<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2147">
  <Title>Zero Pronoun Resolution in Japanese Discourse Based on Centering Theory</Title>
  <Section position="8" start_page="873" end_page="874" type="evalu">
    <SectionTitle>
4 Experiment and Discussion
</SectionTitle>
    <Paragraph position="0"> In the last; section, we des(:ribed our zero pronoun resolution method that can handle colnplex sen.</Paragraph>
    <Paragraph position="1"> tences based on tile centering theory. It di\[lk;rs Koln tile original centering algorithm in the following two t)oints. After partitioning COlnplex sentences into inultiple sinli)le sentences, it searches tile ~mtecedents in the previous four simple sentences, instead of only a previous sentence. Secondly, it; takes into account the information of conjunctive postpositions that are between two sinlple sentences, by classifying them into three classes.</Paragraph>
    <Paragraph position="2"> In this section, we describe the experiments that our zero pronoun resolution method is applied to real Japanese discourses, to evaluate the effectiveness. We inlplement two versions of our zero pronouI) resolution systems which are based on two versions of the centering algorithms teat are inentioned in sect)oil two respectively, and ewfluate the Imrl'orina.nce by comparing ours with the perfl)rmanee of the original ee.ntering algorithms.</Paragraph>
    <Paragraph position="3"> As our test, discourses, we use 275 (prepartitioned) sentences from tive discourses in total, whietl are a review article in the newspaper, a tblk-tale, and a novel. Before the experiments,  \[metho(l\[ corre(:t \[ .h~rre(:i7 \] accura(:y 1 L ~ .... ~, in /!t A TM _1 .... d --~2- ~_- 21-2-- Z 72~ -30 __1--(~7.5(/0-J these (liscours(,s are automati(:ally l);~rtitione(l im;o simple sent(mc(;s and re(:(;ive(l stru(:tural rarely,sis, and the positions of zero pron(mns ~tr(': a,ul;oinati(:ally i(tentili(',d as missing o|)liga.tory cases of w'a't)s. Then, the results of this prel)rocessing m'e inanually (:orre(:t(',d. The zero prOllOUll whos(; &amp;11tece(h'a~t ai)pears after it, i,e., t;he catat)hori(: one, ~11d I;he zero t)l'OllOllIl whoso, anl;ec(;(l(ml; (lots nol; appear in the dis(:ourse, ;~xe outsi(l('~ th(! s(:op(! of this t)a.t)er. Thosc zero pronom~s are 30% of till l;he zero pl'Oll()ltlis itl Ollr l;(!s~ (|iscolll'8(,'s. 'i'h('. correct ~tllt(~('.(~(|(}lll;,q a.l'O manually i(h,m, ified b(ff'orehand agains|; each zero \[)ronollli, a.lld l;h('. t)(M'ormmw.(~ is (:omtmlx~(l bas(xl (m I;h(;se answers.</Paragraph>
    <Paragraph position="4"> The experim(ml;s are ma(te on the following l;hree  CD, SO, S: l. The original c('.nl;('a'ing alg(}rit;hm l;hat uses l;hc i/lforlnal;ion of only a previous simple sentence null 2. 'rhe Mgoril;hm that; s(',ar(:hes l;lm anl;c(:(~d(ml;s in the t)revious Ibm&amp;quot; simple s(~lll;(~llC(~,'--; 3. Th(', a,lgoril;hm not only s(~ar(:h(~s Llle ;i.iI~  tec('d(mt, s in l;lm previous l'om' simph; s('a,ten(:(~s, but also takes into a(:coun(; t, he infof marion of (:onjun(:t;ive 1)osfiposil;ions I;h;~t; are 1)etwee, n two siml)lc 80111;(~11(:C8 The results of the experim(;nl;s on two versions of our systems arc shown it, 'l'abh', 1 and 2, where l;h(', columns of k:orr(',(:t' and 'in(:orred;' show t, he nllnlb(;rs of the (:orre(:l, &amp;lid in(:orr(?(:l; answers th;tl; l;he sysl;(',m oul;puL~; r(!sp(',(:tively, a.m\[ l,hc (;ohmms of 'in' and 'not in' show |;he I/llIII\])(WS ()\[ C~I,S('~S whet(' can(li(lat(;.~ of a.nt(',ce(h;nts in the system inchMc the correct a.nswer and l;\]m mind)or of cases where tim system (toes 11o\[, h&amp;v(! ~h(,, corr(?cl; at~sw(;r as l,h(; can(li(latcs, rest)e('tiv(',ly.</Paragraph>
    <Paragraph position="5"> Air, hough the original ('(;ntx;ri~lg alg()rithms yield the performa~im(, of 60 70%, th(;y have many cgtsos Wh(':l'O, th(! sys|;em canno\[; gel; the corrccl; answer ~ts l;hc candidat;es(qlot in') and cannot output correct; auswers. This indicates that there &amp;l'O. mm~y cases where |;ho, coil(,~(;L &amp;IiL(?ccd(~tl|;,q do i1o|; nt)t)ear in the previous S(~,III;(~,IIC(~,, ~ldld implies l;he phmsibility of our first modific~tion l;o the origina.l algorithm. The improvement of the I)e.rforma.nce in method 2 also ilntflies tit(! plausibilil;y of our method. \],'lUl;h(~rlnore, taking into a(:(:OUil{; 1;he illformation of conjunctive t)ostt)ositions improve.s l;he \[)crformnnt:e 1)y 3 6%. Totally, (:ompnr('d wil;h 1;he original c('.nl;ering algorit;hms, t;}w. performance of our reel;hod improves by 7 \]0%.</Paragraph>
    <Paragraph position="6"> Since the zero 1)ronoml r(~so\[ution method l;hal; is t)a.sexl on the (:(~.lll;Ol'illg theory uses the results of the zero pronolm resolution in previous sentences, 'error~cha.ining' might; occur many times.</Paragraph>
    <Paragraph position="7"> \]';rror-chahfing occurs when the idenl;iticatit)n of &amp; wrong anl;(~(:e(l(mt; ('.raises anol;her wrong zero \])FOllOtlll rt}sohll;ion sut:(;essiv(',ly, ltl (;~/,q(} ()f OllF system(method 3) based on Kalne, yanm.'s algorilJun, 30.2% of the ilICOIT(~Ct; ~I,1ISW0,1'.% kl2&amp;quot;O (hi0 I,o this error--chainint;. There is also the possibilil,y where the (;orr(;(:l; an,qwt~rs m'c Olll;t)lll; |)(x:ausc of Lh(! wrtillg zero llrOllOlln reso\]ui;ion in 1;11(.' previous senlx;nces, in case of our sysl;enl(lnci;ho(1 3) 1)ased on Kameyama's algorithnl, only 1.2% of th(', (:of red; ;mswers are due to this 'false negative.' As you notice fi'om the above two t~fl)les, l;hc, re cxisI; about 30 cases where the mfl;e,t:ed(mt;s ~tl)t)t',ar in more l,han live s(mtt',nces fi'oin th(~ CtllTt!tll, sitllpie sentem:c and camlot; be. tound t)y our lll(~I;hod. YVc think these (;ase.s should not t)(.' handled simply t)y extending l;he search l'~tllge t'(/1' l;h(; ~mt;ec.t~dent;s, Iml, by utilizing tim informa, tiotl of global struc.l;/tr{ ~, of discourses(Grosz and Sidncr, 1986), because the digressive sub-discourse is inserted betw(.'en the. mfl;e(:t~dents mid the zero l)I'OtlOlltlS it, mosl; of these, ca.sos.</Paragraph>
    <Paragraph position="8"> Of ('x)urse, l,h('a'e have 1)ecn tim zero l)rOllOllll r(~solul;iot~ ~t)l)r(la.(:lms l;ha.t t;tke into a.(:(:ount the information of (:(mjunctiv('. (~l('meuts(Nakaiwa a.n(l \[kehara, 1992; Nakaga.wa. and Nishizaw~, 1994; Y=oNhil\[lOl;O, \],(JS(i; SIll'i all(l NIcC()y, 1994:). t/ec.mme N;,kaiw~ds(Nakaiwa. mtd lkehara., 1992)mM Na.kagawa's(Nakagawa and Nishizawa, 1994) a.pt)ro~w.ht'.s use /,he in_forma.l;ion in a r(~stricl;(~(l (it)main or ~oo fine-grainc(l grmmna.ti(:al information, we think they are dif\[icult {;o be tune(1 to th('. 1)road cov(~rag(' z(;ro l)ronoun r(;solution system. Furth(',r-more, Nakagaw~L's and Y()shimol,o's(Yoslfimol;o, 1986) a.t)t)r()a(:h(',,q are not; fully ('va.lual;(~d with rea.1 (lis(:om's(~s. Although Nakniwa's ~q)proa(:h yM(ts high ,~;u(:(:(',ss; rat(; (if 93%, he uses rath(,r small t(!s{, sets(102 ,q(mt;enc(~s from 29 a.rt;icl(~s), and the input, is r(~,qtrM,(~(t Ix) th(~ first t)nragrat)hs of neWSl)a.l)(~r ~u'ti(:h;s.</Paragraph>
    <Paragraph position="9"> ,qm'i's work(Suri a.u(l M(:Coy, \]994) mighl; t)e one of tim few works that extend I;h(; (:(ml,(~rh~/, , I\]a.m(;w()~k 1,() hind(lie (:Oml)h'.x ,q(\]lll;(~.ll(:(.'s, although  she handles only sentences of the form 'SX because SY,' and uses Sidner's focusing framework(Sidner, 1983), that is different from the centering theory that our method is based on. Purthermore, the effectiveness of her work is not evaluated with real discourses.</Paragraph>
    <Paragraph position="10"> Takada's work(T&amp;kada and Doi, 1994) might be the only exception that proposes the zero pronoun resolution method based on the centering theory and evaluates its effectiveness with real discourses.</Paragraph>
    <Paragraph position="11"> Since he handles not only zero pronouns but also overt pronouns, the exact comparison is difficult, but his approach, that is based on Kameyama's approach, yields the performance of 74.8% if the results for overt pronouns are excluded. In addition, to handle complex sentences, he adopts the other approach where they are treated as a single unit, and admits that some problems arise because of this approach.</Paragraph>
    <Paragraph position="12"> Taking into account the information of conjunctive elements in the pronoun resolution reminds us of the works that use the establishment of coherence relations between clauses for pronoun resolution(Hobbs, 1979; Kehler, 1993). They try to establish coherence relations by the costly inference, while we use only the surface information.</Paragraph>
  </Section>
class="xml-element"></Paper>