<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2138">
  <Title>Identifying Temporal Expression and its Syntactic Role Using FST and Lexical Data from Corpus</Title>
  <Section position="4" start_page="955" end_page="958" type="metho">
    <SectionTitle>
3 Acquiring Co-occurrence of
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="955" end_page="955" type="sub_section">
      <SectionTitle>
Temporal Expression
3.1 Categorizing Temporal Nouns
</SectionTitle>
      <Paragraph position="0"> Since many words have in common a similar meaning and flmction, they can be categorized by their features. So do temporal nouns. That is, we say that 'Sunday' and 'Monday' have the same features and so would take the similar behavior patterns such as co-occurring with the similar words in a sentence or phrase. Hence, in the frst place we categorize temporal nouns according to their meaning and function. We first select 259 temporal nouns and divide them into 26 classes as shown in Table 1. Among them, some temporal words have syntactic duality and others play one syntactic role. Thus, the disambiguation process would be applied only to the words with dual syntactic functions.</Paragraph>
    </Section>
    <Section position="2" start_page="955" end_page="956" type="sub_section">
      <SectionTitle>
3.2 Acquisition of Temporal Expressions
from Corpus
</SectionTitle>
      <Paragraph position="0"> Temporal words would be combined with each other in order to be made reference to time, which is called temporal expression. Since a temt)oral expression is typically composed of one or a few temt)oral words, it seems to be possible to describe a grammar of modifying noun jeonlsilll-eUll nlasisseossda</Paragraph>
      <Paragraph position="2"> ral expression the temporal expression with a simple model like finite automata. Ill tile practical system, however, we are confronted with a complicated problenl in treating teml)oral expressions since many temporal words have a functional ambiguity used as both a nominal and predicate modifier. For instance, a temporal noun oneul(today) could play a different role in the similar situation as shown in Figure 2. In the first and the second path, the words to follow oneul are all noun, but the roles (dependency rela;ions) of oncul are different.</Paragraph>
      <Paragraph position="3"> Accurate classitication of their syntactic flmctions is crucial for the application system since great difference would be made according to accuracy of the dependency result. Practically, we therefore should take into consideration the structural ambiguity resolution as well as their representation itself in identi- null here is thai; we eould pre(liel; the synt;a(:l;ic fllncl;ion of I;emt)oral words 1)y looking ahead one or l;wo words. Namely, looldng at; a Dw words thai; follows a 1;emporal word we can figure oul; which word the temporal expression modifies, and call l;he following words local conl, e:rt.</Paragraph>
      <Paragraph position="4"> Unfortunal;ely, it is not easy t() define t, he, local conl;exI; for del;ermilfing 1;he synt, ael;i(: flm('l;ion of eae.h temporal word 1)eeause l;hey are lexieally relai;ed. Thai; is, il; is wholly ditl('.renl; fl:om each wor(t wlw,|;her a I;(nnl)oral noun would modit)- ()l;h(w i1()1111 (:o form ~ (:Oml)Om~d noun or mo(lii~y a 1)re(li(:al;e as m). adverbial l)hrase. ()ur al)t)roa/:h is l;o use col pus to acquire informal;ion atmut, l;he local ('oni;exl;. Since we could obtain fi'om eorl)uS as many examples as needed, rules for comt)ound word generation can be (:onstructe(1 from l;\]le examI)les. In l;his 1)al)el', we llSe CO-OCClllTe, II(;O rela|;ions of l;emlmral llO/lllS ext,r,acted froll\] large corpus I;o represent and consi;ru(:t; rules for idenl;ifieal;ion of l:emporal expressions.</Paragraph>
      <Paragraph position="5"> As lnenl;ioned before, we would 1)a.y a|;ten(,ion (;o two t)oinl;s here,: (l.) In whal; order a tenq)oral ex1)ression would 1)e represenl;ed with temt)oral words, i.e. descrit)|;ion of the temporal exi)ression nel~work.</Paragraph>
      <Paragraph position="6"> (2) how the local context would 1)e described to resolve tile ambiguity of the syntactic tim(lion of tem1)oral ext)ressions. For this tmrpose, we tirs|; extract examl)le sentences containing each of 259 l;eml)oral words from eorlms using l;he KAIST concordance progrmn :l (KAIST, 1998). The numl)er of t, elnporal words is small and so we could mmmally manii)ulate lexieal dal;a ext;racted frOlll corl)us. Figure 3 1KAIST corlms consists of about 50 million cojeols, l';ojeol is a sl)acing unit; comi)oscd of a content word and functional words.</Paragraph>
      <Paragraph position="7"> shows exanll)le sen|;enees at)out, ye.o'reum(sununer) ext;ra(:t;ed l)y the. coneor(lanee l)rogram.</Paragraph>
      <Paragraph position="8"> Second, we s(;leet only l, he t)hrases related wit;h temporal words fl'om the examples (Table 4). As shown in Table 4, yeoreum is associated wii;h va.rying words. Temporal words like temporal pre.tixes can come before it and coIlllIlOil llOl_lllS C}lll follow ig. In (,his stage we describe con(;exts of each temporal word and (;he olll;1)U(; (syn(;ae(;ic tag of (;he tOtal)oral word) under the given eonl;ex(;. In l)artieular, each l;eml)oral word is assigned a (.emporat class. Be.sides, or;her nouns serve as local cent;exits for disaml)igua(;ion of syntac(;ic flmc(;ion of t, emporal words. lS:om (;he examl)les , we can see t, lmC if ha're(night), byeo(jau, g(villa), ba, ngh, ag(vacal, ion) and so on follows it, yeoreum serves as a (:olnponent of a ('ompomld noun with the following word. On t, he other hand, the word naenac wtfich means all the time is a temporal noun and forms a teml)oral adverl)ial l)hl'}/se</Paragraph>
    </Section>
    <Section position="3" start_page="956" end_page="958" type="sub_section">
      <SectionTitle>
and Chunking
4.1 Representing Temporal Expression
Using FST
</SectionTitle>
      <Paragraph position="0"> The co-occurrence data extracted by tile way described ill the previous section can be represented with a finite state machine (Figure 5). For synt;aetie :\[inlet;ion disambigual;ion an(t chunking, the automata should produce an out, lm|;, which leads to a fiifite st;ate t;ranslhleer. In fact, individual deseripl;ion for each data could be integral,ed into one large FST and represented as the right-hand side in Figure 5. A finite sta.te transducer is defined with a nix- null left context word right context</Paragraph>
      <Paragraph position="2"> befbre temporal noml after outlmt freq</Paragraph>
      <Paragraph position="4"> alphabet; E2 in a finite output alphabet; Q in a tinite net of states or vertices; i E Q in the initial state; F C_ (2 is the set of final staten; E C Q x E~: ~ E.; x (2 is the set of transitions or edges.</Paragraph>
      <Paragraph position="5"> Although the syntactic function of a temporal expression would be nondeterministically selected fl'om the context, temporal expressions and the lexical data of local context can be represented in a deterministic way due to their finite length. For the deterministic FST, we define the partial functions (r) and * where q(r)a = q' iffd(q, a) = {q'} and q,a = w' iff ?q' E Q such that q(r)a = q' and 5(q, a, q') = {w'} (R.oche and Schabes, 1995). Then, a nubsequential FST is a eight-tui)le (El, E2, Q, i, F, (r), *, p) where: E1,E2,Q,i and F are the smnc as the FST; (r) is the deterministic state transition fimetion that maps () x E1 on Q; * is the deterministic emission fimction</Paragraph>
      <Paragraph position="7"> Deternfinistic FST resulted from Figure 5 that maps Q x E1 on E~; p : F --) 22~ is the final outtmt fluiction.</Paragraph>
      <Paragraph position="8"> Our teniporal co-occurrence data can lie relivesented with a deterministic finite state transducer</Paragraph>
      <Paragraph position="10"> i)roce, s,s temi)oral ex\])re,,qsion in a similar way. The, sut)s('qu(',ntial FST f()r our sysl,em is (l(,,fined as in Figure (i and Figur(~ 7 ilhLsl.ral;es I;he tral~sdu(:(!r in l?igur(~ 6. In L\]m tiI~me, ti is a c\]ass 1:o whi(:h lhe (:eml)oral w()rd 1)elongs in l;he lx',mporat (:las,qiti('at;ion. wi is a word ol;her l;han l,em1)oral ones 1;hal; has l;he pr(',(:(~(ting t eml)()ral wor(l 1)(', il:s modiiier, and wj is not; such a word 1;() make a compound noun. TN, TA and NT are synt, aciic tags. A word t;agged with 5/'N would modify a su('ceeding llOllll like, barn(night), bangh.ag(vacati(m). A word al:t, ached with TA would lnodify a predica.lx~' aim one with NT nmans ii; is not; a 1;emporal word.</Paragraph>
      <Paragraph position="11"> A(:mally, individual FSTs are coml)in(;d into one aim rules for tagging of temporal words are pul; over l;h(; .,J. The rule is applied according to the prioriW by freqllellcy ill case lllOrl2 t;hall ()lie ()ll{;l)ill; are \])ossible for a (:Oilt;ex|;. Nmnely, it; is a rule-l)ased system W\]I()I'(I ~\]le rllles al'e, (~xl;ra(;|;(?(l frolll (;ort)llS.</Paragraph>
    </Section>
    <Section position="4" start_page="958" end_page="958" type="sub_section">
      <SectionTitle>
4.2 Chunldng
</SectionTitle>
      <Paragraph position="0"> Afl;er the FST of l;enlt)oral (',xt)ressions adds I;o woMs syntactic tags such as TN and TA, chunking is conducted with l'eSlllI;s frolll OllI;l)llI;S 1)y t;h(' FST. As we said earlier, (:hunldng in Korean is relal;iv(;ly easy only if t;h0, t;eml)oral exi)l'essioll wou\](t be successfully recognized. Act;ua.lly, our ('hunker is also based on the, finil;e s(;a,l;e machine. The following is an exmnl)le for (:hunldng rules.</Paragraph>
      <Paragraph position="2"> \]\](!re: j\r is a noun wil;h(ml, rely \])ost.t)osit.ion , NP is a noun wit.h a. 1)oSl;l)OSil,ion, TN is a t;enll)oral noml recogniz(~,d as modifying a suc(:ox'ding n(mn, NU is a number and UN is a uni(; n(mn. Afl;e,r t('mporal l.a.gging, 1;he ('hunker l;ransforms 'NT' into N, NP, (d,(',. according I,o morl)hologi(:al consi;itueid;s and their I)OS. I h'io, tty, t;he, rule says thai; an NP ctmnk is mad(', from eil3mr NI' or l;emporal NIL An NP would \])(! (:()llsLrll('l,(',(1 wii,h on(; or lll()l'(} llOllll.q ;ill(1 \[;boil&amp;quot; modilie(~ or with a noun (lUanl;ified. A TN\] ), whi(:h is r(',lal:ed with lime, is made from n(mns moditied by t('ml)oral words wlfi(:h would 1)(', i(t(;nl;itied by the FST. By i(l(mtifi(:ation of lx!mporal (',xpressi()n and chunking, tlm following (',xmnl)k', senl~elu:e, is chunked as |)(;low.</Paragraph>
      <Paragraph position="4"/>
    </Section>
  </Section>
  <Section position="5" start_page="958" end_page="959" type="metho">
    <SectionTitle>
5 Experimental Results
</SectionTitle>
    <Paragraph position="0"> For l;hc ext)erinmnl; a.bouL l;eint)oral expre, ssion, we e, xla'aci;ed 300 senl;enc('~s (:onl;a.ining temporal expressions from E\]?I{I I)()S cortms. Table 2 shows the r(', null process temporal expression in a similar way. The subs(xlU{'.ntial FST for our sy:stem is detined as in Figure {i and l?igu\]{~ 7 illustrates th{. ~ trans(hl{:er in Figure. (i. In the tigurc, ti is a {'lass to which the tc.mporal w{}rd 1}elongs in the. temporal classification. &amp;quot;wi is a word {}the.r than temporal ones that has |;11{; prex:e.ding temporal word be its moditier, and 'wj is not such a word to make a COml)Oui:d noun. TN, TA and NT are synta{'ti{: tags. A word tagged with TN would mo(lit~y a suc(:ceding noun like barn(night), ban.qh, ag(vacation). A word attached with TA wouhl mo{lii2y a predicate and oi1{; with NT means it is not a temporal word.</Paragraph>
    <Paragraph position="1"> Actually, individual FSTs arc {:oml}ined int{) one. an(l rules for tagging of teml}oral wor{ts are put over the.</Paragraph>
    <Paragraph position="2"> FST. The rule is al}plied according to the priority by fro(tllOll{;y ill case m(}re than o11o (}uttmt are possible for a context. Namely, it is a rule-based system where the rules are extracted fi'om corl}us.</Paragraph>
    <Section position="1" start_page="959" end_page="959" type="sub_section">
      <SectionTitle>
4.2 Clmnking
</SectionTitle>
      <Paragraph position="0"> After the FST of temporal exi}ressiolls adds to words syntactic tags such as TN and TA, chunking is {:onducted with results tiom outl)uts 1)y the Fsr\] '. As we said earlier, {:lmnking in Kore.an is relatively easy only if the teml}oral ext}ression would l)e suc{:e.ssfltlly recognized. Actually, our clmnker is also 1)ased on the finite, state lnachine. The tbllowing is an example tbr chunking rule.s.</Paragraph>
      <Paragraph position="1">  Here, N is a noun without any 1)ostl)osition, N/? is a noun with a postposition, TN is a temporal noun recoglfized as modii~ying a succeeding 1101111, NU is a numbe.r and UN is a unit noun. Aft, er tcmI)oral tagging, the chunker transforms 'NT' into N, NP, (~tc. according to morphological constituents and their POS. Brietly: the rule. says that an NP clmnk is made fl'om either NP or temporal NIL An NP would 1)e (:onst, rll(;te.(1 with one. or lnOl'O llOlllIS and their m{}{lifie{~ {)r with a noun quantified. A TNP, whi{:h is re, lated with time, is made fr{)m nouns mo(liticd by teml}oral words which w{mld be ide, ntitied by the, FST. By identification {)f t('mt){}ral ex\]}ression and chunldng, the following exami)le sentence is ctmnked as below.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>