<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2139">
  <Title>Full-text processing: improving a practical NLP system based on surface information within the context</Title>
  <Section position="5" start_page="825" end_page="827" type="metho">
    <SectionTitle>
3 Effectiveness
</SectionTitle>
    <Paragraph position="0"> The a(:cura('y of syntactic analysis m~\y l)e improved by refinement of the ('ontext nn)del in tlt(' second step of the procedure. For ex~mlple, in an exl)eriment on 244 sentences from a. chapter of a COml)uter manual, in which we attempted to select the correct parse of a sentence from multiple candidate l)arses, ('orre('t parses were sele('ted for 89.1% of 110 multiple pa.rsed sentences by using infbrmation in the ('ontext model, where~us the success rate obtained when the ('ontext model C/'ontmned no ilfformation was 74.5%. In our experiment on ill-f(mned sentences ill technical do('ulnents, in more than h~flf of the incoml)letely 1)~trsed sentences, the lmrt.iM parses were joined into a single stru('ture by using ilfformation in the context model.</Paragraph>
    <Paragraph position="1"> However, after the second step, ambiguities in each sentence are kept unresolved in the context model.</Paragraph>
    <Paragraph position="2"> Thus, we need to resolve problems in each sentence in the context model ill(lividuMly.</Paragraph>
    <Paragraph position="3"> In this section, we describe how the accuracy of senten('e mtalysis in other probh'nls is improved by referring to the siml)le context model, and how the results are refiecte(l in improved machine translation outlmts.</Paragraph>
    <Section position="1" start_page="825" end_page="826" type="sub_section">
      <SectionTitle>
3.1 Resolving the focus of focusing
subjuncts
</SectionTitle>
      <Paragraph position="0"> Ih,solving the focus of fi)cusing sul)juncts such as also ;rod only is a tyl)ieal context-del)endent probl('m tha.t requires ilffornmtion on the 1)revious context. Fo('using sul)jnncts (lr~tw m.tention to a part of ;t senten(-e th~tt often represents new information.</Paragraph>
      <Paragraph position="1"> Consider the se(:ond senten('e, Tom also likes apples, in Figures 1 mM 2. Ill this sentence, the scope of also can 1)e To'm, likes, the entire predicate (the whole sent.enee except the subject Tom), or apple.% acc(trding to the itrevious context. In this ('as(', the preceding senten('e, Joh, n likes apples, has the structure, A likes B, whereas sentence (2) has the structure, X also likes B, where B and the predi(:ate fib,s are identical. The eoml)arison of these two structures indicates that the new intbrmation X (Tom) is the scope of also in sentence (2).</Paragraph>
      <Paragraph position="2"> The fl)('us of focusing sul)jun('ts ix resolved by means of the following algorithln:  1. Find among the 1)revious sentences in the context model one that contains expressions morphologically identical with those in the sentence containing the focusing suhjunet.</Paragraph>
      <Paragraph position="3"> 2. Contpare each candidate focus word or phrase in the sentence containing the tl)('using subjunct with words or phrases in tit(&amp;quot; senten('e extracted in ste l) 1. 3. Drop any mori)hologieally i(hmtical words or I)hrases  as candidates for the focus, and select the remainder as the focus of the fo(-,tsing su|)junct. If more than one candidate remains, take the defaul}, interpretation that wouhl be used if there were no context iuformatiolt.</Paragraph>
      <Paragraph position="4"> Figure 2 shows the translation outputs of our syste,n with and without information 1)rovi(h~d by context pr(t(:essing. As shown in this figure, with(tar the context information, also modifies the 1)redicate like l)y default in l)oth senten('es (2) and (3). In contrast, when context pro('essing is apt)lied, the focus of also ix determined to I)e Tom in senten(:e (2) and orange in sentence (3).</Paragraph>
      <Paragraph position="5"> In our amtlysis of ('omlmter manuals, most nouns were repeated with the same expressions unless they were repla.('ed by 1)ronouns or definite expressions su(h as th, is, that, and tit('.. ()n the other hint(I, predi(-ates were sometimes repeated with different expressions. For exanlple: A has B. ~ A also includes C.</Paragraph>
      <Paragraph position="6"> A contains B. --~ C is also included in A.</Paragraph>
      <Paragraph position="7">  \[11 this case, infornlltl:ion on ,~3&amp;quot;ilOllyillS a, lld derivativ('s (,xtr+t('t(,d fi'om on-line (li('tionari('s can t)(' us('d l;o exalllille the (:OH'eS\[)Oll(h'n('e \])etw('ell two words.</Paragraph>
    </Section>
    <Section position="2" start_page="826" end_page="826" type="sub_section">
      <SectionTitle>
3.2 Resolving pronoun referents
</SectionTitle>
      <Paragraph position="0"> Pronoun resolution is a.noth(,r typical ('ont(,xl(h'l)('nd('nt 1)rol)h'nJ, sin('(' the r('fcr('nl of a l)ronoun is not Mwa.ys in('lud('d in lh(' sam(, smlt:(,n('(,. Our ('oul:ex:l: n).o(lel is us('d to s(qe('t (+uMidat(' noun l)hras('s for a 1)ronoun r('fl'rent. \]qlrthermore, information on word fr('qu(m('y and moditi('r-moditi('(' rel+t(ionships extr;tcted fi'om the (:ontext 1no(\[el inll)roves the a(.(.uracy with whi('h th(' ('orre('t rcf('r(,nt is s(q(,('tod froui the (';m(lid~t(' noun l)hri~s(,s, a.s shown in a. pr('vious pap('r (Nasukaw;t, 199,i). By applying h(mrisii(' rules according to which a, candi(lat(, that has h('im frequ('ntly r(,pe~m~(l in th(, 1)re('eding sent(m('es and it candidate th~tt modifi(,s the morl)hoh)gi('a.lly id('nti-(:al predicat('s as tho 1)rollollll in i;he same context are t)referred, w(, obt.Mn('d a su('(:(,ss i'~'L(,O O\[ ,0.'~.8(Z, ill pronoun r(,solution.</Paragraph>
      <Paragraph position="1"> However, the results of pronoun resohliiOn may not be explicitly r('th'('t('d in th(, out.put of :t ma.('hin(, tral,sla.tion system, sin((' most languag('s have ('orre Sl)onding an+q)hori(: expressions, ~tnd us(' of th(, corre-Sl)onding a.naphori( expression in lhe translation oull)ut: hi~s the adviLnt+tge of a.voi(ling misint('rl)r('ta.tions ('a.used by misr('solution of 1)ronoun ref('r('nts, ('v('n if the probability of misim.('rl)r('tation is less than 10J(.</Paragraph>
      <Paragraph position="2"> Thus, ill Figure 2, He in .q('illrOll('(~ (3) is tra, nsl~Lt('d as the Ja,1)anese 1)ronoun ~;a'r(:, Mthough its ref(,renl; is correctly resolv(,d a,s Tor~,. Even so, corr(,('t resolution of a 1)ronoun r('f('r('ul: is iml)ortanl for disambiguating the word sense ()f a 1)r('di('al:(' modified 1)y t, he l)roiiou11. &amp;quot;~ Ill ad(lition, if the 1)ositions of a, aIn fact, t.he result of pronoun r('solution for s('nl:('nc(' (3) of Figure 2, in whi('h To~,. is s(%('t(,d as (.ho rofe&gt; t)t'()ll()llll i/,tl( |i1:,% l'('f('l'Olll; llOlln 1)hra,s( ' &amp;l?(' reversed ill the ll:~ulsllt/:ion of a. (:Oml)h,x senten('e where an initim main ('lause ill a, sour('(,-lmtgmtge s(,nt(,n('(, ('om(,s afl(,r th(' sul)ordin+tte ('l+ms(' in th(' target language, the r('t'('r(mt, noun phr~ts(' shouhl be repbt('ed with th(' I)ronoull, to avoid ('ata.phori(' refer(,n('(,. For ('xaml/h', the t&amp;quot;m~,,lish S('lll,(qlc(' Th,(: dog 'will eat you,'r c.,kC/', if you dcm,'t ho, vC/: q'eti(:kly, should bc translatod as Kiw~.i \[v,,,,\] ~/a .~ono keiki \[th&lt; &lt;..kq wo ,~'tq/'~C/,~,i \[q,,i,.~l.\] ~a.l~C/' &amp;quot;:~,C/ri \[,10,,'~ &lt; .~1 ~,(1,'ra., ,,~o'n,o i~tu \[~h, d,,~\] ,qa ,I :a, hetc:_sD, i?r~,a,'iPS~/o \[,,,i.., q.</Paragraph>
      <Paragraph position="3"> Sin('(' in the t,r;mslated .\]ai)~uwse s(,nt(,n('(, the suboMinate clause, i,f you do'u'I have it quickly, ('om(,s 1)efor(' th(' main el+rose, The dog 'will ,at your&amp;quot; (:ai;e, the pronoun it in th(, sUbol'dinat(, claus(, must l)e r('solved in order to g('n(,r;tte a natura.1 .\]iq)an(,s(, sent(m('(,. Mioreover, the word sense of h, ave in the subordinar(' claus(' cannot 1)e sch,('t(,d without infl)rma.tion on th(' ret'orent of the pronoun it.</Paragraph>
    </Section>
    <Section position="3" start_page="826" end_page="827" type="sub_section">
      <SectionTitle>
3.3 Lexical and Structural disambiguation
</SectionTitle>
      <Paragraph position="0"> In a. consistent text, 1)olyselnOUS words withiu a discourse tend (o have the sam(, word s('ns(' (Gale et a,l., 1992; N;tsukawa, 1993). Thus, \])y al)plyiug discours(! ('ovstra.int in such a, nlanner that 1)olysemous words with the slune lemma within a context ha.ve th(' same (,nt of He, is r('tle(q;(~d in (:he translation of the predicate like. lh'('~mse of the l,~(:k of tt scnmnti(' f('ature PS'lt~t~,an for th(, h'xi('al enl;ries '/'o~, a.nd ,loh'u in our (ti('tion~try at th(' tinio of this transla, tion, diti'eront word senses for animate sul)jc('ts mid nolt-aalinla|;(! sul)je('ts were s(,lectcd for tl, c verb like, and the verb like was r(,n(h,r('d (lit\[(,r('nlly in th(' translations with mM withont context.</Paragraph>
      <Paragraph position="1"> &lt;lThis translation was not 1)roduced by our syst(,m.</Paragraph>
      <Paragraph position="2">  word sense, a result of word sense (lisambiguation aI)plied in one sentence cau be shared with all ()tiler words in tile context that have the same lemma. Furthermore, by assuming dis('ourse I)reference, namely, a tendency for each word to modify or be modified by similar words within a discourse, structural infornmtion on all other words with the same lemma within the discourse 1)rovides clue for determining the modifiees of structurally mnl)iguous 1)hrases (Nasukawa and Uramoto, 1995). This method can 1)e used to solve context-dependent t)rol)leuls such as the well-known examt)le shown in Figure 3.</Paragraph>
      <Paragraph position="3">  In sentence (1) of tile figure, the mo(lifiee of the prel)ositional phrase with a telescope can be either saw or girl, depending on its context. In this case, information in sentence (2), where the identical t)repositional t)hra.se modifies girl, provides a clue that with a telescope in sentence (1) is likely to modify girl.</Paragraph>
      <Paragraph position="4"> In this way, modifier-m&lt;)difiee relationships extracted from a context model provide clues for disambiguating structurally ambiguous phrases. Needless to say, the effectiveness of this method is highly dependent on the s&lt;mrce text, and it may seem too optimistic to expe(:t such useful information ill the same context.</Paragraph>
      <Paragraph position="5"> However, as shown i~1 Figure 4, which is a translation output of an actual &lt;:Oml)uter manual, we can often find modifier-modifiee relationships that (lisambiguate structurally anlbiguous phrases in tile sltme context, at least in technical documents. In Figure 4, the ambiguous prepositional 1)hrase of a job 5 in sentence (2) is disamt)iguated and attached to the flow l)y ~of + noun may modify verb, as in He robbed a lady of her money.</Paragraph>
      <Paragraph position="6"> using the information provided by the unamt)iguous 1)rel)ositional phrase in The flow of a job in sentence (7). Similarly, tile information on the unaml)iguous prepositional phrase in placed on an output queue in sentence (11) disaml)iguates the aml)iguous I)rel)osi tional t)hrase on a job queue in sentence (9), alh)wing it to be attached to places.</Paragraph>
    </Section>
    <Section position="4" start_page="827" end_page="827" type="sub_section">
      <SectionTitle>
3.4 Supplementing phrases for elliptical
sentences
</SectionTitle>
      <Paragraph position="0"> Supplementatiml of elliptical phrases is another typical context-dependent prol)lem. In spite of the sin&gt; t)lMty of our context model, some elliptical phrases can be supt)lelnented by using information extracted h'om the context model. For example, if a group of words ending with a cohm is not a complete sentence, as in the ease of (3) in Figure 4, This allows you to: our system adds either do the following or the following t)y referring to the tyl)e of the next sentence or phrase in the context model. If verb phrases follow, do the following is added, and if noun l)hrases folh)w, the following is added. Thus, in (3) in Figure 4, do the following is added 1)ecause a verb phrase follows this sentence.</Paragraph>
    </Section>
    <Section position="5" start_page="827" end_page="827" type="sub_section">
      <SectionTitle>
3.5 Resolving modality
</SectionTitle>
      <Paragraph position="0"> The modality of itemized sentences or phrases is of_ ten ambiguous as a result of the 1)resence of ellipses.</Paragraph>
      <Paragraph position="1"> For example, (4), (5), and (6)in Figure 4 couhl be imt)erative sentences in certain contexts. In this ease, however, they are itemized phrases, and by reference to (3), they (:all be identified as supl)lementary w, rb phrases to be attached to (3). Thus our system analyzes them as verb phrases and nominalizes them in the translation.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>