W~u'rant do belier. Contrasl ligure 6 with the Standard t~tsk ~md s~une cost p~n'amelers in 5.</Paragraph>
      <Paragraph position="2"> These result suggesls thai including w~u'rants is highly effective when agents must agree on a specilic w~ua~u/t, if lhey are atlenlion-limited to any extent.</Paragraph>
      <Paragraph position="3"> 5 (~tlnclllsion This paper has discussed an iuslaiice of a general probloin in tile design of convorsalional agents: when lo inchido optional infornlation. We presented and lested a nunlber of hypotheses aboul the factors lhat conlribnle  All-Implicit agents: qlisk = Zero-Nonmatching-Bcliel~s, commcost = 10, inl~;ost = (/, retcost = 0 to tile decision of when Io include a w:urant in a proposed. We showed thai w~ur~mts ~u'e useful when the task requires agreement on the warrant, when the win'rant is not currently s~dient, when retrieval of tile w~u-r~mt is indeterminate, or when retriewd has some associated cost, and that warranls hinder perfornlance if communication is costly ~uld if tim w~urant c~ul displace inli.)rnlation that is needed to complete the task, e.g. when AWM is very limited and wm'r\[mts ~ue not required to be shared.</Paragraph>
      <Paragraph position="4"> Tile method used here is a new experimental methodelegy for computational linguistics that supports testing hypotheses about benelici~d disconrse strategies \[Carletta, 1992; Pollack and Ringuelle, 1990\]. The Design-World environment is b~tsed on a cognitive model of limited attention ~md supports experimenls on the interaction of discourse strategies with agents' cognitive limitations. The use of the method and the focns of lhis wtnk are novel: previous work has l~)CliSed Oil determining nnderlying mechanisnls PS~r cooperative strategies rather than on investigating when a slrategy is elIective.</Paragraph>
      <Paragraph position="5"> To my knowledge, no previous work on di;dogue l/~ts ever argued that conversational agents' resonroe limits are a lnajor factor in determining C/IIective conversational strategies in collaboration. Tim resulls presented here suggest that cooperative strategies cannot be delhied in the abslracl, but cooperation arises from the interaction of two agents in dialogue. If one agent has limited working memory, then the ()thor agenl can make the di~doguc go more slnoothly by adopting a strategy that makes deliberative premises salient. In other words, slrategies ~ue cooperative for certain conversational p;u'tners, in/der particular task delinitions, lor p~uticul~u communicalion situations.</Paragraph>
      <Paragraph position="6"> Here we compared two discourse strategies: All-hnplicit ~ul(l Explicit-Warr~mh Explicit-W;uranl is a type of discourse stralegy called ~m Attelition strategy in \[W;dkel; 1993\] because its main lunction is to manipulate agents' altenlional slate. Elsewhere we show  that (1) some IRU strategies are only beneficial when inferential complexity is higher Ihall in the Standard &amp;quot;l,u,~k \[R~unbow and Walker, 1994; Walker, 1994al; (2) IRUs that make intL'rences explicit can help inlbrence limited agents perlorm as well as logic;ally omniscient ones I Walker, 199311.</Paragraph>
      <Paragraph position="7"> Although much work remains to be done, there is reason to believe that these results are (Iomsdn independent. The simplicity of the Design-World task inemls thai its ,',;trllCttlr(.; is a stlbCOlllpOl/enl of malty other task,,,;. The model of limited resources is cognilively based, but the cosl pmameters support modeling diflcrent ageil\[ archilectures, and we exl)h)red the effects of dilli:rent cost l)ar~unelers. The Exl)licil-WmTant strategy is b~used on simple relationships between different ihcls which we would expect to occur in any domain, i.e. the lact that some belief csm be ilsed sis a WARRANT fi)r accepting a l)roposal should occur in sdmost any task. Future work should extend these results, showing that a 'cooperative strategy' need not always be 'coopcralive', sut(l investigate additional factors thai determine when strategies me effective.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>