An obstacle to the wide spread use of additive manufacturing (AM) is the difficulty in estimating the effects of process parameters on the mechanical properties of the manufactured part. The complex relationship between the geometry, parameters and mechanical properties makes it impractical to derive an analytical relationship and calls for the use of a numerical model. An approach to formulate a numerical model in developed in this thesis. The AM technique focused in this thesis is fused filament fabrication (FFF). A numerical model is developed by recreating FFF build process in a simulation environment. Machine instructions generated by a slicer to build a part is used to create a numerical model. The model acts as a basis to determine the effects of process parameters on the stiffness and the strength of a part. Determining the stiffness of the part is done by calculating the response of the model to a uniformly distributed load. The strength of the part depends on it's thermal history. The developed numerical model serves as a basis to implement models describing the relation between thermal history and strength. The developed model is suited to optimize FFF parameters as it encompass effects of all FFF parameters. A genetic algorithm is used to optimize the FFF parameters for minimum weight with a minimum stiffness constraint. / Ett hinder för att additiv tillverkning (AT), eller ”3D-printing”, ska få ett bredare genomslag är svårigheten att uppskatta effekterna av processparametrar på den tillverkade produktens mekaniska prestanda. Det komplexa förhållandet mellan geometri och processparametrar gör det opraktiskt och komplicerat att härleda analytiska uttryck för att förutsäga de mekaniska egenskaperna. Alternativet är att istället använda numeriska modeller. Huvudsyftet med denna avhandling har därför varit att utveckla en numerisk modell som kan användas för att förutsäga de mekaniska egenskaperna för detaljer tillverkade genom AT. AT-tekniken som avses är inriktad på Fused Filament Fabrication (FFF). En numerisk modell har utvecklats genom att återskapa FFF-byggprocessen i en simuleringsmiljö. Instruktioner (skriven i GCode) som används för att bygga en detalj genom FFF har här översatts till en numerisk FE-modell. Modellen används sen för att bestämma effekterna av processparametrar på styvheten och styrkan hos den tillverkade detaljen. I detta arbete har strukturstyvheten hos olika detaljer beräknats genom att utvärdera modellens svar för jämnt fördelade belastningsfall. Styrkan, vilket är starkt beroende på den tillverkade detaljens termiska historia, har inte utvärderats. Den utvecklade numeriska modellen kan dock fungera som underlag för implementering av modeller som beskriver relationen mellan termisk historia och styrka. Den utvecklade modellen är anpassad för optimering av FFF-parametrar då den omfattar effekterna av alla FFF-parametrar. En genetisk algoritm har använts i detta arbete för att optimera parametrarna med avseende på vikt för en given strukturstyvhet.

<p dir="ltr">Semantic pairs, which consist of related entities or concepts, serve as the foundation for comprehending the meaning of language in both written and spoken forms. These pairs enable to grasp the nuances of relationships between words, phrases, or ideas, forming the basis for more advanced language tasks like entity recognition, sentiment analysis, machine translation, and question answering. They allow to infer causality, identify hierarchies, and connect ideas within a text, ultimately enhancing the depth and accuracy of automated language processing.</p><p dir="ltr">Nevertheless, the task of extracting semantic pairs from sentences poses a significant challenge, necessitating the relevance of syntactic dependency patterns (SDPs). Thankfully, semantic relationships exhibit adherence to distinct SDPs when connecting pairs of entities. Recognizing this fact underscores the critical importance of extracting these SDPs, particularly for specific semantic relationships like hyponym-hypernym, meronym-holonym, and cause-effect associations. The automated extraction of such SDPs carries substantial advantages for various downstream applications, including entity extraction, ontology development, and question answering. Unfortunately, this pivotal facet of pattern extraction has remained relatively overlooked by researchers in the domains of natural language processing (NLP) and information retrieval.</p><p dir="ltr">To address this gap, I introduce an attention-based supervised deep learning model, ASPER. ASPER is designed to extract SDPs that denote semantic relationships between entities within a given sentential context. I rigorously evaluate the performance of ASPER across three distinct semantic relations: hyponym-hypernym, cause-effect, and meronym-holonym, utilizing six datasets. My experimental findings demonstrate ASPER's ability to automatically identify an array of SDPs that mirror the presence of these semantic relationships within sentences, outperforming existing pattern extraction methods by a substantial margin.</p><p dir="ltr">Second, I want to use the SDPs to extract semantic pairs from sentences. I choose to extract cause-effect entities from medical literature. This task is instrumental in compiling various causality relationships, such as those between diseases and symptoms, medications and side effects, and genes and diseases. Existing solutions excel in sentences where cause and effect phrases are straightforward, such as named entities, single-word nouns, or short noun phrases. However, in the complex landscape of medical literature, cause and effect expressions often extend over several words, stumping existing methods, resulting in incomplete extractions that provide low-quality, non-informative, and at times, conflicting information. To overcome this challenge, I introduce an innovative unsupervised method for extracting cause and effect phrases, PatternCausality tailored explicitly for medical literature. PatternCausality employs a set of cause-effect dependency patterns as templates to identify the key terms within cause and effect phrases. It then utilizes a novel phrase extraction technique to produce comprehensive and meaningful cause and effect expressions from sentences. Experiments conducted on a dataset constructed from PubMed articles reveal that PatternCausality significantly outperforms existing methods, achieving a remarkable order of magnitude improvement in the F-score metric over the best-performing alternatives. I also develop various PatternCausality variants that utilize diverse phrase extraction methods, all of which surpass existing approaches. PatternCausality and its variants exhibit notable performance improvements in extracting cause and effect entities in a domain-neutral benchmark dataset, wherein cause and effect entities are confined to single-word nouns or noun phrases of one to two words.</p><p dir="ltr">Nevertheless, PatternCausality operates within an unsupervised framework and relies heavily on SDPs, motivating me to explore the development of a supervised approach. Although SDPs play a pivotal role in semantic relation extraction, pattern-based methodologies remain unsupervised, and the multitude of potential patterns within a language can be overwhelming. Furthermore, patterns do not consistently capture the broader context of a sentence, leading to the extraction of false-positive semantic pairs. As an illustration, consider the hyponym-hypernym pattern <i>the w of u</i> which can correctly extract semantic pairs for a sentence like <i>the village of Aasu</i> but fails to do so for the phrase <i>the moment of impact</i>. The root cause of this limitation lies in the pattern's inability to capture the nuanced meaning of words and phrases in a sentence and their contextual significance. These observations have spurred my exploration of a third model, DepBERT which constitutes a dependency-aware supervised transformer model. DepBERT's primary contribution lies in introducing the underlying dependency structure of sentences to a language model with the aim of enhancing token classification performance. To achieve this, I must first reframe the task of semantic pair extraction as a token classification problem. The DepBERT model can harness both the tree-like structure of dependency patterns and the masked language architecture of transformers, marking a significant milestone, as most large language models (LLMs) predominantly focus on semantics and word co-occurrence while neglecting the crucial role of dependency architecture.</p><p dir="ltr">In summary, my overarching contributions in this thesis are threefold. First, I validate the significance of the dependency architecture within various components of sentences and publish SDPs that incorporate these dependency relationships. Subsequently, I employ these SDPs in a practical medical domain to extract vital cause-effect pairs from sentences. Finally, my third contribution distinguishes this thesis by integrating dependency relations into a deep learning model, enhancing the understanding of language and the extraction of valuable semantic associations.</p>

L’objectif de cette thèse est de proposer un Alphabet Structural (AS) permettant une caractérisation fine et précise des structures tridimensionnelles (3D) des protéines, à l’aide des chaînes de Markov cachées (HMM) qui permettent de prendre en compte la logique issue de l’enchaînement des fragments structuraux en intégrant l’augmentation des conformations 3D des structures protéiques désormais disponibles dans la banque de données de la Protein Data Bank (PDB). Nous proposons dans cette thèse un nouvel alphabet, améliorant l’alphabet structural HMM-SA27,appelé SAFlex (Structural Alphabet Flexibility), dans le but de prendre en compte l’incertitude des données (données manquantes dans les fichiers PDB) et la redondance des structures protéiques. Le nouvel alphabet structural SAFlex obtenu propose donc un nouveau modèle d’encodage rigoureux et robuste. Cet encodage permet de prendre en compte l’incertitude des données en proposant trois options d’encodages : le Maximum a posteriori (MAP), la distribution marginale a posteriori (POST)et le nombre effectif de lettres à chaque position donnée (NEFF). SAFlex fournit également un encodage consensus à partir de différentes réplications (chaînes multiples, monomères et homomères) d’une même protéine. Il permet ainsi la détection de la variabilité structurale entre celles-ci. Les avancées méthodologiques ainsi que l’obtention de l’alphabet SAFlex constituent les contributions principales de ce travail de thèse. Nous présentons aussi le nouveau parser de la PDB (SAFlex-PDB) et nous démontrons que notre parser a un intérêt aussi bien sur le plan qualitatif (détection de diverses erreurs)que quantitatif (rapidité et parallélisation) en le comparant avec deux autres parsers très connus dans le domaine (Biopython et BioJava). Nous proposons également à la communauté scientifique un site web mettant en ligne ce nouvel alphabet structural SAFlex. Ce site web représente la contribution concrète de cette thèse alors que le parser SAFlex-PDB représente une contribution importante pour le fonctionnement du site web proposé. Cette caractérisation précise des conformations 3D et la prise en compte de la redondance des informations 3D disponibles, fournies par SAFlex, a en effet un impact très important pour la modélisation de la conformation et de la variabilité des structures 3D, des boucles protéiques et des régions d’interface avec différents partenaires, impliqués dans la fonction des protéines / The purpose of this PhD is to provide a Structural Alphabet (SA) for more accurate characterization of protein three-dimensional (3D) structures as well as integrating the increasing protein 3D structure information currently available in the Protein Data Bank (PDB). The SA also takes into consideration the logic behind the structural fragments sequence by using the hidden Markov Model (HMM). In this PhD, we describe a new structural alphabet, improving the existing HMM-SA27 structural alphabet, called SAFlex (Structural Alphabet Flexibility), in order to take into account the uncertainty of data (missing data in PDB files) and the redundancy of protein structures. The new SAFlex structural alphabet obtained therefore offers a new, rigorous and robust encoding model. This encoding takes into account the encoding uncertainty by providing three encoding options: the maximum a posteriori (MAP), the marginal posterior distribution (POST), and the effective number of letters at each given position (NEFF). SAFlex also provides and builds a consensus encoding from different replicates (multiple chains, monomers and several homomers) of a single protein. It thus allows the detection of structural variability between different chains. The methodological advances and the achievement of the SAFlex alphabet are the main contributions of this PhD. We also present the new PDB parser(SAFlex-PDB) and we demonstrate that our parser is therefore interesting both qualitative (detection of various errors) and quantitative terms (program optimization and parallelization) by comparing it with two other parsers well-known in the area of Bioinformatics (Biopython and BioJava). The SAFlex structural alphabet is being made available to the scientific community by providing a website. The SAFlex web server represents the concrete contribution of this PhD while the SAFlex-PDB parser represents an important contribution to the proper function of the proposed website. Here, we describe the functions and the interfaces of the SAFlex web server. The SAFlex can be used in various fashions for a protein tertiary structure of a given PDB format file; it can be used for encoding the 3D structure, identifying and predicting missing data. Hence, it is the only alphabet able to encode and predict the missing data in a 3D protein structure to date. Finally, these improvements; are promising to explore increasing protein redundancy data and obtain useful quantification of their flexibility

Thesis submitted for the joint institutional requirements for the double-badged degree of Doctor of Philosophy and Docteur de l'Université de Provence, Spécialité : Informatique. / Thesis (PhD)--Macquarie University, Division of Information and Communication Sciences, Department of Computing, 2008. / Includes bibliography (p. 229-240) and index. / Introduction -- Background -- A model-theoretic framework for PG -- Loose constraint-based parsing -- A computational model for gradience -- Conclusion. / The grammaticality of a sentence has conventionally been treated in a binary way: either a sentence is grammatical or not. A growing body of work, however, focuses on studying intermediate levels of acceptability, sometimes referred to as gradience. To date, the bulk of this work has concerned itself with the exploration of human assessments of syntactic gradience. This dissertation explores the possibility to build a robust computational model that accords with these human judgements. -- We suggest that the concepts of Intersective Gradience and Subsective Gradience introduced by Aarts for modelling graded judgements be extended to cover deviant language. Under such a new model, the problem then raised by gradience is to classify an utterance as a member of a specific category according to its syntactic characteristics. More specifically, we extend Intersective Gradience (IG) so that it is concerned with choosing the most suitable syntactic structure for an utterance among a set of candidates, while Subsective Gradience (SG) is extended to be concerned with calculating to what extent the chosen syntactic structure is typical from the category at stake. IG is addressed in relying on a criterion of optimality, while SG is addressed in rating an utterance according to its grammatical acceptability. As for the required syntactic characteristics, which serve as features for classifying an utterance, our investigation of different frameworks for representing the syntax of natural language shows that they can easily be represented in Model-Theoretic Syntax; we choose to use Property Grammars (PG), which offers to model the characterisation of an utterance. We present here a fully automated solution for modelling syntactic gradience, which characterises any well formed or ill formed input sentence, generates an optimal parse for it, then rates the utterance according to its grammatical acceptability. -- Through the development of such a new model of gradience, the main contribution of this work is three-fold. -- First, we specify a model-theoretic logical framework for PG, which bridges the gap observed in the existing formalisation regarding the constraint satisfaction and constraint relaxation mechanisms, and how they relate to the projection of a category during the parsing process. This new framework introduces the notion of loose satisfaction, along with a formulation in first-order logic, which enables reasoning about the characterisation of an utterance. -- Second, we present our implementation of Loose Satisfaction Chart Parsing (LSCP), a dynamic programming approach based on the above mechanisms, which is proven to always find the full parse of optimal merit. Although it shows a high theoretical worst time complexity, it performs sufficiently well with the help of heuristics to let us experiment with our model of gradience. -- And third, after postulating that human acceptability judgements can be predicted by factors derivable from LSCP, we present a numeric model for rating an utterance according to its syntactic gradience. We measure a good correlation with grammatical acceptability by human judgements. Moreover, the model turns out to outperform an existing one discussed in the literature, which was experimented with parses generated manually. / Mode of access: World Wide Web. / xxviii, 283 p. ill

The work is focused on the area of the proteins and their domains. It also briefly describes gathering methods of the protein´s structure at the various levels of the hierarchy. This is followed by examining of existing tools for protein´s domains prediction and databases consisting of domain´s information. In the next part of the work selected representatives of prediction methods are introduced.  These methods work with the information about the internal structure of the molecule or the amino acid sequence. The appropriate chapter outlines applied procedure of domains´ boundaries prediction. The prediction is derived from the primary structure of the protein, using a neural network  The implemented procedure and its possibility of further development in the related thesis are introduced at the conclusion of this work.

This thesis introduces syntax-directed translation based on deep pushdown automata. Necessary theoretical models are introduced in the theoretical part. The most important model, introduced in this thesis, is a deep pushdown transducer. The transducer should be used in syntax analysis, significant part of translation. Practical part consists of an implementation of simple-language interpret based on these models.

This master's thesis deals with implementation of ISO C99 language interpreter. The goal of this thesis is to provide support of education in C language programming and fast algorithm prototyping. It enables students to create own C programs and to experiment with language constructions without compiling. User interface includes editor and simple debugger. The interpreter is implemented in a novel grammar development environment written in Java language - ANTLRWorks which includes ANTLR language tool.

Cette thèse par article comprend quatre articles qui contribuent au domaine de l'apprentissage profond, en particulier à l'accélération de l’apprentissage par le biais de réseaux à faible précision et à l'application de réseaux de neurones profonds au traitement du langage naturel. Dans le premier article, nous étudions un schéma d’entraînement de réseau de neurones qui élimine la plupart des multiplications en virgule flottante. Cette approche consiste à binariser ou à ternariser les poids dans la propagation en avant et à quantifier les états cachés dans la propagation arrière, ce qui convertit les multiplications en changements de signe et en décalages binaires. Les résultats expérimentaux sur des jeux de données de petite à moyenne taille montrent que cette approche produit des performances encore meilleures que l’approche standard de descente de gradient stochastique, ouvrant la voie à un entraînement des réseaux de neurones rapide et efficace au niveau du matériel. Dans le deuxième article, nous avons proposé un mécanisme structuré d’auto-attention d’enchâssement de phrases qui extrait des représentations interprétables de phrases sous forme matricielle. Nous démontrons des améliorations dans 3 tâches différentes: le profilage de l'auteur, la classification des sentiments et l'implication textuelle. Les résultats expérimentaux montrent que notre modèle génère un gain en performance significatif par rapport aux autres méthodes d’enchâssement de phrases dans les 3 tâches. Dans le troisième article, nous proposons un modèle hiérarchique avec graphe de calcul dynamique, pour les données séquentielles, qui apprend à construire un arbre lors de la lecture de la séquence. Le modèle apprend à créer des connexions de saut adaptatives, ce qui facilitent l'apprentissage des dépendances à long terme en construisant des cellules récurrentes de manière récursive. L’entraînement du réseau peut être fait soit par entraînement supervisée en donnant des structures d’arbres dorés, soit par apprentissage par renforcement. Nous proposons des expériences préliminaires dans 3 tâches différentes: une nouvelle tâche d'évaluation de l'expression mathématique (MEE), une tâche bien connue de la logique propositionnelle et des tâches de modélisation du langage. Les résultats expérimentaux montrent le potentiel de l'approche proposée. Dans le quatrième article, nous proposons une nouvelle méthode d’analyse par circonscription utilisant les réseaux de neurones. Le modèle prédit la structure de l'arbre d'analyse en prédisant un scalaire à valeur réelle, soit la distance syntaxique, pour chaque position de division dans la phrase d'entrée. L'ordre des valeurs relatives de ces distances syntaxiques détermine ensuite la structure de l'arbre d'analyse en spécifiant l'ordre dans lequel les points de division seront sélectionnés, en partitionnant l'entrée de manière récursive et descendante. L’approche proposée obtient une performance compétitive sur le jeu de données Penn Treebank et réalise l’état de l’art sur le jeu de données Chinese Treebank. / This thesis by article consists of four articles which contribute to the field of deep learning, specifically in the acceleration of training through low-precision networks, and the application of deep neural networks on natural language processing. In the first article, we investigate a neural network training scheme that eliminates most of the floating-point multiplications. This approach consists of binarizing or ternarizing the weights in the forward propagation and quantizing the hidden states in the backward propagation, which converts multiplications to sign changes and binary shifts. Experimental results on datasets from small to medium size show that this approach result in even better performance than standard stochastic gradient descent training, paving the way to fast, hardware-friendly training of neural networks. In the second article, we proposed a structured self-attentive sentence embedding that extracts interpretable sentence representations in matrix form. We demonstrate improvements on 3 different tasks: author profiling, sentiment classification and textual entailment. Experimental results show that our model yields a significant performance gain compared to other sentence embedding methods in all of the 3 tasks. In the third article, we propose a hierarchical model with dynamical computation graph for sequential data that learns to construct a tree while reading the sequence. The model learns to create adaptive skip-connections that ease the learning of long-term dependencies through constructing recurrent cells in a recursive manner. The training of the network can either be supervised training by giving golden tree structures, or through reinforcement learning. We provide preliminary experiments in 3 different tasks: a novel Math Expression Evaluation (MEE) task, a well-known propositional logic task, and language modelling tasks. Experimental results show the potential of the proposed approach. In the fourth article, we propose a novel constituency parsing method with neural networks. The model predicts the parse tree structure by predicting a real valued scalar, named syntactic distance, for each split position in the input sentence. The order of the relative values of these syntactic distances then determine the parse tree structure by specifying the order in which the split points will be selected, recursively partitioning the input, in a top-down fashion. Our proposed approach was demonstrated with competitive performance on Penn Treebank dataset, and the state-of-the-art performance on Chinese Treebank dataset.

This document deals with introduction focused on pragmatically oriented research at branch of theoretical computer science and with presentation of designed methods for chosen application topics. At this study the theoretical subject is represented by kind of generative system - multisequential grammar and application topics are chosen according to possibilities supported by multisequential grammars. In order to follow results published by Thompson (see [9]), Lindenmayer (see [26]), Mandelbrot (see [8]) and also studies published by Morneau (see [17]), which shows the relation between natural laws and human discipline - mathematics, we study the applications of multi-sequential grammars from two points of view: generative L-systems (which further includes applications of fractal geometry and biomathematics) and natural language processing (which further includes the design of proper abstract language). Some problems related to compiler construction are also mentioned.

Software components provide essential means to structure and organize software effectively. However, frequently, required component abstractions are not available in a programming language or system, or are not adequately combinable with each other. Invasive software composition (ISC) is a general approach to software composition that unifies component-like abstractions such as templates, aspects and macros. ISC is based on fragment composition, and composes programs and other software artifacts at the level of syntax trees. Therefore, a unifying fragment component model is related to the context-free grammar of a language to identify extension and variation points in syntax trees as well as valid component types. By doing so, fragment components can be composed by transformations at respective extension and variation points so that always valid composition results regarding the underlying context-free grammar are yielded. However, given a language’s context-free grammar, the composition result may still be incorrect. Context-sensitive constraints such as type constraints may be violated so that the program cannot be compiled and/or interpreted correctly. While a compiler can detect such errors after composition, it is difficult to relate them back to the original transformation step in the composition system, especially in the case of complex compositions with several hundreds of such steps. To tackle this problem, this thesis proposes well-formed ISC—an extension to ISC that uses reference attribute grammars (RAGs) to specify fragment component models and fragment contracts to guard compositions with context-sensitive constraints. Additionally, well-formed ISC provides composition strategies as a means to configure composition algorithms and handle interferences between composition steps. Developing ISC systems for complex languages such as programming languages is a complex undertaking. Composition-system developers need to supply or develop adequate language and parser specifications that can be processed by an ISC composition engine. Moreover, the specifications may need to be extended with rules for the intended composition abstractions. Current approaches to ISC require complete grammars to be able to compose fragments in the respective languages. Hence, the specifications need to be developed exhaustively before any component model can be supplied. To tackle this problem, this thesis introduces scalable ISC—a variant of ISC that uses island component models as a means to define component models for partially specified languages while still the whole language is supported. Additionally, a scalable workflow for agile composition-system development is proposed which supports a development of ISC systems in small increments using modular extensions. All theoretical concepts introduced in this thesis are implemented in the Skeletons and Application Templates framework SkAT. It supports “classic”, well-formed and scalable ISC by leveraging RAGs as its main specification and implementation language. Moreover, several composition systems based on SkAT are discussed, e.g., a well-formed composition system for Java and a C preprocessor-like macro language. In turn, those composition systems are used as composers in several example applications such as a library of parallel algorithmic skeletons.