<?xml version="1.0" standalone="yes"?>
<Paper uid="C88-2130">
  <Title>Directing the Generation of Living Space Descriptions</Title>
  <Section position="3" start_page="626" end_page="628" type="metho">
    <SectionTitle>
3. The representation
</SectionTitle>
    <Paragraph position="0"> Practically any familiar representation language that one might &amp;quot;take off the shelf.' to use in modeling the information needed for the description of a house will be technically deficient in several ways when one comes to use it as a source for generation: it may not supply first-class objects for the information units a natural language can reference; its taxonomic hierarchy may provide the wrong generalizations, and so on. To avoid these problems, we developed our own representation system, essentially a system for building a classic semantic net.2 Every minimal fact and item to which a text can refer is its own first-class object, as are the relationships among them. We refer to these objects as noumena,3 and presently break them down into three basic types, reflecting differences in how they are mapped to the realization component.</Paragraph>
    <Paragraph position="1"> objects, such as kitchen-window and sink relations, such as has-property and next--to propenies, such as large and picture-window-like Noumena have links to selected other noumena.</Paragraph>
    <Paragraph position="2"> iThese are the basis of the connectivity that (tacitly) makes a given knowledge base into a coherent whole, and allows the descriptive strategies to navigate it.</Paragraph>
    <Paragraph position="3"> Connections are introduced on an empirical basis wherever noumena are related in such a way that they can be combined by a strategy in some description as determined by our analysis of the corpus, The knowledge base for a given living space consists of all the noumena that might reasonably be mentioned, given our analysis.</Paragraph>
    <Paragraph position="4"> While deliberate connections between noumena may seem to be begging the question, they account for a phenomenon that cannot be neglected, namely why it is that it never occurs to anyone to say, e.g., the toilet is next to the stove. If all aspects of describing a living space are data-directed, i.e. following or choosing among already established connections, then a speaker will never even think about infeasible possibilities. One can easily imagine other architectures, such as simply lumping all objects into a common heap organized by their salience, where one would have to actively search for interesting relations by methods like generate and  4est. Such a design would make different predictions i.</Paragraph>
    <Paragraph position="5"> 2 At this point we clo not include any sort of part-whole hierarchy such as house dominating room dominating furniture. If such a structure eventually emerges as a generalization that, say, simplifies the statement of our strategies, then this will suggest that it is inherent in the conceptualization of the task. On the other hand if we build in a hierarchy a priori, we will never know whether the slrueture is them only because we put it there. 3 Singular: noumenon; a Greek word used by Kant to mean a thing- in-itself, independent of sensuous or intellectual perception of it. ,627 about resource demands and processing effort than ours would. 4 4. Strategies and meta-strategies  A description is a controlled traversal of the knowledge base.5 No component of this traversal is precomputed; that is, there are no &amp;quot;plans&amp;quot; which dictate a priori the structure of the description. Instead, control is handled by strategies, which are dynamically selected and linked together by meta-strategies. A strategy, when chosen, operates in a context which determines how it will traverse (its part of) the knowledge base.</Paragraph>
    <Paragraph position="6"> This context is composed of the most recently visited noumenon, all of the untraversed links emanating from it, and the most recently used strategy. There are other factors which feed into the context, many of which can be conceptualized as parameters which&amp;quot; bias the choices of strategies within a particular house description. One such parameter is level of detail: a description may or may not include the more detailed descriptions of objects within it.</Paragraph>
    <Paragraph position="7"> We believe that this implementation of the context is sufficient to account for most of the choices of strategies that could be made. However there are clearly cases in which a richer context is required, for example, And the door, again, is in the same relationship to the windows as it is in Penni's room. Here we need to model! some awareness of previous patterns and the ability to refer to them in constructing new descriptions.</Paragraph>
    <Paragraph position="8"> We have so far identified approximately 15 strategies in our corpus, each grouping noumena together and ordering their presentation. Typical strategies include moves such as circular sweep, in which the speaker picks an anchor point in a room, and describes the room's features or contents in an order determined by their placement along the circumference of the room: look right - look left, in which the speaker describes features to either side of a mental reference point, or follow a hallway, one of the strategies by which a speaker shifts to a new vantage point.</Paragraph>
    <Paragraph position="9"> To understand this better, let us look at how the strategies and recta-strategies come into play in\[ 4 An arguably equivalent and perhaps preferable representation might be a non-propositional geometrical model after the fashion of an architect's drawing. However, we have never seen any evidence of the precision that such a representation would bring with it (quite the contrary), and have found many conventional aspects to the descriptions in our corpus that would be quite at odds with a model that captured the actual visual appearance of the house.</Paragraph>
    <Paragraph position="10"> 5 Our observations agree with Linde's that a minimal description mentions all of the rooms (except possibly the bathroom) and their spatial relation to each other. Apt keeps track of rooms (and other noumena) mentioned, and simply stops when all the rooms have been mentioned.</Paragraph>
    <Paragraph position="11">  generating this excerpt from a description by a subject named Lisa. (This is an implemented example that APT has actually produced.) Then, in the kitchen,(1) there's a large window which faces the backyard, with two flanking windows.(2) And, if we're facing the backyard,(3) on the righthand side is a sliding glass door, and then a small window. If we're again facing the backyard,(4) on the lefthand side is the stove, then a refrigerator. And, beneath that large window is the sink,(5) and on the righthand side is the dishwasher, This segment starts with a preposed adverbial to mark a shift of vantage point.(1) Upon entering a major room a meta-strategy preferring any especially salient objects over object sequences applies, giving us the matrix clause of the first sentence.(2) That window is connected to three sets of objects, each of which is organized by a sweep strategy. This pattern (i.e. a salient object that is the nexus of several sweeps) triggers a room-sweep meta-strategy that anchors them all to the same object (the window), expressing the sweeps as displacements from this anchor using deietic terms (righthand side, and then) and reorienting to the salient focal point between sweeps.(3,4, 5) A recta-strategy, probably specific to Lisa, prefers starting with &amp;quot;righthand&amp;quot; alternatives, thus giving the sweeps their order.</Paragraph>
  </Section>
  <Section position="4" start_page="628" end_page="628" type="metho">
    <SectionTitle>
5. Linguistic choices
</SectionTitle>
    <Paragraph position="0"> Thus far we have been talking about issues of what we would call &amp;quot;orchestration&amp;quot;: planning the text structure that provides the order of presentation, segmentation into sentences, and the textual function and salience of a body of information that has been selected for inclusion in an utterance. We must also look at issues in &amp;quot;mapping&amp;quot;: selecting the specific wording and choice of construction that will realize a given noumenon.6 Lexical selection is in most respects a non-issue in living space descriptions. Nearly every physical object has an obvious and very over-learned name (e.g. kitchen, bathroom, sink, refrigerator), making the process one of simple retrieval rather than judgment and planning. The exceptions are, as one would predict, the objects whose associated common nouns do not pick them out uniquely, such as &amp;quot;hallway&amp;quot;, &amp;quot;closet&amp;quot;, or &amp;quot;window&amp;quot;. For these APT will have to explicitly construct descriptions by folding in restrictive modifiers as they are needed. In the corpus, such descriptions were most often constructed</Paragraph>
  </Section>
  <Section position="5" start_page="628" end_page="628" type="metho">
    <SectionTitle>
6 The other principal activities of generation (as we see it) are &amp;quot;selection&amp;quot;, which is in most respects trivial in this domain since we
</SectionTitle>
    <Paragraph position="0"> stipulate that all of the noumena in the knowledge base are to be mentioned, and &amp;quot;realization&amp;quot;, which is carded out by the program Mumhlo-86 in the fashion described in Meteer et al. 1987.</Paragraph>
    <Paragraph position="1"> from the same sort of spatial information used in clauses.</Paragraph>
    <Paragraph position="2"> Thus we have references to a large hallway that leads into the kitchen, or the smaller hallway that leads, to the bedrooms. After it has been mentioned a few times, a description will be abbreviated and eanonicalized: that wide hallway, that smaller hallway, with or without further (non-restrictive) modification.</Paragraph>
    <Paragraph position="3"> Choosing syntactic constructions is a constrained problem in this task, since our corpus contains surprisingly few construction types. For example, once affective comments and digressions have been removed, more than half of all clauses fall within the class locative relation: there is &lt;object&gt; &lt;at location&gt; &lt;at location&gt; there is &lt;object&gt; , &lt;at location&gt;/s &lt;object&gt; &lt;object&gt; is &lt;at location&gt; &lt;objectl&gt; has &lt;object2&gt; at &lt;location&gt; Which construction is selected is determined by a set of discourse-level heuristics. For example within a sweep the &amp;quot;&lt;at location&gt; is &lt;object&gt;&amp;quot; choice is natural because it facilitates chaining. Breaks between discourse segments can be flagged with a marked construction like There-Insertion (Then there's Sabine's room on the right, as opposed to Sabine's room is on the right).</Paragraph>
  </Section>
class="xml-element"></Paper>