<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-3100">
  <Title>CARAMEL: A flexible model for interaction between the cognitive processes</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract :
</SectionTitle>
    <Paragraph position="0"> In this paper we present a general natural language processing system called CARAMEL (in French : Comprdhension Automatique de R~cits, Apprentissage et Moddlisation des E:changes Langagiers)o Over the last few years our group has developed many pro~ams to deal with differem: aspects of natural language processing: This paper describes a general m'chitectt~re tha~ integrates them in a flexible way, and provides a control strategy capable of adapting itself to the requirements of a particular ~sko The model is composed o:r three ftmd~r~ental elements &amp;quot; - a structmdegex~ memory containing pe~nanent l~owledge and wofldng structures of the system - a set of processes, dedicated to the execution of the various cogmtive tasks a supervisor, whose function is to Ixigger, to run coherently and to synchronize the pmcesseso The sysmm contains a kind of blackboaN, which b; enhanced with a control mechanism &amp;iver~ by recta-rules. This a:rchitecture is fully implementeddeg We am etm'ently developing the meta-m3es necessary to use the model for various tasks.</Paragraph>
    <Paragraph position="1"> io 5usfifieati~ ~f the approae~ Research in A\]\[ is baseA on the assumption that intelligertce can be thought of as the ~ransformafior~ ~f ~nfor~na~or~ (Newell &amp; Simon (63), Fodor (68)) in order to solve problemsdeg Viewed in this light, NL processing consists in chang~rtg represek~tat~er~s from a forma~ language to another.</Paragraph>
    <Paragraph position="2"> ~Ne PSangltages used in CARAMEL are based on concepuuff grap~ (Sowa 84). q~is ,qeuerag formalism has been exten&amp;d in order to allow sophlseica~ed inference mechanis~. Its use facilitates ~he commu~dcao'on between ~he processes.</Paragraph>
    <Paragraph position="3"> Given the diversity of knowledge sources, we are confronted with the problem of conflict resolution and resource management. The current a'end in AI is to express knowledge in a declarative form, but the independence of the know|edge sources causes artificial ambiguitydeg to order to be efficient, NL systems may need to integrate all the knowledge sourees~ btxt organizing the knowledge with this objective in mind is a rather difficult enterprise. The essential problem is the inadequacy of the control mechanisms in classical systems, no matter whether their architecture is serial, hierarchical or heterarchical. Erman et Lesser (80) suggest that a solution is to base complex systems on a blackboard architecture. This allows for distributed control, for autonomous 1. For an application of this principle in a parser, see (Sabah &amp; Rady 83).</Paragraph>
    <Paragraph position="4"> and asynchronous use of the knowledge sources. The implementation of increasingly elaborate systems leads All to multi-expert's systems, that allow for complex communications and for flexible use of metal.</Paragraph>
    <Paragraph position="5"> knowledge (Haton 89).. Nevertheless, one important problem remains : once a process is started no external control can intervene.</Paragraph>
    <Paragraph position="6"> Hence, control remains intetrnittenl.</Paragraph>
    <Paragraph position="7"> Our a~'chitecture integrates ff~se ~eas and eX o ~en~ ef~e 6l,~ck6oard model 6 9 including a conC/in.uous control system, allowing a sophisticated rt~rlwemen~ of the Wocesscs and of H~eir in~:ert,;.Ftion, qgis is reade possible by pars\[gel imp(ementa~ion.</Paragraph>
    <Paragraph position="8"> TIae arc~igec~ure ef CAgAMEL Om o model takes into account the fact that the vario~a processes cannot be, we-ordered (their order depends on the global task and the particular data to be processed) and that their management has to be based &lt;m a p~am-~h,g processdeg ~\[r, CARAMEL the sequence of pro.deg cesses to be applied in a given situation ia order to realize a given task is planned by a supervb sot. Another important role of this supervisor is to update the working memory : as it is the only one to have a global view, it is entitled to decide what representations should be kept and be updated in a global working memory.</Paragraph>
    <Paragraph position="9"> Finally, it builds a general representation of the reasoning process ; thus it can explain why a given process has been triggered.</Paragraph>
    <Paragraph position="10"> 446 1 The system may be used in such different applications as : user-friendly interfaces, on-line help in text processors, summaries of texts, intelligent tutoring systems, etc.</Paragraph>
  </Section>
class="xml-element"></Paper>