<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0205">
  <Title>Telicity as a Cue to Temporal and Discourse Structure in Chinese-English Machine Translation*</Title>
  <Section position="8" start_page="38" end_page="39" type="evalu">
    <SectionTitle>
8 Results
</SectionTitle>
    <Paragraph position="0"> We have applied the rules in (6) in generating 80 sentences in the corpus (starting from often ambiguous CLCS analyses). Evaluation is still tricky, since, in many cases, the interlingua analysis is incorrect or ambiguous in ways that affect the appropriateness of the generated translation.</Paragraph>
    <Section position="1" start_page="38" end_page="39" type="sub_section">
      <SectionTitle>
8.1 Tense
</SectionTitle>
      <Paragraph position="0"> As mentioned above, evaluation can be very difficult in a number of cases. Concerning tense, our &amp;quot;gold standard&amp;quot; is the set of human translations, generated tense past present human past 134 17 translation present 17 27  previously constructed for these sentences. In many cases, there is nothing overt in the sentence which would specify tense, so a mismatch might not actually be &amp;quot;wrong&amp;quot;. Also, there are a number of sentences which were not directly applicable for comparison, such as when the human translator chose a different syntactic structure or a complex tense. The newspaper articles were divided into 80 sentences. Since some of these sentences were conjunctions, this yielded 99 tensed main verbs. These verbs either appeared in simple present, past, present or past perfect('has or had verb-t-ed), present or past imperfective (is verb-l-lag , was verb--I--lag) and their corresponding passive (is being kicked, was being kicked, have been kicked) forms. For cases like the present perfect ('has kicked), we noted the intended meaning ( e.g past activity) expressed by the verb as well as the verb's actual present perfective form. We scored the form as correct if the system translated a present perfective with past tense meaning as a simple past or present perfective. There were 10 instances where a verb in the human translation had no corresponding verb in the machine translation, either due to incorrect omission or correct substitution of the corresponding nominalization. We excluded these forms from consideration. If the system fails to supply a verb for independent reasons, our system clearly can't mark it with tense. The results of our evaluation are summarized in Table 2.</Paragraph>
      <Paragraph position="1"> These results definitely improve over our previous heuristic, which was to always use past tense (assuming this to be the default mode for newspaper article reporting). Results are also better than always picking present tense. These results seem to indicate that atelicity is a fairly good cue for present tense. We also note that 8 out of the 14 cases where the human translation used the present tense while the system used past tense are headlines. Headlines are written using the historical present in English (&amp;quot;Man bites Dog&amp;quot;). These sentences would not be incorrectly translated in the past (&amp;quot;The Man Bit the Dog&amp;quot;) Therefore, a fairer judgement might leave only remaining 6 incorrect cases in this cell. Using atelicity as a cue for the present yields correct results approximately 65incorrect results 35worst case results because they do not take into account presence or absence of the grammatical perfective and progressive markers referred to in the introduction.</Paragraph>
    </Section>
    <Section position="2" start_page="39" end_page="39" type="sub_section">
      <SectionTitle>
8.2 Relationship between clauses
</SectionTitle>
      <Paragraph position="0"> Results are more preliminary for the clausal connectives. Of the 80 sentences, 35 of them are flagged as (possibly) containing events or states directly modifying other events or states. However, of this number, some actually do have lexical connectives represented as featural rather than structural elements in the LCS, and can be straightforwardly realized using translated English connectives such as since, after, and if.then. Other apparently &amp;quot;modifying&amp;quot; events or states should be treated as a complement relationship (at least according to the preferred reading in ambiguous cases), but are incorrectly analyzed as being in a non-complement relationship, or have other structural problems rendering the interlingua representation and English output not directly related to the original clause structure.</Paragraph>
      <Paragraph position="1"> Of the remaining clear cases, six while relationships were generated according to our heuristics, indicating cotemporaneousness of main and modifying situation, e.g. (7)a,b, in the automated translations of (1) and (2), respectively. None were inappropriate. Of the cases where then was generated, indicating sequential events, there were four cases in which this was appropriate, and three cases in which the situations really should have been cotemporaneous.</Paragraph>
      <Paragraph position="2"> While these numbers are small, this preliminary data seems to suggest again that atelicity is a good cue for cotemporality, while telicity is not a sufficient cue.</Paragraph>
      <Paragraph position="3"> (7) a. Before 1965, China altogether only have the ability shipbuilding about 300 thousand tons , while the annual output is 80 thousand tons.</Paragraph>
      <Paragraph position="4"> b. this 80 thousand tons actually includes 517 ships, while the ship tonnage is very low.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>