<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2152">
  <Title>Hypothesis Scoring over Theta Grids Information in Parsing Chinese Sentences with Serial Verb Constructions</Title>
  <Section position="5" start_page="945" end_page="946" type="evalu">
    <SectionTitle>
4 Experimental Results
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="945" end_page="946" type="sub_section">
      <SectionTitle>
4.1 Results of More Sample Sentences
</SectionTitle>
      <Paragraph position="0"> in tablc 2, we show thc results of more sentences with SVC in the legal documents which are parsed by this scheme in our TG-Chart parser. The sample sentences are shown in table 1 : Tahle 1. Some sample sentences with SVCs Sl:~,-~ -ff~g~ ~{~ ~ ~-{-~J~;~ (tl~~thedefendant tg!y 2 three hundred thousand dollars) The plaintiffpetitioncd the defendant to ~ive him three hundred thousand dollars. $2:~,~-~ g~/~ ~-~ ~ t~J (~'~ the defendant re~L ~ The plaintiffrequested the defendant to repay his debts.</Paragraph>
      <Paragraph position="1"> $3: ~0~-~ ~ ~lJ \]2~ -~:~ (Ihedefendant didnht arrive theeonrt The defendant didn't arrive at the court to argue.</Paragraph>
      <Paragraph position="2"> $4: ~-~ ~ ~f~i~' ~l\]~g-~ ~;~ (the defendant suddcnl~ ~ left h ..... desert his famil~ The defendant deserted his family suddenly and causelessly.</Paragraph>
      <Paragraph position="3"> $5: ~-~ :5~ ~_ _~ ~ J~,-~ \[Nit ~ (the defendant didn't retum l ..... ith the21aintiffcohabit ) The defendant didn't return home to cohabit with the plaintiff.</Paragraph>
      <Paragraph position="4"> $6: f'~,-~ ~.~ -~g~=~J -~)-, (the defendant petition inten'o~ate the witness) The defendant petitioned to interro\[~ate the witness.</Paragraph>
      <Paragraph position="5"> $7: ~j~-~ ~J_~ /~,~-~ ~ -~,~ (the defendant ~ ~ c_an The defendant hoped that the plaintiffcould ford, ire him.</Paragraph>
      <Paragraph position="6"> $8: N-~ I~g~ ~-~\]~\[\] ~T{~I~ (the defendant ~ attend the labor insurance) The defendant applied to attend the labor insurance.</Paragraph>
      <Paragraph position="7"> S9: 1~,-~ -~\[\]~ ~,~ ,,k, ~1~ ~l\]lt'~ (theplaintiff ordinaril~ treat iLeo2~lc ~ ~) Ordinarily, the plaintifftreats people fiiendly.</Paragraph>
      <Paragraph position="8"> SIO: ~,~'~ ~Z~ Z --IN ~~1~ {1~ {~ (~fl&amp;quot; hreak As E ........ ~ va\[nah\[~) The plaintiffbroke a vase thai was valuable.</Paragraph>
      <Paragraph position="9"> Tahle 2. Results of S-function calculation for sample sentences</Paragraph>
      <Paragraph position="11"> ~11, v2: -5~ vl,v2 vl=v2 f~j~,v2: ~Z-~: vl,v2 vl=v2 ~_, v2: ~/=~ vl,v2 vl-v2 vl: ~.~,v2: ~yt~ vl,v2 vl&gt;v2 vl: NN,v2: NN</Paragraph>
    </Section>
    <Section position="2" start_page="946" end_page="946" type="sub_section">
      <SectionTitle>
4.2 Demonstrating How to ilandle
Three-Verbs SVCs
</SectionTitle>
      <Paragraph position="0"> Let's consider the following three-verbs senlencc: &amp;quot; .~.~ &amp;quot;~ ~ -lh~ .},t_ ~ ~_ 4~,&amp;quot; (!t~cplaintiff return home remind his wife p)~ fees_) (The plaintiff relurned home to remind his wife lo pay fees.). There are three verbs in this sentence: .~ (return), ~:L/~2 (remind), and ~ (pay). At the first stage, Combination Generator generates 29 possible combination; and then, Combination Filler filters out 26 of them, and only three cases remained to be considered: &amp;quot;~ = -1~ ~2 = ,~&amp;quot;,&amp;quot;~ = \[ ,b~/$~ &gt; .~ l&amp;quot;, and &amp;quot;1 ~ = ,t,~{ fi'~l &gt; ~ &amp;quot;. Thus, Score Evaluator only needs to calculate the scores lot these three remained cases. At the final slage, Structure Selector accepts the evahmted scores for these cases and selects the one with the highest score. In this example, the structure &amp;quot;=&gt;&amp;quot; gels the highesl score: (/.94', it is lhe correct structure l'or this sentence.</Paragraph>
      <Paragraph position="1"> Consider another interesting example, &amp;quot;,fC vx~ k .q~ '~)1 ~ qg ~ ~, 6.0&amp;quot; (12q think l mock he i s ~,rong) \[Pun 1991\]. This sentence is ambiguou.v to native speakers, since there arc two possible readings: (1) &amp;quot;l~g vX~ ;1.~ ':~)1 ~ 4'gl ~ $~@&amp;quot; (His thinking lhal 1 mocked him is wrong.), and (2) &amp;quot;~G vX J..~ \[4~, t~)l ~ ~ ~'~ $~ 6&amp;quot;~J\] '' (He thinks that 1 mocked him for being wrong.). In Smodel, bath these two readings get the highest score: 1.0, and thus both are selected by Slruclure Selector as the final onlpnl. S-model doesn't altempt 1o select a &amp;quot;uniquely-correct&amp;quot; structure, bul just selects what are pr~'.rred. It matches humans' behavior since even a human may not be able to tell which of these two is better,</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>