<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1216">
  <Title>Text Meaning Representation for Chinese</Title>
  <Section position="4" start_page="109" end_page="109" type="metho">
    <SectionTitle>
Concept GOVERNMENT-ACTIVITY
</SectionTitle>
    <Paragraph position="0"> DEFINITION: an activity commonly carried out by a government.</Paragraph>
  </Section>
  <Section position="5" start_page="109" end_page="109" type="metho">
    <SectionTitle>
IS-A: POLITICAL-EVENT
AGENT: HUMAN
THEME: EVENT OBJECT
ACCOMPANIER: HUMAN
LOCATION: PLACE
</SectionTitle>
    <Paragraph position="0"> This example indicates that the concept GOVERNMENT-ACTIVITY is a subclass of the concept POLITICAL-EVENT~ its case role AGENT requires its semantic value as HUMAN and its THEME requires its value as either OBJECT or EVENT~ the GOVERNMENT-ACTIVITY can also have case role ACCOMPANIER with value as HUMAN and LOCATION with value as PLACE. Any lexicon entry mapping to the concept GOVERNMENT-ACTIVITY gets extended information through this frame.</Paragraph>
  </Section>
  <Section position="6" start_page="109" end_page="109" type="metho">
    <SectionTitle>
3 Semantic Lexicon
</SectionTitle>
    <Paragraph position="0"> Semantic lexicon is another knowledge source for text meaning representation. In the M.ikroKosmos project each lexicon entry is designed as a frame with 11 zones corresponding to information relevant to orthography, morphology, syntax, semantics, syntax-semantic linking, stylistics, and database type management record, etc. The core of the lexicon frame is syntactic zone SYN-STRUC, semantic zone SEM-STRUC and their link SYNSEM zone.</Paragraph>
    <Paragraph position="1"> Syntax particular to a given language is described in the syntactical zone. The semantic zone maps a sense into an ontological concept in the case of single sense, or to several concepts in the case of multiple senses. Through the syntactic-semantic link zone the information of each word in the text can be extracted directly from lexicon database and its relevant world knowledge also can be retrieved. The general template of semantic lexicon entry is shown as follows. For a detailed description see Viegas and l~kin (1998).</Paragraph>
    <Paragraph position="2">  Chinse lexicon entry ~k in the sense of {GOVERNMENT-ACTIVITY. The SYN zone indicates that when parsing a sentence containing this entry, subcategories SUBJ and OBJ are required. The SEM zone presents the semantic value of each case role, i.e. AGENT with value HUMAN, and TttEM~ with value EVENT or OB-JECT. The SYNSEM zone provides information about the syntax-semantic linking. That is, SUBJ \[\] is linked to AGENT ~-l with value HUMAN and OBJ \[\] is linked to THEblE with value EVENT or OBJECT.</Paragraph>
    <Paragraph position="3"> Due to the lack of morphological information in Chinese, it is often the case that the same Chinese word form can be mapped to a different part of speech and has multiple senses, such as the word ~:g~: * in the context ~:~ ~:~ flowers bloom, can be an intransitive verb mapping to a concept BLOOM with the definition to produce flower.</Paragraph>
    <Paragraph position="4"> * in the context ~ ~k ~ ~ ~ the government opens the foreign trade policy, can be a transitive verb mapping to a concept GOVERNMENT-ACTIVITY with the definition an activity that is commonly carried out by a government at any level.</Paragraph>
    <Paragraph position="5"> * in the context ~ ~ ~k ~ the government carries open policy, can be an adjective mapping to OPEN-TO-PUBLIC with the definition to be available to the public.</Paragraph>
    <Paragraph position="6"> * in the context I~l~ ~k the library is open, can be an intransitive verb with the same concept OPEN-TO-PUBLIC.</Paragraph>
    <Paragraph position="7"> Using the ontological concepts as the value of semantic variables and linking them to syntactic variables makes the lexicon very informative. Figure 2. and Figure 3. present each sense and POS of the lexicon entries for the</Paragraph>
  </Section>
  <Section position="7" start_page="109" end_page="112" type="metho">
    <SectionTitle>
4 Semantic Analysis for Word
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="109" end_page="112" type="sub_section">
      <SectionTitle>
Sense Disambiguation
</SectionTitle>
      <Paragraph position="0"> The task of a semantic analyzer is to combine the knowledge contained in the ontology and lexicon and apply it to the input text to produce text meaning representation output.</Paragraph>
      <Paragraph position="1"> The central tasks involved are to retrieve the appropriate semantic constraints for each possible word sense, test each sense in context, and construct the output TMBs by instantiating the concepts in semantic zones of the word senses that best satisfy the combination of constraints. Figure 4. illustrates the process of text meaning representation. Below illustrates the process through a sentence ~ \[\]</Paragraph>
      <Paragraph position="3"> ernment has opened foreign trade policy. The syntactic analysis gives the following output:  The semantic analysis process takes the following steps: * to gather all of the possible lexicon for each of the words with instantiated each concepts.</Paragraph>
      <Paragraph position="4">  Syntactic variables are bound to one another using the syntactic patterns in the lexical entries to establish syntactic dependencies. In addition: ontological concepts referred to the semantic zones of the lexical entries are instantiated and linked through ontological relations to establish semantic dependencies. For example, the syntactic structure of the text requires ~k to be a verb. Thus: the ADJ category with sense OPEN-TO-PUBLIC-2-4 is rejected. From Figure 2. and Figure  3. both SYN zones indicate an intransitive verb that violates the required syn- null tax. Therefore, the concepts BLOOM and OPEN-TO-PUBLIC are also rejected. In the same way, the adverb ~b with sense OUTWARD-5-2 and the verb ~ with sense COMMERCE-EVENT-4-2 are also rejected because of the violation of required POS. Finally the ADJ .~ with the sense INTERNATIONAL-ATTRIBUTE-5-1 and the NOUN ~ with COMMERCE-EVENT-4-1 are selected. After all senses are determined: SYN-SEM zone binds all syntactic variables with semantic variables, i.e. SUBJ FEDERATION-I is bound to the AGENT of GOVERNMENT-ACTIVITY2-2, OBJ LAW-3 is bound to the THEME of GOVEB_NMENT-ACTIVITY-2-2.</Paragraph>
      <Paragraph position="5"> * In the next step, selectional constraints are retrieved from the ontology. Individual selectional constraints are checked. In the example, the concept GOVEthNMENT-ACTIVITY requires AGENT to be HUMAN and THEME to be EVENT or OBJECT.</Paragraph>
      <Paragraph position="6"> The lexical information indicates that the SUBJ ~ with sense FEDERATION must satisfy the AGENT of GOVERNMENT-ACTIVITY with value HUMAN. An inference rule described below checks the satisfaction. The OBJ ~ with the sense LAW satisfies THEME of GOVERNMENT- null ACTIVITY with value OBJECT. Through IS-A links it is found that LAW is a descendant of OBJECT. Therefore, the semantic constraints are satisfied.</Paragraph>
      <Paragraph position="7"> Seeking satisfaction through inference rules, the semantic analyzer does more than match selectional constraints or find the distance along IS-A links. The search inside the ontology also involves looking for metonymic type links, such as FEDERATION in a metonymic relation with HUMAN through the property HAS- null in which DOMAIN is ORGANIZATION that has subclass FEDERATION and RANGE is HUMAN. Thus, the constraint of AGENT of GOVERNAIENT-ACTIVITY to be HUMAN is satisfied.</Paragraph>
      <Paragraph position="8"> * In case multiple senses all satisfy the constraints, the concept with the shortest path is selected as the best choice. An ontological search program, Onto-Search, is presented in Onyshkevych (1997). The resulting preference values for each constralnt are combined in an efficient control and search algorithm called Hunter-Gatherer that combines constraint satisfaction~ branch and bound, and solution synthesis techniques to pick the best combination of word senses of the entire sentence in near linear time, as described in Beale (1997).</Paragraph>
      <Paragraph position="9"> * Chosen word senses are assembled into TMR frames.</Paragraph>
    </Section>
  </Section>
  <Section position="8" start_page="112" end_page="113" type="metho">
    <SectionTitle>
5 Text Meaning Representation
</SectionTitle>
    <Paragraph position="0"> i text meaning representation(TMR) is a language-neutral description of the meaning conveyed in a text. It is derived by syntactic and semantic analysis. TMR captures not only the meaning of individual words in the text, but also the relation between those words. It provides information about the lexicon-semantic dependencies. In addition, it also represents stylistic and other factors presented in the text. From the result of word sense disambiguation, TMR integrates lexical, ontological and textual information into a single hierarchical framework. Below is a TMR for the example sentence ~\[\] R~ ~:~ T  After semantic analysis~ a variety of microtheories are applied to further analyze elements of text meaning such as time, aspect: propositions, sets, co-reference, and so on..</Paragraph>
    <Paragraph position="1"> to produce a complete TMR. In the example, ASPECT-7 is applied within the scope of GOVERNMENT-ACTIVITY in which TELIC with value YES indicates the GOVERNMENT-ACTIVITY is complete that means the action  of opening foreign trade policy is done. TIME8 indicates the GOVERNMFENT-ACTIVITY happens at the time the speaker make the utterance. Thus, the meaning of the Chinese sentence ~H\] ~ ~ ~ 3&amp;quot; ~t&amp;quot; ~ ~ is completely represented in the TlVIR.</Paragraph>
  </Section>
class="xml-element"></Paper>