Univ., Diss.--Hamburg, 2004.

Nous présentons une recherche en ingénierie des connaissances appliquée aux prédicats linguistiques et aux définitions lexicographiques de la théorie Sens-Texte (TST). Notre méthodologie comporte trois étapes. 1. Nous montrons en quoi la conceptualisation de la TST devrait être étendue pour faciliter sa formalisation. Nous justifions la nécessité de définir un niveau sémantique profond (SemP) à base de graphes. Nous y définissons la notion de type d'unité sémantique profonde et sa structure actancielle, de sorte que leur organisation hiérarchique puisse correspondre à une hiérarchie de sens au sein de laquelle ces structures actancielles sont héritées et spécialisées. Nous reconceptualisons les définitions lexicographiques au niveau SemP, et au niveau du dictionnaire. Finalement, nous présentons un prototype d'éditeur de définitions basé sur la manipulation directe de graphes. 2. Nous proposons un formalisme de représentation des connaissances adapté à cette conceptualisation. Nous démontrons que les logiques de description et le formalisme des Graphes Conceptuels ne sont pas adaptés, et nous construisons alors un nouveau formalisme, dit des Graphes d'Unités. 3. Nous étudions l'opérationnalisation du formalisme des Graphes d'Unités. Nous lui associons une sémantique formelle basée sur la théorie des modèles et l'algèbre relationnelle, et montrons que les conditions de décidabilité du raisonnement logique correspondent aux intuitions des lexicographes. Nous proposons également une implémentation du formalisme avec les standards du web sémantique, ce qui permet de profiter des architectures existantes pour l'interopérationnalisation sur le web des données lexicales liées. / We present our research in applying knowledge engineering to linguistic predicates and lexicographic definitions of the Meaning-Text Theory (MTT). We adopt a three-step methodology. 1. We first show how the MTT conceptualization should be extended to ease its formalization. We justify the need of defining a new graph-based deep semantic level. We define the notion of deep semantic unit types and its actantial structure, so that their hierarchical organization may correspond to a hierarchy of meanings, inside which actantial structures are inherited and specialized. We re-conceptualize lexicographic definitions at the deep semantic level, and at the level of dictionaries. Finally, we present a definition editor prototype based on graph direct manipulation, which will allow us, in future work, to integrate our formal model into explanatory combinatorial lexicographic projects. 2. We then propose a knowledge representation formalism (KR) adapted for this conceptualization. We demonstrate that Description Logics and the Conceptual Graphs formalism do not fit our needs. This leads us to construct a new knowledge representation formalism: the Unit Graphs formalism. 3. Finally, we operationalize the Unit Graphs formalism. We assign it a formal semantic model, which we create based on model theory and relational algebra. We then show that the reasoning decidability conditions match the intuitions that lexicographers have. We also provide an implementation using semantic web standards, which enable us to use existing architectures for sharing, interoperability, and knowledge querying over the web of lexical linked data.

Unmittelbar nach den Tode beginnen im Koerper chemische Prozesse. Waehrend der Zersetung des Gewebes gehen vom Koerper verschieden Gerueche aus - je nach Dekompositionsstadium. Da aasfressende Insektenarten durch diese charakteristischen Gerueche angelockt werden, kann ihre vorhersehbare Sukzession zusammen mit unserem Wissen ueber ihre Entwicklung genutzt werden, Rueckschlusse auf den post mortem interval (PMI) zu fuehren. Solche Berechnungen anhand von Insektenarten und ihrer Larvenentwicklung basieren auf experimentell ermittelten Daten, da das Auftreten der Arten und Temperaturadaptationen lokal variieren koennen. Jedoch sind die Zusammenhaenge zwichen den aeusseren Bedingungen, die die Dekompostion beeinflussen, und den resultierenden Geruechen unbekannt, und somit entsteht auch eine Luecke in unserem Wissen ueber die Besiedelung des Koerpers durch Insekten. Diese Studie beleuchtet die Zersetzungsprozesse in Zusammenhang auf Klima, die Produktion von fluechtigen Geruchssubstanzen der verschiedenen Dekompositionsstadien und der Attraktivitaet der fuer die Gerueche verantwortlichen Substanzen auf Aasinsekten, beispielhaft gezeigt anhand der Kaisergoldfliege Lucilia caesar Linneus, 1758 (Diptera: Calliphoridae. Weiterhin soll gezeigt werden, dass Individuen der gleichen Insektenart, die einen zersetzenden Koerper besiedeln, von verschiedenen Geruchsmustern, und somit verschiedenen Dekompositionsstadien, angelockt werden, abhaengig vonGeschlecht, Ernaehrung und Entwicklungszustand (vittellogene Phase und Paarungszustand). Die Ergebnisse tragen zum Verstaendnis von geruschssinn- und physiologisch gesteurtem Verhalten der Insekten sowie der Dekompositionsprozesse bei und ermoeglichen zuverlaessigere Leichenliegezeitbestimmungen. / After death a body undergoes chemical processes, which depend on oxygen, bacteria, temperature, humidity, and more. The longer a body remained undetected, the more important it is to know these parameters to estimate the time of death. During the decay, a dead body emits a series of odour types, depending on the stage of decomposition. As necrophagous insect species are attracted by the characteristical decomposition odour, we use their predictable succession on a corpse and our knowledge about the larval development rates to draw conclusions about the post mortem interval (PMI). These estimations are based on case-studies and locally collected data as insect succession and development can vary due to external circumstances, as well as distribution and local temperature-adaptation of the insects. However, the interactions between external factors and the resulting emission of different odours and therefore on insect settlements is largely unknown. This study gives new insights on decomposition processes according to climate conditions, the production of volatile odour pattern of distinct decay stages and the attraction of necrophagous insects, exemplified on Lucilia caesar Linneus, 1758 (Diptera: Calliphoridae), to these odours and separated volatile compounds. Furthermore it is shown that insects of the same species, settling a dead body, are attracted by different odour pattern, thus by different decomposition stages, depending on their sex, nutrition and development stage (vittellogenous phase and mating status). The results contribute to the understanding of insect behaviour mediated by odour and physiological parameters, decomposition processes and help making reliable estimates of the exact time of death.

Usability aspects of programming languages are often overlooked, yet have a substantial effect on programmer productivity. These issues are even more acute in the field of Inductive Synthesis, where programs are automatically generated from sample expected input and output data, and the programmer needs to be able to comprehend, and confirm or reject the suggested programs. A promising method of Inductive Synthesis, CombInduce, which is particularly suitable for synthesizing recursive programs, is a candidate for improvements in usability as the target language Combilog is not user-friendly. The method requires the target language to be strictly compositional, hence devoid of variables, yet have the expressiveness of definite clause programs. This sets up a challenging problem for establishing a user-friendly but equally expressive target language. Alternatives to Combilog, such as Quine's Predicate-functor Logic and Schönfinkel and Curry's Combinatory Logic also do not offer a practical notation: finding a more usable representation is imperative. This thesis presents two distinct approaches towards more convenient representations which still maintain compositionality. The first is Visual Combilog (VC), a system for visualizing Combilog programs. In this approach Combilog remains as the target language for synthesis, but programs can be read and modified by interacting with the equivalent diagrams instead. VC is implemented as a split-view editor that maintains the equivalent Combilog and VC representations on-the-fly, automatically transforming them as necessary. The second approach is Combilog with Name Projection (CNP), a textual iteration of Combilog that replaces numeric argument positions with argument names. The result is a language where argument names make the notation more readable, yet compositionality is preserved by avoiding variables. Compositionality is demonstrated by implementing CombInduce with CNP as the target language, revealing that programs with the same level of recursive complexity can be synthesized in CNP equally well, and establishing the underlying method of synthesis can also work with CNP. Our evaluations of the user-friendliness of both representations are supported by a range of methods from Information Visualization, Cognitive Modelling, and Human-Computer Interaction. The increased usability of both representations are confirmed by empirical user studies: an often neglected aspect of language design.