<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1607">
  <Title>A context-dependent algorithm for generating locative expressions in physically situated environments</Title>
  <Section position="7" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
4 Discussion
</SectionTitle>
    <Paragraph position="0"> We can illustrate the framework using the visual context provided by the scene on the left of Figure 7. This context consists of two red boxes R1 and R2 and two blue balls B1 and B2. Imagine that we want to refer to B1. We begin by calling the locative incremental algorithm, Algorithm 2. This in turn calls the basic incremental algorithm, Algorithm 1, which will return the property ball. However, this is not sufficient to create a distinguishing description as B2 is also a ball. In this context the set of candidate landmarks equals {R1,R2} and the first relation in the hierarchy is topological proximity, which we model using the algorithm developed in [Kelleher and Kruijff, 2005]. The image on the right of  work: the green region on the left defines the area deemed to be proximal to R1, and the yellow region on the right defines the area deemed to be proximal to R2. It is evident that B1 is in the area proximal to R1, consequently R1 is classified as a trajector landmark. As none of the distractors (i.e., B2) are located in a region that is proximal to a candidate landmark there are no distractor landmarks. As a result when the basic incremental algorithm is called to create a distinguishing description for the trajector landmark R1 it will return box and this will be deemed to be a distinguishing locative description. The overall algorithm will then return the vector {ball, proximal, box} which would result in the realiser generating a reference of the form: the ball near the box.</Paragraph>
    <Paragraph position="1"> The relational hierarchy used by the framework has some commonalities with the relational subsumption hierarchy proposed in [Krahmer and Theune, 2002]. However, there are two important differences between them. First, an implication of the subsumption hierarchy proposed in [Krahmer and Theune, 2002] is that the semantics of the relations at lower levels in the hierarchy are subsumed by the semantics of their parent relations. For example, in the portion of the subsumption hierarchy illustrated in [Krahmer and Theune, 2002] the relation next to subsumes the relations left of and right of.</Paragraph>
    <Paragraph position="2"> By contrast, the relational hierarchy developed here is based solely on the relative cognitive load associated with the semantics of the spatial relations and makes no claims as to the semantic relationships between the semantics of the spatial relations. Secondly, [Krahmer and Theune, 2002] do not use their relational hierarchy to guide the construction of domain models.</Paragraph>
    <Paragraph position="3"> By providing a basic contextual definition of a landmark we are able to partition the context in an appropriate manner.</Paragraph>
    <Paragraph position="4"> This partitioning has two advantages: 1. it reduces the complexity of the context model construction, as the relationships between the trajector and the distractor objects or between the distractor objects themselves do not need to be computed; 2. the context used during the generation of a landmark description is always a subset of the context used for a trajector (as the trajector, its distractors and the other objects in the domain that do not stand in relation to the trajector or distractors under the relation being considered are excluded). As a result the framework avoids the issue of infinite recusion. Furthermore, the trajector-landmark relationship is automatically included as a property of the landmark as its feature based description need only distinguish it from objects that stand in relation to one of the distractor objects under the same spatial relationship.</Paragraph>
    <Paragraph position="5"> .</Paragraph>
    <Paragraph position="6"> In future work we will focus on extending the framework to handle some of the issues effecting the incremental algorithm, see [van Deemter, 2001]. For example, generating locative descriptions containing negated relations, conjunctions of relations and involving sets of objects (sets of trajectors and landmarks).</Paragraph>
  </Section>
class="xml-element"></Paper>