<?xml version="1.0" standalone="yes"?>
<Paper uid="P94-1019">
  <Title>VERB SEMANTICS AND LEXICAL SELECTION</Title>
  <Section position="3" start_page="136" end_page="137" type="intro">
    <SectionTitle>
(%SEPARAT E-IN-PIEC ES-STATE
</SectionTitle>
    <Paragraph position="0"> ing).</Paragraph>
    <Paragraph position="1"> After filling the argument of each verb representation and doing an inexact match with the internal representation, the result is as.follows: conceptions 6/7 0 0 0 0 constraints 3/14 0 3/7 0 0 The system then chooses the verb ~-J&amp;quot; (duan la) as the target realization.</Paragraph>
    <Paragraph position="2"> Handling metaphorical usages - One test of our approach was its ability to match metaphorical usages, relying on a handcrafted ontology for the objects involved. We include it here to illustrate the flexibility and power of the similarity measure for handling new usages. In these examples the system effectively performs coercion of the verb arguments (Hobbs, 1986).</Paragraph>
    <Paragraph position="3"> The system was able to translate the following metaphorical usage from the Brown corpus correctly. null cfO9:86:No believer in the traditional devotion of royal servitors, the plump Pulley broke the language barrier and lured her to Cairo where she waited for nine months, vainly hoping to see Farouk.</Paragraph>
    <Paragraph position="4"> In our system, break has one sense which means loss of functionality. Its selection restriction is that the patient should be a mechanical device which fails to match language barrier. However, in our ontology, a language barrier is supposed to be an entity having functionality which has been placed in the nominal hierachy near the concept of mechanical-device. So the system can choose the break sense loss of functionality over all the other break senses as the most probable one. Based on this interpretation, the system can correctly select the Chinese verb ?YM da-po as the target realization. The correct selection becomes possible because the system has a measurement for the degree of satisfaction of the selection restrictions. In another example, ca43:lO:Other tax-exempt bonds of State and local governments hit a price peak on February P1, according to Standard gJ Poor's average. null hit is defined with the concepts %move-toward-inspace %contact-in-space %receive-fores. Since tarexempt bonds and a price peak are not physical objects, the argument structure is excluded from the HIT usage type. If the system has the knowledge that price can be changed in value and fixed at some value, and these concepts of change-in-value  and fix-at-value are near the concepts ~movetoward-in-space ~contact-in-space, the system can interpret the meaning as change-in.value and fixat-value. In this case, the correct lexical selection can be made as Ik~ da-dao. This result is predicated on the definition of hit as having concepts in three domains that are all structurally related, i.e., nearby in the hierarchy, the concepts related to prices.</Paragraph>
    <Paragraph position="5"> Methodology and experimental results Our UNICON system translates a subset (the more concrete usages) of the English break verbs from the Brown corpus into Chinese with larger freedom to choose the target verbs and more accuracy than the TranStar system. Our coverage has been extended to include verbs from the semantically similar hit, touch, break and cut classes as defined by Beth Levin. Twenty-one English verbs from these classes have been encoded in the system. Four hundred Brown corpus sentences which contain these 21 English verbs have been selected, Among them, 100 sentences with concrete objects are used as training samples. The verbs were translated into Chinese verbs. The other 300 sentences are divided into two test sets. Test set one contains 154 sentences that are carefully chosen to make sure the verb takes a concrete object as its patient. For test set one, the lexical selection of the system got a correct rate 57.8% before encoding the meaning of the unknown verb arguments; and a correct rate 99.45% after giving the unknown English words conceptual meanings in the system's conceptual hierarchy. The second test set contains 116 sentences including sentences with non-concrete objects, metaphors, etc. The lexical selection of the system got a correct rate of 31% before encoding the unknown verb arguments, a 75% correct rate after adding meanings and a 88.8% correct rate after extended selection process applied. The extended selection process relaxes the constraints and attempts to find out the best possible target verb with the similarity measure.</Paragraph>
    <Paragraph position="6"> From these tests, we can see the benefit of defining the verbs on several cognitive domains. The conceptual hierarchical structure provides a way of measuring the similarities among different verb senses; with relaxation, metaphorical processing becomes possible. The correct rate is improved by 13.8% by using this extended selection process.</Paragraph>
    <Paragraph position="7">  With examples from the translation of English to Chinese we have shown that verb semantic representation has great impact on the quality of lexical selection. Selection restrictions on verb arguments can only define default situations for verb events, and are often overridden by context information. Therefore, we propose a novel method for defining verbs based on a set of shared semantic domains. This representation scheme not only takes care of the semantic-syntactic correspondence, but also provides similarity measures for the system for the performance of inexact matches based on verb meanings. The conceptual similarity has priority over selection constrants on the verb arguments. We leave scaling up the system to future work.</Paragraph>
  </Section>
class="xml-element"></Paper>