<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1043">
  <Title>From route descriptions to sketches: a model for a text-to-image translator</Title>
  <Section position="4" start_page="0" end_page="299" type="metho">
    <SectionTitle>
2 Some translation problems
</SectionTitle>
    <Paragraph position="0"> Our first approach to translate RDs into graphic maps consisted in manually transcribing linguistic descriptions into sketches. By doing this, we encountered several problems, some of which we will try to illustrate through the following example, taken from the French corpus of (Gryl, 1992).</Paragraph>
    <Paragraph position="1"> Example 2.1 A la sortie des tourniquets du RER tu prends sur ta gauche. II y a une magni\]ique descente~ prendre. Puis tu tournes ~ droite, tu tombes sur une sdrie de panneaux d'informations. Tu continues tout droit en longeant les terrains de tennis et tu tombes sur le bdtiment A. 1 In the description here above we can observe some ambiguities, or incompleteness of information, which may be a problem for a graphic depiction. The most striking case is the information about the tennis courts: we do not know on which side of the path, right or left, they are located.</Paragraph>
    <Paragraph position="2"> 1 At the turnstiles of the RER station you turn left.</Paragraph>
    <Paragraph position="3"> There is a steep (a magnificent) downgrade to take.</Paragraph>
    <Paragraph position="4"> Then you turn right, you come across a series of sign posts. You continue straight on, passing alongside the tennis courts, and you come to building A.</Paragraph>
    <Paragraph position="5">  There is also another kind of ambiguity due to the fact that in a RD the whole path does not have to be &amp;quot;linguistically covered&amp;quot;. Consider the fragment about turning to the left (&amp;quot;tu prends sur ta gauche&amp;quot;) and the downgrade (&amp;quot;descente&amp;quot;). It is difficult to judge whether the downgrade is located right after the turn, or &amp;quot;a little further&amp;quot;. The same question holds for the right turn (&amp;quot;puis tu tournes ~ droite&amp;quot;) and the sign posts (&amp;quot;panneaux d'informations&amp;quot;): should the posts be represented as immediately following the turning point (as expressed in the text) or should there be a path between them? This kind of ambiguity is not really perceived unless we want to derive a graphic representation of the route. The information is complete enough for a real life situation of finding one's way.</Paragraph>
    <Paragraph position="6"> Another kind of problem concerns the &amp;quot;magnifique descente&amp;quot;. It would not be easy to represent a slope in a simple sketch and, even less so, its characteristic of being steep, which the French word &amp;quot;magnifique&amp;quot; suggests in this context. The incompleteness of information will occur on the graphic side this time, not all properties of the described element being possible to express in this mode.</Paragraph>
    <Paragraph position="7"> Such transcription constraints, once defined and analyzed, should be taken into account in order to obtain a &amp;quot;faithful&amp;quot; graphic representation. It seems that, in some cases, verbal-side incompleteness problems might be solved thanks to some relevant linguistic markers, as well as to the knowledge included in the conceptual model of the route. We think here in particular of the questions whether there is a significant stretch of path between two elements of environment (landmarks), or a turn and a landmark, mentioned in the text immediately one after * the other. Concerning the ambiguity related to the location of landmarks, one can either choose an arbitrary value or try to find a way of preserving the ambiguity in the graphic mode itself.</Paragraph>
    <Paragraph position="8"> We have mentioned here only some of the problems concerning the translation of RDs into graphic sketches. We have not considered those parts of linguistic description contents which are not representable by images, such as comments or evaluations (e.g. &amp;quot;you can't miss it&amp;quot;; &amp;quot;it's very simple&amp;quot;).</Paragraph>
  </Section>
  <Section position="5" start_page="299" end_page="300" type="metho">
    <SectionTitle>
3 Steps of the translation process
</SectionTitle>
    <Paragraph position="0"> Translating linguistic utterances into a pictorial code cannot be done without an intermediate representation, that is, a conceptual structure that bridges the gap between these two expression modes (Arnold, 1990). Abraham and Descl~s (1992) talk about the necessity of creating a common semantics for the two modes.</Paragraph>
    <Paragraph position="1"> In our case, the purpose of the intermediate representation is to extract from the linguistic description the information concerning the route with the aim of representing it in the form of a sketch. However, instead of trying to create a unique &amp;quot;super-structure&amp;quot;, we envisage a dual representation, with the linguistic and the conceptual levels. The core of the process of translating RDs into graphic maps will thus consist in the transition from the linguistic representation to the conceptual one.</Paragraph>
    <Paragraph position="2"> For the sake of the linguistic representation, we thought it necessary to carry out an analysis of real examples and elaborate a linguistic model of this particular type of discourse. We have worked on a corpus of 60 route descriptions in French. The analysis has been performed at two levels: the global level and the local level. Global analysis consisted in dividing descriptions into global units, defined as sequences and connections, and in categorizing these units on a functional and thematic basis. We have thus specified several categories of route description sequences, the main ones being action prescriptions (e.g. &amp;quot;tu continues tout droit&amp;quot;) and landmark indications (e.g. &amp;quot;tu tombes sur le bPStiment A.&amp;quot;). 2 The inter-sequence connections (e.g. &amp;quot;puis&amp;quot;, &amp;quot;quand&amp;quot;, &amp;quot;ou&amp;quot;: &amp;quot;then&amp;quot;, &amp;quot;when&amp;quot;, &amp;quot;or&amp;quot;), which mark the relationships between sequences or groups of sequences, have been categorized according to their functions (e.g. succession, anchorage, alternative).</Paragraph>
    <Paragraph position="3"> Local analysis consisted in the determination of semantic sub-units of descriptions and in the definition of the content of different sequences with respect to these sub-units. These latter will enable, during the processing of a RD, to extract and represent information concerning actions and landmarks, and their attributes. Thus, one of the objectives of local analysis has been to determine which types of verbs in the RD express travel actions and which ones serve to introduce landmarks. The sub-units have been further analyzed and divided into types (e.g. different types of actions).</Paragraph>
    <Paragraph position="4"> For the purpose of the conceptual representation of RDs, we need a prototypical model of their referent which is the route. We have decomposed it into a path and landmarks. A path is made up of transfers and relays. Relays are abstract points initiating transfers and may be &amp;quot;covered&amp;quot; by a turn. Landmarks can be either associated with relays or with transfers. More formally, a route is structured into a list of segments, each segment consisting of a relay and of a transfer. Landmarks are represented as possible attributes (among others) of these two ele- null ments. Having such a prototype for routes, with all elements defined in terms of attribute-value pairs, it is relatively easy to re-construct the route described by the linguistic input: the reconstruction consists in recognizing the relevant elements and in assigning values to their attributes. Using the route model, some elements missing in the text can be inferred. For example, since every route segment contains one relay (which may be a turn) and one transfer, the information concerning the fragment of the route expressed by: &amp;quot;tournez k gauche et puis droite&amp;quot; (&amp;quot;turn to the left and then to the right&amp;quot;), must be completed by adding a transfer between the two turns.</Paragraph>
    <Paragraph position="5"> Apart from models for linguistic and conceptual representations, the rules of transition have to be defined. For this purpose, it is necessary to establish relationships between different linguistic and conceptual entities. For example, the action of the type &amp;quot;progression&amp;quot; (e.g. &amp;quot;continuer&amp;quot;, &amp;quot;aller&amp;quot;) corresponds to a transfer and the actions of the type &amp;quot;change of direction&amp;quot; (e.g. &amp;quot;tourner&amp;quot;) or &amp;quot;taking a way&amp;quot; (e.g. &amp;quot;prendre la rue&amp;quot;) to a relay (which will coincide with a turn or with the beginning of a way-landmark, e.g.</Paragraph>
    <Paragraph position="6"> a street, respectively).</Paragraph>
    <Paragraph position="7"> Another aspect of modeling consists in specifying graphic objects corresponding to the entities in the route model. For the time being, we decided to do with simple symbolic elements, without a fine distinction between landmarks. The graphic symbols have been created on the basis of the information accessible from the context rather than the one contained in the &amp;quot;names&amp;quot; of landmarks. These latter are included in sketches in the form of verbal labels.</Paragraph>
    <Paragraph position="8"> Once the whole route has been reconstructed at the conceptuM level, we start to generate the corresponding graphic map, like the one here below.</Paragraph>
  </Section>
class="xml-element"></Paper>