<?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="4" start_page="572" end_page="572" type="metho">
    <SectionTitle>
EVENTTYPE
NON-DURATIVE, INCHOATIVE
</SectionTitle>
    <Paragraph position="0"/>
    <Paragraph position="2"> The abbreviations denote: Tb~, Ten,t: start, end time of the event; SB, SE: scene begin and scene end; I)IR, LOC, STAT, RED: directional (turn off, return), locomotion (walk, overtake), and static (stand, wait) verbs, finally verbs whose recognition implies reference objects (reach s. th., arrive at).</Paragraph>
    <Paragraph position="3"> The figure has to be read as follows. If an inchoative event like losfahren (start moving) has to be verbalized which has the verbtype locomotion, then choose direction? and locative? as deep cases. The question mark generally means, look into the partnermodel Lo see whether this deep case has already been generated fi)r another event. If so, determine by use of the object's actual location (represnnted in the scene representation) whether it is still valid. If this is the case don't generate a uatural language expression for this deep case, otherwise do.</Paragraph>
    <Paragraph position="4"> Presently the partnermodel contains information about the static background of the scene and about what has been said so far in the same relational notation as was shown for instantiations in section 2. It is being updated when an event is verbalized.</Paragraph>
    <Paragraph position="5"> Note, that for durative events the decision is based on whether the start and end time of the event coincide with the beginning or ending of the image sequence. Consider the first case for durative events as given in figure 2. Right from the beginning of the sequence there is a car moving along a street until the sequence ends. In such a case it is not possible to verbalize a source as the object may have started its motion anywhere. To restrict the hearer's visualization, direction and locative cases are verbalized, leading to a sentence like: The car moves on Schliiterstreet in direction of HaHerplace.</Paragraph>
    <Paragraph position="6"> Verbalizing a direction when the static background is known restricts the trajectory to being on one side of the road. Basically, our direction case is a goal or source ease where only two prepositional phrases are allowed, the German phrases in Richtung and aus Richtung (in direction~ from direction). These phrases do not imply that the motion ends at the goal location as do most prepositional phrases in German which have to be in accusative surface case to denote a goal. The English language is in this respect inherently ambiguous. In the sentence The car moves behind the truck, the phrase behind the truck may denote a locative or goal deep case. In German these eases arc distinguished at the surface.</Paragraph>
    <Paragraph position="7"> \[&amp;quot;or locative the above sentence translates to Des Aitto f~hrt hinter dem LKW, for the goal case, it translates to Des Auto f~hrt hinter den LKW.</Paragraph>
    <Paragraph position="8"> We have to distinguish different verbtypes as e.g. the meaning of a directional phrase changes with the verl)type. Consider the sentences The car moves in direction of Hallerplace versus The car stands in direction of l\[allerplace (in German both sentences arc well formed). The first sentence denotes the direction of the motion whereas the second one denotes the orientation of I, hc car.</Paragraph>
    <Paragraph position="9"> We thns distinguish between static (STAT) and h)eomotion (LOC) verbs. The third verbtype, directional (I)IR), is used for verbs with a strong directional component like umkehren (return), abbiegen (turn off), etc. As they already imply a certain direction the additional verbalization of a direction using a prepositional phrase does usually not lead to acceptable sentences. The fourth type (REO) is used tbr verbs like erreichen (reach s. th.) having an obligatory locative case.</Paragraph>
    <Paragraph position="10"> The main result to note here is that the selection processes are low-level and verboriented. The only higher level goal is to inform the hearer and to convey as ranch information about an event as possible. In the next section we show by differem; verbalizations of the same scene how rather complex syntactic structures arise.</Paragraph>
  </Section>
  <Section position="5" start_page="572" end_page="574" type="metho">
    <SectionTitle>
5 Generation
</SectionTitle>
    <Paragraph position="0"> The general scheme for the generation process is as follows:  1. Sort the objects according to their classmembership, vehicles first, then persons; 2. in the above partial order sort the objects according to their time of occurrence in the scene, earliest first; 3. do for all elements in each verbalization list of each object (a) if the current event has a precedent and its event time is included in the precedent's, begin the sentence with dabei (in the meantime); go to (c); (b) if the current event has a precedent and its event time overlaps the precedent's, begin the sentence with unterdessen (approx, in the meantime); go to (c); (c) determine the optional deep cases and build a simple  declarative sentence by using all chosen deep cases and applying the deep case semantics.</Paragraph>
    <Paragraph position="1"> Two temporally consecutive events are not verbalized using a temporal adverb as in the cases of inclusion and overlapping. This is due to the fact that from the linear order of the sentences the hearer usually infers consecutivity.</Paragraph>
    <Paragraph position="2"> The result of the above algorithm is a formal representation of the surface sentence which, rougidy, contains the w~rb's stem, gemls verbi, modality, and person, all deep cases in random order, and all stems of the \[exical entries which appear in the surface sentence. This representation is taken as input by the system SUTRA (for further details on the formal represeutation and the SUTRA system see \[41) which then generates a correctly inflected German sentence. Below is an example of the output of NAOS.</Paragraph>
    <Paragraph position="3"> 18. ,ausgabe text  The tall pedestrian walks hJ the direction of Dammtnr on the southern sidewalk west of Sehlseterstreet. h~ the meantime he recedes from the department of compnter science.</Paragraph>
    <Paragraph position="4"> 19. ,logout The first sentence above is a standard one having the same structure for all different scenes. The remaining four paragraphs are motion descriptions for the tbur moving objects.</Paragraph>
    <Paragraph position="5"> We now discuss step (c) of the above algorithm in more detail as it covers some interesting phenomena.</Paragraph>
    <Paragraph position="6"> Consider the third paragraph describing the motions of the yellow VW. The verbalization list for this object is:</Paragraph>
    <Paragraph position="8"> The beginning (SB) and ending of the sequence (SE) lie at points 0 and 40, respectively. According to the selection algorithm (figure 3) a SOURCE should be verbalized for a durative event with the above event time if the verbtype is LOC. The generation algorithm checks whether the chosen optional cases are allowed for the verb, if so, it is further checked whether the combinations are allowed.</Paragraph>
    <Paragraph position="9"> As a SOURCE may not be generated alone for a fahren (drive, move) event, SOURCE and GOAL are generated.</Paragraph>
    <Paragraph position="10"> The fourth paragraph shows the outcome of a deep case selection in which the chosen case is not allowed for the verb. The verbalization llst for the black BMW contains only ilberholen (overtake) and entfernen-r (recede).</Paragraph>
    <Paragraph position="11"> (((OVERTAKE BMWI VWI (10 12)(12 32) (10 32)) ((RECEDE Bl~qt ~/2 20 40) (32 40))) According to event- and verhtype DIRECTION is chosen as the appropriate deep case. As this case may not be used with the verb overtake two sentences are generated, one describing the direction  of the motion and the other one describing tbe specific event. The second sentence begins with a temporal advert) specifying that both motions occur at the same time. In order to generate the two sentences first the classmembership of the agent of the verb which may not take the chosen deep case is determined. Then the speeializationhierarehy is used to go up to either fahren (driv% move) or gnhen (walk) as those verbs may take any deep case. Then the sentences are generated.</Paragraph>
    <Paragraph position="12"> Consider the following verbalization list:  Assuming the direction and location of the motion to be the same as before the algorithm presented so fat&amp;quot; would generate A black BMW drives in the direction of Hallerplace. During this time it overtakes the yellow VW in front of the department of computer science. The black BMW drives.</Paragraph>
    <Paragraph position="13"> According to the deep ease selection algorithm a DIRECTION and LOCATIVE should be generated for the second event above.</Paragraph>
    <Paragraph position="14"> As both cases have already been generated with the first event and are still valid the sentence The black BMW drives is not generated because before generating a sentence it is checked whether the intbrmation is already known to the partner.</Paragraph>
    <Section position="1" start_page="573" end_page="574" type="sub_section">
      <SectionTitle>
5.1 Referring Phrases
</SectionTitle>
      <Paragraph position="0"> In this section some aspects of the referring phrase generator are discussed. As can be seen from the example text objects are characterized by their properties, introdueed with indefinite noun phrases when they are not single representatives of a class and they may also be pronominalized to add to the coherence of the text.</Paragraph>
      <Paragraph position="1"> Therefore we use standard techniques as e.g. described in \[8\], \[9\].</Paragraph>
      <Paragraph position="2"> We want to stress one aspect of our referring phrase generator, namely its capability to generate restrictive relative clauses with motion verbs. As it may be easily the ease that a scene contains two objects with similar properties the task arises to distinguish them and generate unequivocal referring expressions.</Paragraph>
      <Paragraph position="3"> It is an interesting fact, that, we have several options to cope with this problem which each have their consequences.</Paragraph>
      <Paragraph position="4"> One option is to adopt McDonald's scheme of generation without precisely knowing what to say next \[13\]. According to this scheme two similar objects are characterized in the following way in NAOS. When the first one is introduced it is characterized by it's properties e.g. a yellow VW. When the second one has to be introduced, REF notices that a yellow VW is already known to the partner and generates the phrase another yellow VW. It starts getting interesting in subsequent reference. The objects are then characterized by the events in which they were involved earlier whether as agent or in another role. This leads to referring phrases like the yellow VW, which receded from the pedestrian or the yellow VW, which has been overtaken. Note, how passive relative clauses arise naturally from the task of generating referring phrases in this paradigm. The same is also true for negation. Consider the case where the first yellow VW, say VWI, has passed an object and the second yellow VW, say VW2, has overtaken an object and both event,s are already known to the partner. If REF has to generate again a referring phrase for VWI it notices that pass is a more general verb than overtake and may thus also be applied for the overtake event. It therefore generates the phrase the yellow VW, which has not overtaken the other object to distinguish it unequivocally from VW2, Below is an example of this strategy in a texL for the same scene as above. The difference to the th'st scene is that we replaced the green VW by a yellow one.</Paragraph>
      <Paragraph position="5"> 10. ,ausgabe text;</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="574" end_page="574" type="metho">
    <SectionTitle>
UEBERIIOILT WORI)F,N IST.
</SectionTitle>
    <Paragraph position="0"> A black BMW drives in direction of Ifallerphtce. Dewing this time it overtakes the other VW which receded fronl the yellow VW, is ti'oet of the department of computer science. Tile black BMW recedes fl'om the yellow VW which was not ow~rtaken.</Paragraph>
  </Section>
  <Section position="7" start_page="574" end_page="574" type="metho">
    <SectionTitle>
I)EI{ GROSSE FUSS(.~AEN(\]Ie, R (IEIIT IN R1.CIITUNG
I)AMMTOR AUF I)I,,M SUEI)LICHI,2N I,'USSWEG WEST-
LICH DER SCIILUI'~TIt',I{STRASSE. WAIi;III{ENDI)FSSI,;N ENT-
FERNT El1. SICH VON I)FM FACIIBh'J~.E\[Clt INFORMATIK.
</SectionTitle>
    <Paragraph position="0"> &amp;quot;/'lie tall pedestrian walks in direction of Dammtor on the southern sidewalk west of Schlueterstreet. \[n the meantime he recedes from the department of computer science.</Paragraph>
    <Paragraph position="1"> 11. ,logout The consequences of this first option are rather complex syntactic structures whieh are not inotivated by higher level stylisl.ic choices.</Paragraph>
    <Paragraph position="2"> 1,el us now look at a second opt, ion which has also been implemented. Experience with the above algorithm for dill%rent scenes showed, that if more than two similar objects are in a scene the restrictive relative clauses become hardly mlderstandable. We ~,hus determine how many similar objects there are in the scene before we start the generation process. If there are more than two, REF generates names for them and introduces them as e.g. the first yellow VW, the second yellow VW and so on and uses these phrases in subsequent references. An example of this strategy would look like the first example text where the different vehicles are nanmd l, he first ..., the second .... Tbe rest of the text would remain the same.</Paragraph>
    <Paragraph position="3"> Taking this option implies leaving McDonald's scheme and approaching to a planning paradigm.</Paragraph>
    <Paragraph position="4"> It should be noted here that there is a third optimt which has hardly been investigated, namely to switch frmn contextual to cotextual reference as in phrases like the VW I mentioned last. We need filrther research hefore we can use such techniques effectively.</Paragraph>
  </Section>
class="xml-element"></Paper>