<?xml version="1.0" standalone="yes"?>
<Paper uid="C86-1134">
  <Title>LOC RED DEEP CASES LOCATIVE? DIRECTION?, LOCATIVE? DIRECTION? LOCATIVE? NIL NIL LOCATIVE? DIRECTION?, LOCATIVE? LOCATIVE? NIL DIRECTION? LOCATIVE? LOCATIVE? SOURCE?, DIRECTION? NIL</Title>
  <Section position="3" start_page="570" end_page="572" type="intro">
    <SectionTitle>
4 The ~3election Problem
</SectionTitle>
    <Paragraph position="0"> Usually this ln'oblem is divided intc~ the subtasks of deeiding what to mxy and how t,. say it,. As mentioned above NAOS uses two selection processes. First, it selects amoug the instantiated events and second, it selects among the optional deep cases of the verb associated with the choseu evellt. The first selection process corresponds to deciding what to say and the second one determines largely how to say it as will be shown later.</Paragraph>
    <Paragraph position="1"> The selection processes are based on the representation of the ease semantics of an event model and on a specialization hierarchy of the verbs. Below is the representation of the case semantics for tile event model iiberholen (overtake).</Paragraph>
    <Paragraph position="3"> contains first the verb stem of iiberholen as needed by the generation component and second the formal notation for an instantiation. The obligatory cases must be generated but may be omitted in the surface string in case of elliptic utterances whereas optional deep cases need not be generated at all. In the combinations slot it is represented which deep cases may be generated together (e.g. for the verb fahren (drive) it is not allowed to generate a single SOURCE but instead SOURCE and GOAL must be generated). The Lot-preps slot specifies the prepositions which may be used with the verb iiberholen to generate locative expressions.</Paragraph>
    <Paragraph position="4"> The case descriptions in the obligatory and optional slots consist of two parts: a declaration of an identifier for the case expression on the language side, and a predicate (in general a list of predicates) relating the case expression to the scene data. The most important predicates are REF, TIME-REF, and LOC-REF.</Paragraph>
    <Paragraph position="5"> REF generates referring phrases for internal object descriptors like BMW1. TIME-REF generates the tense of the verb. As descriptions are usually given in present tense, presently TIME-REF only generates this tensc. LOC-REF relates the abstract location of the object as given by its coordinates to a natural language expression for a reference object. Note, that REF has to be used to generate a referring phrase for the reference object. Consider the sixth entry of the database in section 2. The instantiation only contains internal identifiers for objects, like traflic-lightl, for which referring phrases have to be generated (see section 4 for further details on REF).</Paragraph>
    <Paragraph position="6"> In NAOS we use a specialization hierarchy for motion verbs.</Paragraph>
    <Paragraph position="7"> This hierarchy is pragmatically motivated and is rooted in situational semantics. It is no hierarchy of motion concepts as the one proposed in \[23\]. It connects general verbs witb more special ones.</Paragraph>
    <Paragraph position="8"> A situation which may be described using a special verb implies the application of all more general verbs Take for instance the verb iiberholen (overtake). \[t implies the use of the more general verbs vorueberfahren~ vorl)nifahren (drive past), passieren (pass), naehern-r (approach), entfernen-r (recede), fahren (drive, move), and bewegen-r (move).</Paragraph>
    <Paragraph position="9"> It shonld be intuitively plausible that such a hierarchy is also used for event recognition. If, for instance, no naehern-r (approach) can be instantiated the more special events need not be tested.</Paragraph>
    <Section position="1" start_page="571" end_page="572" type="sub_section">
      <SectionTitle>
4.1 Event Selection
</SectionTitle>
      <Paragraph position="0"> In NAOS the overall strategy for generating a descriptive text is as follows:  * Group all moving objects according to their classmembership; * For each object in each group describe the motions of the object for the time interval during which it was visible in the scene, Event selection for an object is done according to the following algorithm: 1. Collect all events in the interval where the object was visible and where the object was the agent; 2. determine for each timepoint during the object's visibility the most special event of the above collected ones; 3. if two events have the same specificity then either take the  one which started earlier and has the same or longer duration as the other one or take the one with longer duration; 4. put the selected events on the verbalization list of the object in temporally consecutive order.</Paragraph>
      <Paragraph position="1"> Consider the following example. All events which were found for PERSON1 are:  interval in which the event was the most special one.)</Paragraph>
    </Section>
    <Section position="2" start_page="572" end_page="572" type="sub_section">
      <SectionTitle>
4.2 Selection of Optional Deep Cases
</SectionTitle>
      <Paragraph position="0"> This selection process is our first implementation of the strategy of anticipated visualization. The underlying question is: Which optional deep cases should be selected to restrict the hearer's possibilities of placing the trajectory of an object in his internal model of the static background of the scene? In NAOS the selection algorithm answering the above question is rather straightforward. It is based on the manner of action of the verb, the verbtype, and the heater's knowledge. The algorithm is graphically represented in figure 2.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>