L'atténuation statistique des surdétections d'un correcteur grammatical symbolique

Les logiciels de correction grammaticale commettent parfois des détections illégitimes (fausses alertes), que nous appelons ici surdétections. La présente étude décrit les expériences de mise au point d’un système créé pour identifier et mettre en sourdine les surdétections produites par le correcteur du français conçu par la société Druide informatique. Plusieurs classificateurs ont été entraînés de manière supervisée sur 14 types de détections faites par le correcteur, en employant des traits couvrant di-verses informations linguistiques (dépendances et catégories syntaxiques, exploration du contexte des mots, etc.) extraites de phrases avec et sans surdétections. Huit des 14 classificateurs développés sont maintenant intégrés à la nouvelle version d’un correcteur commercial très populaire. Nos expériences ont aussi montré que les modèles de langue probabilistes, les SVM et la désambiguïsation sémantique améliorent la qualité de ces classificateurs. Ce travail est un exemple réussi de déploiement d’une approche d’apprentissage machine au service d’une application langagière grand public robuste.

Système symbolique de création de résumés de mise à jour

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal

Représentation OWL de la ressource lexicale LVF et son utilisation dans le traitement automatique de la langue

Le dictionnaire LVF (Les Verbes Français) de J. Dubois et F. Dubois-Charlier représente une des ressources lexicales les plus importantes dans la langue française qui est caractérisée par une description sémantique et syntaxique très pertinente. Le LVF a été mis disponible sous un format XML pour rendre l’accès aux informations plus commode pour les applications informatiques telles que les applications de traitement automatique de la langue française. Avec l’émergence du web sémantique et la diffusion rapide de ses technologies et standards tels que XML, RDF/RDFS et OWL, il serait intéressant de représenter LVF en un langage plus formalisé afin de mieux l’exploiter par les applications du traitement automatique de la langue ou du web sémantique. Nous en présentons dans ce mémoire une version ontologique OWL en détaillant le processus de transformation de la version XML à OWL et nous en démontrons son utilisation dans le domaine du traitement automatique de la langue avec une application d’annotation sémantique développée dans GATE.

Advances in scaling deep learning algorithms

Les algorithmes d'apprentissage profond forment un nouvel ensemble de méthodes puissantes pour l'apprentissage automatique. L'idée est de combiner des couches de facteurs latents en hierarchies. Cela requiert souvent un coût computationel plus elevé et augmente aussi le nombre de paramètres du modèle. Ainsi, l'utilisation de ces méthodes sur des problèmes à plus grande échelle demande de réduire leur coût et aussi d'améliorer leur régularisation et leur optimization. Cette thèse adresse cette question sur ces trois perspectives. Nous étudions tout d'abord le problème de réduire le coût de certains algorithmes profonds. Nous proposons deux méthodes pour entrainer des machines de Boltzmann restreintes et des auto-encodeurs débruitants sur des distributions sparses à haute dimension. Ceci est important pour l'application de ces algorithmes pour le traitement de langues naturelles. Ces deux méthodes (Dauphin et al., 2011; Dauphin and Bengio, 2013) utilisent l'échantillonage par importance pour échantilloner l'objectif de ces modèles. Nous observons que cela réduit significativement le temps d'entrainement. L'accéleration atteint 2 ordres de magnitude sur plusieurs bancs d'essai. Deuxièmement, nous introduisont un puissant régularisateur pour les méthodes profondes. Les résultats expérimentaux démontrent qu'un bon régularisateur est crucial pour obtenir de bonnes performances avec des gros réseaux (Hinton et al., 2012). Dans Rifai et al. (2011), nous proposons un nouveau régularisateur qui combine l'apprentissage non-supervisé et la propagation de tangente (Simard et al., 1992). Cette méthode exploite des principes géometriques et permit au moment de la publication d'atteindre des résultats à l'état de l'art. Finalement, nous considérons le problème d'optimiser des surfaces non-convexes à haute dimensionalité comme celle des réseaux de neurones. Tradionellement, l'abondance de minimum locaux était considéré comme la principale difficulté dans ces problèmes. Dans Dauphin et al. (2014a) nous argumentons à partir de résultats en statistique physique, de la théorie des matrices aléatoires, de la théorie des réseaux de neurones et à partir de résultats expérimentaux qu'une difficulté plus profonde provient de la prolifération de points-selle. Dans ce papier nous proposons aussi une nouvelle méthode pour l'optimisation non-convexe.

A Multilingual Query Processing System using Software Agents

The goal of this work was developing a query processing system using software agents. Open Agent Architecture framework is used for system development. The system supports queries in both Hindi and Malayalam; two prominent regional languages of India. Natural language processing techniques are used for meaning extraction from the plain query and information from database is given back to the user in his native language. The system architecture is designed in a structured way that it can be adapted to other regional languages of India. . This system can be effectively used in application areas like e-governance, agriculture, rural health, education, national resource planning, disaster management, information kiosks etc where people from all walks of life are involved.

Studies on the treatment of effluents from natural rubber processing units

The present study was undertaken to evaluate the effectiveness of a few physico-chemical and biological methods for the treatment of effluents from natural rubber processing units. The overall objective of this study is to evaluate the effectiveness of certain physico-chemical and biological methods for the treatment of effluents from natural rubber processing units. survey of the chemical characteristics of the effluents discharged from rubber processing units showed that the effluents from latex concentration units were the most polluting

Shrinking restarting automata

Restarting automata are a restricted model of computation that was introduced by Jancar et.al. to model the so-called analysis by reduction. A computation of a restarting automaton consists of a sequence of cycles such that in each cycle the automaton performs exactly one rewrite step, which replaces a small part of the tape content by another, even shorter word. Thus, each language accepted by a restarting automaton belongs to the complexity class $CSL cap NP$. Here we consider a natural generalization of this model, called shrinking restarting automaton, where we do no longer insist on the requirement that each rewrite step decreases the length of the tape content. Instead we require that there exists a weight function such that each rewrite step decreases the weight of the tape content with respect to that function. The language accepted by such an automaton still belongs to the complexity class $CSL cap NP$. While it is still unknown whether the two most general types of one-way restarting automata, the RWW-automaton and the RRWW-automaton, differ in their expressive power, we will see that the classes of languages accepted by the shrinking RWW-automaton and the shrinking RRWW-automaton coincide. As a consequence of our proof, it turns out that there exists a reduction by morphisms from the language class $cL(RRWW)$ to the class $cL(RWW)$. Further, we will see that the shrinking restarting automaton is a rather robust model of computation. Finally, we will relate shrinking RRWW-automata to finite-change automata. This will lead to some new insights into the relationships between the classes of languages characterized by (shrinking) restarting automata and some well-known time and space complexity classes.

On the Gap-Complexity of Simple RL-Automata

Analysis by reduction is a method used in linguistics for checking the correctness of sentences of natural languages. This method is modelled by restarting automata. All types of restarting automata considered in the literature up to now accept at least the deterministic context-free languages. Here we introduce and study a new type of restarting automaton, the so-called t-RL-automaton, which is an RL-automaton that is rather restricted in that it has a window of size one only, and that it works under a minimal acceptance condition. On the other hand, it is allowed to perform up to t rewrite (that is, delete) steps per cycle. Here we study the gap-complexity of these automata. The membership problem for a language that is accepted by a t-RL-automaton with a bounded number of gaps can be solved in polynomial time. On the other hand, t-RL-automata with an unbounded number of gaps accept NP-complete languages.

The Degree of Word-Expansion of Lexicalized RRWW-Automata

Restarting automata can be seen as analytical variants of classical automata as well as of regulated rewriting systems. We study a measure for the degree of nondeterminism of (context-free) languages in terms of deterministic restarting automata that are (strongly) lexicalized. This measure is based on the number of auxiliary symbols (categories) used for recognizing a language as the projection of its characteristic language onto its input alphabet. This type of recognition is typical for analysis by reduction, a method used in linguistics for the creation and verification of formal descriptions of natural languages. Our main results establish a hierarchy of classes of context-free languages and two hierarchies of classes of non-context-free languages that are based on the expansion factor of a language.

Design, implementation and application of a generic framework for integrated regional land-use modeling

Land use is a crucial link between human activities and the natural environment and one of the main driving forces of global environmental change. Large parts of the terrestrial land surface are used for agriculture, forestry, settlements and infrastructure. Given the importance of land use, it is essential to understand the multitude of influential factors and resulting land use patterns. An essential methodology to study and quantify such interactions is provided by the adoption of land-use models. By the application of land-use models, it is possible to analyze the complex structure of linkages and feedbacks and to also determine the relevance of driving forces. Modeling land use and land use changes has a long-term tradition. In particular on the regional scale, a variety of models for different regions and research questions has been created. Modeling capabilities grow with steady advances in computer technology, which on the one hand are driven by increasing computing power on the other hand by new methods in software development, e.g. object- and component-oriented architectures. In this thesis, SITE (Simulation of Terrestrial Environments), a novel framework for integrated regional sland-use modeling, will be introduced and discussed. Particular features of SITE are the notably extended capability to integrate models and the strict separation of application and implementation. These features enable efficient development, test and usage of integrated land-use models. On its system side, SITE provides generic data structures (grid, grid cells, attributes etc.) and takes over the responsibility for their administration. By means of a scripting language (Python) that has been extended by language features specific for land-use modeling, these data structures can be utilized and manipulated by modeling applications. The scripting language interpreter is embedded in SITE. The integration of sub models can be achieved via the scripting language or by usage of a generic interface provided by SITE. Furthermore, functionalities important for land-use modeling like model calibration, model tests and analysis support of simulation results have been integrated into the generic framework. During the implementation of SITE, specific emphasis was laid on expandability, maintainability and usability. Along with the modeling framework a land use model for the analysis of the stability of tropical rainforest margins was developed in the context of the collaborative research project STORMA (SFB 552). In a research area in Central Sulawesi, Indonesia, socio-environmental impacts of land-use changes were examined. SITE was used to simulate land-use dynamics in the historical period of 1981 to 2002. Analogous to that, a scenario that did not consider migration in the population dynamics, was analyzed. For the calculation of crop yields and trace gas emissions, the DAYCENT agro-ecosystem model was integrated. In this case study, it could be shown that land-use changes in the Indonesian research area could mainly be characterized by the expansion of agricultural areas at the expense of natural forest. For this reason, the situation had to be interpreted as unsustainable even though increased agricultural use implied economic improvements and higher farmers' incomes. Due to the importance of model calibration, it was explicitly addressed in the SITE architecture through the introduction of a specific component. The calibration functionality can be used by all SITE applications and enables largely automated model calibration. Calibration in SITE is understood as a process that finds an optimal or at least adequate solution for a set of arbitrarily selectable model parameters with respect to an objective function. In SITE, an objective function typically is a map comparison algorithm capable of comparing a simulation result to a reference map. Several map optimization and map comparison methodologies are available and can be combined. The STORMA land-use model was calibrated using a genetic algorithm for optimization and the figure of merit map comparison measure as objective function. The time period for the calibration ranged from 1981 to 2002. For this period, respective reference land-use maps were compiled. It could be shown, that an efficient automated model calibration with SITE is possible. Nevertheless, the selection of the calibration parameters required detailed knowledge about the underlying land-use model and cannot be automated. In another case study decreases in crop yields and resulting losses in income from coffee cultivation were analyzed and quantified under the assumption of four different deforestation scenarios. For this task, an empirical model, describing the dependence of bee pollination and resulting coffee fruit set from the distance to the closest natural forest, was integrated. Land-use simulations showed, that depending on the magnitude and location of ongoing forest conversion, pollination services are expected to decline continuously. This results in a reduction of coffee yields of up to 18% and a loss of net revenues per hectare of up to 14%. However, the study also showed that ecological and economic values can be preserved if patches of natural vegetation are conservated in the agricultural landscape. -----------------------------------------------------------------------

A Language for Interactive Cooperative Agents

Cooperative behaviour of agents within highly dynamic and nondeterministic domains is an active field of research. In particular establishing highly responsive teamwork, where agents are able to react on dynamic changes in the environment while facing unreliable communication and sensory noise, is an open problem. Moreover, modelling such responsive, cooperative behaviour is difficult. In this work, we specify a novel model for cooperative behaviour geared towards highly dynamic domains. In our approach, agents estimate each other’s decision and correct these estimations once they receive contradictory information. We aim at a comprehensive approach for agent teamwork featuring intuitive modelling capabilities for multi-agent activities, abstractions over activities and agents, and a clear operational semantic for the new model. This work encompasses a complete specification of the new language, ALICA.

Ontology merging with formal concept analysis

Ontologies have been established for knowledge sharing and are widely used as a means for conceptually structuring domains of interest. With the growing usage of ontologies, the problem of overlapping knowledge in a common domain becomes critical. In this short paper, we address two methods for merging ontologies based on Formal Concept Analysis: FCA-Merge and ONTEX. --- FCA-Merge is a method for merging ontologies following a bottom-up approach which offers a structural description of the merging process. The method is guided by application-specific instances of the given source ontologies. We apply techniques from natural language processing and formal concept analysis to derive a lattice of concepts as a structural result of FCA-Merge. The generated result is then explored and transformed into the merged ontology with human interaction. --- ONTEX is a method for systematically structuring the top-down level of ontologies. It is based on an interactive, top-down- knowledge acquisition process, which assures that the knowledge engineer considers all possible cases while avoiding redundant acquisition. The method is suited especially for creating/merging the top part(s) of the ontologies, where high accuracy is required, and for supporting the merging of two (or more) ontologies on that level.

Evolving Distributed Algorithms with Genetic Programming

Distributed systems are one of the most vital components of the economy. The most prominent example is probably the internet, a constituent element of our knowledge society. During the recent years, the number of novel network types has steadily increased. Amongst others, sensor networks, distributed systems composed of tiny computational devices with scarce resources, have emerged. The further development and heterogeneous connection of such systems imposes new requirements on the software development process. Mobile and wireless networks, for instance, have to organize themselves autonomously and must be able to react to changes in the environment and to failing nodes alike. Researching new approaches for the design of distributed algorithms may lead to methods with which these requirements can be met efficiently. In this thesis, one such method is developed, tested, and discussed in respect of its practical utility. Our new design approach for distributed algorithms is based on Genetic Programming, a member of the family of evolutionary algorithms. Evolutionary algorithms are metaheuristic optimization methods which copy principles from natural evolution. They use a population of solution candidates which they try to refine step by step in order to attain optimal values for predefined objective functions. The synthesis of an algorithm with our approach starts with an analysis step in which the wanted global behavior of the distributed system is specified. From this specification, objective functions are derived which steer a Genetic Programming process where the solution candidates are distributed programs. The objective functions rate how close these programs approximate the goal behavior in multiple randomized network simulations. The evolutionary process step by step selects the most promising solution candidates and modifies and combines them with mutation and crossover operators. This way, a description of the global behavior of a distributed system is translated automatically to programs which, if executed locally on the nodes of the system, exhibit this behavior. In our work, we test six different ways for representing distributed programs, comprising adaptations and extensions of well-known Genetic Programming methods (SGP, eSGP, and LGP), one bio-inspired approach (Fraglets), and two new program representations called Rule-based Genetic Programming (RBGP, eRBGP) designed by us. We breed programs in these representations for three well-known example problems in distributed systems: election algorithms, the distributed mutual exclusion at a critical section, and the distributed computation of the greatest common divisor of a set of numbers. Synthesizing distributed programs the evolutionary way does not necessarily lead to the envisaged results. In a detailed analysis, we discuss the problematic features which make this form of Genetic Programming particularly hard. The two Rule-based Genetic Programming approaches have been developed especially in order to mitigate these difficulties. In our experiments, at least one of them (eRBGP) turned out to be a very efficient approach and in most cases, was superior to the other representations.

Instant Storyboarding

This thesis aims at empowering software customers with a tool to build software tests them selves, based on a gradual refinement of natural language scenarios into executable visual test models. The process is divided in five steps: 1. First, a natural language parser is used to extract a graph of grammatical relations from the textual scenario descriptions. 2. The resulting graph is transformed into an informal story pattern by interpreting structurization rules based on Fujaba Story Diagrams. 3. While the informal story pattern can already be used by humans the diagram still lacks technical details, especially type information. To add them, a recommender based framework uses web sites and other resources to generate formalization rules. 4. As a preparation for the code generation the classes derived for formal story patterns are aligned across all story steps, substituting a class diagram. 5. Finally, a headless version of Fujaba is used to generate an executable JUnit test. The graph transformations used in the browser application are specified in a textual domain specific language and visualized as story pattern. Last but not least, only the heavyweight parsing (step 1) and code generation (step 5) are executed on the server side. All graph transformation steps (2, 3 and 4) are executed in the browser by an interpreter written in JavaScript/GWT. This result paves the way for online collaboration between global teams of software customers, IT business analysts and software developers.