<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-4207">
  <Title>Recorlstructirlg Spati~l hm~ge from Natural Language Texts</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Tile Approach
</SectionTitle>
    <Paragraph position="0"> The esscn('(~ of our approach is its fo}}ows: a ~\[(qillillg of thP llal(l(';ll lktll{4111tg(' rxl)rrssions ILs the constraints among tit(' sl)atiM era;ties  worhl model.</Paragraph>
    <Paragraph position="1"> We regard the worm its ml i~ssembly of the spatial ent, iti(~s, and r(q)resent each entity a.s the (:onfltimd;i\[m of its pl'ototylm lind the real wdues t)}&amp;quot; il:s t)itl';ttlltlt,(!l',q. W(! \[n'eplu'e the gl'ap}tic object, s corr(!sponding to tim prototypes. Each graphic (d)ject is represented by the parameters prescribing the details of it. The pa, rametcrs prescribe its }ot:ation, orientation, and extmd,. Now the t~sk becomes to gen(,'rate the graphic objects corresponding to the described entities }tll( |to (|(!tCl'lllill(? th(~ p}Ll.'itltl(!tCl' values pres(tl'ibing thmn.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
tem SPRINT
</SectionTitle>
      <Paragraph position="0"> It is difficult to deter,nine the tmrameter values directly front the natural language descriptions.</Paragraph>
      <Paragraph position="1"> beeattse of the I)artiality of the information and tim vagueness about the sttatial rehttions alnollg tile entities. So. at first, we extract such information as the qualitative spatial constraints among the spatial attributes of the entities, and then.</Paragraph>
      <Paragraph position="2"> interpret these COllstrailltS alld calcuhtte the t&gt;a: ranleter values. This process is shown in figure 1.</Paragraph>
      <Paragraph position="3"> Given ~ text, SPRINT makes a sm'faee ease structure using the lexical information. Each entity is described ms a noltlt. Next, SPRINT extracts spatial constraints about the entities by analyzing the related words in the case. structure. At this time. SPRINT also extracts the sequence of the information references fl'om the lexical mtbrmation as dependencies, which are used as cues in the calculation of the paranwters. null At the next stage, the extracted qualitative constraints are intertn'eted as the nmnerical constraints among the e,ltity paranletc.rs. These nulllerical COllstrailltS :4re repl'esented }kS the COlllbinatiolt of the primitive constraints. Tit(! tmten tial energy function is one of such primitives, and this is an efficient method to treat the vagllelteSS in the constraints. Other primitives are the tot mlogical constraints and the regions. The potential energy flmction is a kind of the cost fllnetiolls which t~tkes all related paranmters and output the ('()st. The less the wthm of the potential (mergy flmction, the more credit the combinatiml of the gemnetric parameters gains. Using the gradient descendent method, the solution with nlininnnn cost is calculated. The t)otcntial (mc.rgy flmction 1)rovides a means for accmnulating fl'om fragnmntal'y infornuttion. (Tit(; basic i(te~ of the pote,ltial ene.rgy fm|etion is reported in</Paragraph>
    </Section>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 The Example
</SectionTitle>
    <Paragraph position="0"> Suptlose that the fi)llowing sentences are the inputs to SPRINT.</Paragraph>
    <Paragraph position="1">  (1) Fill V~i0'Dq,~E~at,fI.g;0%b/oo J (There is a fount;tin at the center of till, Yalnmshita Park.) (2) \[,fI*a) &amp; ~_ 70~,65v,\[$ia)~a)lrq~. 5 ~:)klll)lt,~ ~&amp; ~ &amp;:0~ ~ 70. j (Front that place, you can sec Hikawa-maru (a slfip) Iwyond the fence of the park.) (3) V).k JIl .,ic ~ ,~i N l,: l~. &amp;quot;q&amp;quot; ') &amp;quot;./47 V- g: /: o &amp;quot;C  ~)5o j (There is a marine tOwl.r to tit(. right hand of Hikawa-mm'u.) Frmn these sentences, SPRINT gets the surfttee eR.se strlwtltres a, ttd interprel, s each eOllltection in tit(! structures to extr;u:t sp;ttial constraints. Tit(; ext.racled constraints in this example is shown in table 1.</Paragraph>
    <Paragraph position="2"> Then SPRINT calculates the entity parameter vahles based Oll these COllstrailltS llSillg potential c.nergy flmctions. The exanq)le of the t)l)tentiM energy fllllctioll is showlt ill figm'e 2. This is one which is used to calculate the location of the ship. In this figure, the line repre.sents the edge of the park. and the thither side of the line me;ms the inside of the t)ark. Finally SPRINT draw a world image (m the graphic display. This is shown in figure 3.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 The Analysis of the View
</SectionTitle>
    <Paragraph position="0"> In the bunt I~xanlple. the treatment of the view is vm'y important. Usually an ob.s(wver sees the world ~md notices how the world is. If you did Ilot klloW which directiol~ the observer sees. yell wouM not dete,'mine the directi(m &amp;quot;'to the right&amp;quot; alia (,(mid llOt illlagille wll(!r(! the tower is. Allother way to (tetern|ine the direction &amp;quot;'to the  ,J coustrain the view by Ihe ,,ye direction righl:'&amp;quot; is t,o cal('uhtl:e il only from t;he orienl, al;ion of i:he ship. l)ul we: do m~l: lhink it is usual. Thi.~  server as one of t;lw spat:ia\[ et~l,it:ies, which has lhc ey~ iminl, I,hc aim point:. ~tliil the eye dire/&amp;quot; lion. lu this mwl;i/m, we itlladyzt! tho descripl:ions aboltI; view in &amp;'/:alia.</Paragraph>
    <Paragraph position="1"> At first, w(~ detin,~ the relali, m almul &amp;quot;'seN&amp;quot; as f.llows: &amp;quot;There is no visible obsl:acles bid:wccn t.hc eye point mid the aimed ent.il:y.&amp;quot; The constraint.s about tht, eye tminl:, eye dire(:t.ion, and t:h/', itilll point, comes IJt'Olll t:his detinilion. null Th,~ silulth~.st ci~se is shown in table 2. For /!XallI|)l/~, t,\]wre ILl'(? 5 ClHl,qIl'l~illt.S t.O t,h/~ S/!ll null If the eye tloint has its own direct(ira, the 5th (!Ollst, r~illt ill '2 \[)eCOllle.N ;~ relative one llased Oil the direction of the eye t)oint. For example, to ~ To\] (If you get a('ross the crossroad, You can sec a tower to the right hand.) the. constraint (13) ~t)ove lice(lilies (E') direction(view 1)=t o-t he-right (view- point 2) which means the (lireetiml &amp;quot;'to tit(.' right&amp;quot; is determined by the direction of tile eye of the observer. In this case tile observer get across the crossroad and no other information is obt~dned, so tile directiml of tim eye is determined as the same ~m that of the transfm&amp;quot; of the observer.</Paragraph>
    <Paragraph position="2"> There are the cases where the directi(m of the eye changes l'UllOllg the trallsfer. Ill slletl closes, the last eye direction must be calculated ~meording to the intermediate eh~mges. So the change point is imt, ~md it nle(liates the change of the direction of the tralmfer. The necessary COllStl'ttitlts are as follows: * eonstrtfint about the change point  fer with the Interlnediate Change The direction of the eye after the change is same ~Ls the diructioll of the' tl'~ulsf't~r-vector2. For examph~, the sentence V'l'rF-~'~),i~I?-~&amp;quot; ;5 L, ,~Pl: # r\]_ ?)~,~ )5 \] (If you turn left at the crossroad, you can see a tower to the right h~md.) is interpreted as in figure 4. hi this case, the directiml &amp;quot;to the right&amp;quot; is calculated Kom the last direction of the eye.</Paragraph>
    <Paragraph position="3"> This interpretation satisfies the constraints in the Sellte, ltee, howe.ver, olle llllty think this is not tlle Sallle its he/she imagine becmlse in this intel\])l'etltt.ioIl the obse, l'vel' ('gll see the tower (IV(,~ll before the crossroad. The sentence &amp;quot;If you turn left....'&amp;quot; seems to imply tlu~t &amp;quot;until you turn left at tile Cr(lssro3(l, yOll CgllllOt see 3, tower yet.&amp;quot; and this is not ill the case of the logical sense.</Paragraph>
    <Paragraph position="4"> Of course this iv not Mways true,. Suppose the situation where you see a t(lwer now ~md arc toM the last se.utcnce (llrotlably in English you say not &amp;quot;a tower&amp;quot; /)ut &amp;quot;'the tower&amp;quot;), this will be the c~me of the integration of the several views. Sll the additional pragmatic constraints are strongly influen(:ed by the puri)ose of the utterance,.</Paragraph>
    <Paragraph position="5"> Anyway if you do not want to see a towm' t)efore the crossroad, one of the solutions to this problem is like this: put some obstacle on the view of tit(: observer 1)efore the crossroad, that means put it between the p()int of the observer and the tower. In this ease, till the observer turn at tile corller, there is llO way to kllow the locati(m of the tower, so no way to trot the obstacle. Tile interpretation ~u'eor(ling to this solution is showll in figure 5.</Paragraph>
    <Paragraph position="6"> ()lie ()f the other solutilms is that you know</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Added Obstacle
</SectionTitle>
      <Paragraph position="0"> |,here is buildings or sorer:thing Mong a st.reel, and llS(~ tili(~lll }Lq IX ol)stacle.</Paragraph>
      <Paragraph position="1"> This kind .f &amp;quot;ilwisil)le' sit:uation must, tm discussed with respect t:o the read world and the daily language use.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
5 Related Work
</SectionTitle>
    <Paragraph position="0"> From the lmrc linguistic point of view, A. Herskovits \[1\] analyzed locativ(~ expr(~ssi(ms in English. As for constructing a ('Oml)uter model, conventional logic fMls short of ore&amp;quot; tmrpose.</Paragraph>
    <Paragraph position="1"> Anlong the formulations based Imrely on C()llVelltioual logic, n,ost, t,ypical is slot-tiller ret)resen~a|,ion such as a tbrmulal:ion by Gordon Nowtk ,It&amp;quot; \[2\]. Tlmre also is a work |,y D. Waltz\[3\]. i1 is however hlu'd to draw logical c(mchmion out. of a set of axioms which lliay involve predicates vague and to get a reusable model of the world toni|gunction. null Ore' apln'oach allows both cont, iiluous and dist:oiil;iillIOliS fllntq,iOll8 go l'(!pl'(}Sell~, spatiM COlistxMnts, so that the prot)ability changes eit:lwr contimumsly and discontilmously.</Paragraph>
    <Paragraph position="2"> It Mso works as ~t clmnk of the information.</Paragraph>
    <Paragraph position="3"> Though it seems that our aptn'oach is rathm' subjective, it seems imtiossil)le to construct a model for the worhl without smnc kind of subjective.</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> texts. The area of spa('e-language relationstrip contains a lot of hm'd issues, and some liroblems related to this work are mentioned tMow.</Paragraph>
    <Paragraph position="1"> ln'esenl;~d,i(m of the image, Our progr~tm makes ~t internal 3-(lin,ensional model of the world, but the t)i't!Selii:~ttioil t)iI l,lio s(!rt!t!ii is now llHtiill~tlly done. which means that. tim camera position fin' t.he computm' graphics is lnmmltlly decided (it is usmdly a bird's-eye view). How to iiresellt tht! iilI;erllld (!oiifigura, tiOll ~ts an image is a flu'thin' prot)lem.</Paragraph>
    <Paragraph position="2"> * inl:egration of the iuiti;d image.</Paragraph>
    <Paragraph position="3"> if ;dl tim model is t:onstrut:l;rx\[ b~me.d Oll fill(~ wn'bal inf'ol'nt;tl, itm, how to give the initial v3.hi(!s of the t)0,ritlilt~|;(:i,q effectively t}(}(:t)llie,~ the t)roblenl. If the tim reconstruction tiegins wii:h an initial image, the inl.egration of t, hat inmge aim the verbM inforniation is the other tiroblein. (Proll,d)ly the initial ilmtge is also vague.) We are now considering t;lw pn~gmatic use of the verbal eXl)l'ession in tim world model, and making a model of l:he visual disappearance.</Paragraph>
  </Section>
class="xml-element"></Paper>