Le traitement automatique des langues fondé sur les données a récemment assimilé de nombreuses techniques et perspectives héritées du domaine de la reconnaissance de parole. Parmi celles-ci, les méthodes qui utilisent le mot comme unité de traitement sont difficilement transposables aux systèmes d'écriture sans séparateur orthographique, et ne sont donc pas multilingues.<br />Le présent travail promeut l'utilisation de méthodes travaillant au niveau du signal de l'écrit: le caractère, unité immédiatement accessible dans toute langue informatisée, permet de se passer de segmentation en mots, étape actuellement incontournable pour des langues comme le chinois ou le japonais.<br /><br />Dans un premier temps, nous transposons et appliquons en caractères une méthode bien établie d'évaluation objective de la traduction automatique, BLEU.<br />Les résultats encourageants nous permettent dans un deuxième temps d'aborder d'autres tâches de traitement des données linguistiques. Tout d'abord, le filtrage de la grammaticalité; ensuite, la caractérisation de la similarité et de l'homogénéité des ressources linguistiques. Dans toutes ces tâches, le traitement en caractères obtient des résultats acceptables, et comparables à ceux obtenus en mots.<br />Dans un troisième temps, nous abordons des tâches de production de données linguistiques: le calcul analogique sur les chaines de caractères permet la production de paraphrases aussi bien que la traduction automatique.<br />Ce travail montre qu'on peut construire un système complet de traduction automatique ne nécessitant pas de segmentation, a fortiori pour traiter des langues sans séparateur orthographique.

For many challenging problems where the mathematical description is not explicitly defined, artificial intelligence methods appear to be much more robust compared to traditional algorithms. Such methods share the common property of learning from examples in order to “explore” the problem to solve. Then, they generalize these examples to new and unseen input signals. The reservoir computing paradigm is a bio-inspired approach drawn from the theory of artificial Recurrent Neural Networks (RNNs) to process time-dependent data. This machine learning method was proposed independently by several research groups in the early 2000s. It has enabled a breakthrough in analog information processing, with several experiments demonstrating state-of-the-art performance for a wide range of hard nonlinear tasks. These tasks include for instance dynamic pattern classification, grammar modeling, speechrecognition, nonlinear channel equalization, detection of epileptic seizures, robot control, timeseries prediction, brain-machine interfacing, power system monitoring, financial forecasting, or handwriting recognition. A Reservoir Computer (RC) is composed of three different layers. There is first the neural network itself, called “reservoir”, which consists of a large number of internal variables (i.e. reservoir states) all interconnected together to exchange information. The internal dynamics of such a system, driven by a function of the inputs and the former reservoir states, is thus extremely rich. Through an input layer, a time-dependent input signal is applied to all the internal variables to disturb the neural network dynamics. Then, in the output layer, all these reservoir states are processed, often by taking a linear combination thereof at each time-step, to compute the output signal. Let us note that the presence of a non-linearity somewhere in the system is essential to reach high performance computing on nonlinear tasks. The principal novelty of the reservoir computing paradigm was to propose an RNN where most of the connection weights are generated randomly, except for the weights adjusted to compute the output signal from a linear combination of the reservoir states. In addition, some global parameters can be tuned to get the best performance, depending on the reservoir architecture and on the task. This simple and easy process considerably decreases the training complexity compared to traditional RNNs, for which all the weights needed to be optimized. RC algorithms can be programmed using modern traditional processors. But these electronic processors are better suited to digital processing for which a lot of transistors continuously need to be switched on and off, leading to higher power consumption. As we can intuitively understand, processors with hardware directly dedicated to RC operations – in otherwords analog bio-inspired processors – could be much more efficient regarding both speed and power consumption. Based on the same idea of high speed and low power consumption, the last few decades have seen an increasing use of coherent optics in the transport of information thanks to its high bandwidth and high power efficiency advantages. In order to address the future challenge of high performance, high speed, and power efficient nontrivial computing, it is thus natural to turn towards optical implementations of RCs using coherent light. Over the last few years, several physical implementations of RCs using optics and (opto)electronics have been successfully demonstrated. In the present PhD thesis, the reservoirs are based on a large coherently driven linear passive fiber cavity. The internal states are encoded by time-multiplexing in the cavity. Each reservoir state is therefore processed sequentially. This reservoir architecture exhibits many qualities that were either absent or not simultaneously present in previous works: we can perform analog optical signal processing; the easy tunability of each key parameter achieves the best operating point for each task; the system is able to reach a strikingly weak noise floor thanks to the absence of active elements in the reservoir itself; a richer dynamics is provided by operating in coherent light, as the reservoir states are encoded in both the amplitude and the phase of the electromagnetic field; high power efficiency is obtained as a result of the passive nature and simplicity of the setup. However, it is important to note that at this stage we have only obtained low optical power consumption for the reservoir itself. We have not tried to minimize the overall power consumption, including all control electronics. The first experiment reported in chapter 4 uses a quadratic non-linearity on each reservoir state in the output layer. This non-linearity is provided by a readout photodiode since it produces a current proportional to the intensity of the light. On a number of benchmark tasks widely used in the reservoir computing community, the error rates demonstrated with this RC architecture – both in simulation and experimentally – are, to our knowledge, the lowest obtained so far. Furthermore, the analytic model describing our experiment is also of interest, asit constitutes a very simple high performance RC algorithm. The setup reported in chapter 4 requires offline digital post-processing to compute its output signal by summing the weighted reservoir states at each time-step. In chapter 5, we numerically study a realistic model of an optoelectronic “analog readout layer” adapted on the setup presented in chapter 4. This readout layer is based on an RLC low-pass filter acting as an integrator over the weighted reservoir states to autonomously generate the RC output signal. On three benchmark tasks, we obtained very good simulation results that need to be confirmed experimentally in the future. These promising simulation results pave the way for standalone high performance physical reservoir computers.The RC architecture presented in chapter 5 is an autonomous optoelectronic implementation able to electrically generate its output signal. In order to contribute to the challenge of all-optical computing, chapter 6 highlights the possibility of processing information autonomously and optically using an RC based on two coherently driven passive linear cavities. The first one constitutes the reservoir itself and pumps the second one, which acts as an optical integrator onthe weighted reservoir states to optically generate the RC output signal after sampling. A sine non-linearity is implemented on the input signal, whereas both the reservoir and the readout layer are kept linear. Let us note that, because the non-linearity in this system is provided by a Mach-Zehnder modulator on the input signal, the input signal of this RC configuration needs to be an electrical signal. On the contrary, the RC implementation presented in chapter 5 processes optical input signals, but its output is electrical. We obtained very good simulation results on a single task and promising experimental results on two tasks. At the end of this chapter, interesting perspectives are pointed out to improve the performance of this challenging experiment. This system constitutes the first autonomous photonic RC able to optically generate its output signal. / Doctorat en Sciences de l'ingénieur et technologie / info:eu-repo/semantics/nonPublished