Letteratura scientifica selezionata sul tema "Author and Document Representation Learning"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Consulta la lista di attuali articoli, libri, tesi, atti di convegni e altre fonti scientifiche attinenti al tema "Author and Document Representation Learning".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Articoli di riviste sul tema "Author and Document Representation Learning":
1
Para, Upendar, e M. S. Patel. "A New Term Representation Method for Gender and Age Prediction". International Journal on Recent and Innovation Trends in Computing and Communication 11, n. 5s (17 maggio 2023): 90–104. http://dx.doi.org/10.17762/ijritcc.v11i5s.6633.
Abstract (sommario):
Author Profiling is a kind of text classification method that is used for detecting the personality profiles such as age, gender, educational background, place of origin, personality traits, native language, etc., of authors by processing their written texts. Several applications like forensic analysis, security and marking are used the techniques of author profiling for finding the basic details of authors. The main problem in the domain of author profiling is preparation of suitable dataset for predicting the characteristics of authors. PAN is one organization conducting competitions on various types of shared tasks. In 2013, PAN organizers presented the task of author profiling in their series of competitions and continued this task in further years. They arranged different kinds of datasets in different varieties of languages. From 2013 onwards several researchers proposed solutions for author profiling to predict different personality features of authors by utilizing the datasets provided in PAN competitions. Researchers used different kinds of features like character based, lexical or word based, structural features, syntactic, content based, style based features for distinguishing the author’s writing styles in their texts. Most of the researchers observed that the content based features like words or phrases those are used in the text are most useful for detecting the personality features of authors. In this work, the experiment conducted with the content based features like most important words or terms for predicting age group and gender from the PAN competition datasets. Two datasets such as PAN 2014 and 2016 author profiling datasets are used in this experiment. The documents of dataset are converted in to a vector representation which is a suitable format for giving training to machine learning algorithms. The term representation in a document vector plays a crucial role to improve the performance of gender and age group prediction.The Term Weight Measures (TWMs) are such techniques used for this purpose to represent the significance of a term value in document vector representation. In this work, we developed a new TWM for representing the term value in document vector representation. The proposed TWM’s efficiency is compared with the efficiency of other existing TWMs. Two Machine Learning (ML) algorithms like SVM (Support Vector Machine) and RF (Random Forest) are considered in this experiment for estimating the accuracy of proposed approach. We recognized that the proposed TWM accomplished best accuracies for gender and age prediction in two PAN Datasets.
2
Ma, Yingying, Youlong Wu e Chengqiang Lu. "A Graph-Based Author Name Disambiguation Method and Analysis via Information Theory". Entropy 22, n. 4 (7 aprile 2020): 416. http://dx.doi.org/10.3390/e22040416.
Abstract (sommario):
Name ambiguity, due to the fact that many people share an identical name, often deteriorates the performance of information integration, document retrieval and web search. In academic data analysis, author name ambiguity usually decreases the analysis performance. To solve this problem, an author name disambiguation task is designed to divide documents related to an author name reference into several parts and each part is associated with a real-life person. Existing methods usually use either attributes of documents or relationships between documents and co-authors. However, methods of feature extraction using attributes cause inflexibility of models while solutions based on relationship graph network ignore the information contained in the features. In this paper, we propose a novel name disambiguation model based on representation learning which incorporates attributes and relationships. Experiments on a public real dataset demonstrate the effectiveness of our model and experimental results demonstrate that our solution is superior to several state-of-the-art graph-based methods. We also increase the interpretability of our method through information theory and show that the analysis could be helpful for model selection and training progress.
3
Stoean, Catalin, e Daniel Lichtblau. "Author Identification Using Chaos Game Representation and Deep Learning". Mathematics 8, n. 11 (2 novembre 2020): 1933. http://dx.doi.org/10.3390/math8111933.
Abstract (sommario):
An author unconsciously encodes in the written text a certain style that is often difficult to recognize. Still, there are many computational means developed for this purpose that take into account various features, from lexical and character-based attributes to syntactic or semantic ones. We propose an approach that starts from the character level and uses chaos game representation to illustrate documents like images which are subsequently classified by a deep learning algorithm. The experiments are made on three data sets and the outputs are comparable to the results from the literature. The study also verifies the suitability of the method for small data sets and whether image augmentation can improve the classification efficiency.
4
Pooja, Km, Samrat Mondal e Joydeep Chandra. "Exploiting Higher Order Multi-dimensional Relationships with Self-attention for Author Name Disambiguation". ACM Transactions on Knowledge Discovery from Data 16, n. 5 (31 ottobre 2022): 1–23. http://dx.doi.org/10.1145/3502730.
Abstract (sommario):
Name ambiguity is a prevalent problem in scholarly publications due to the unprecedented growth of digital libraries and number of researchers. An author is identified by their name in the absence of a unique identifier. The documents of an author are mistakenly assigned due to underlying ambiguity, which may lead to an improper assessment of the author. Various efforts have been made in the literature to solve the name disambiguation problem with supervised and unsupervised approaches. The unsupervised approaches for author name disambiguation are preferred due to the availability of a large amount of unlabeled data. Bibliographic data contain heterogeneous features, thus recently, representation learning-based techniques have been used in literature to embed heterogeneous features in common space. Documents of a scholar are connected by multiple relations. Recently, research has shifted from a single homogeneous relation to multi-dimensional (heterogeneous) relations for the latent representation of document. Connections in graphs are sparse, and higher order links between documents give an additional clue. Therefore, we have used multiple neighborhoods in different relation types in heterogeneous graph for representation of documents. However, different order neighborhood in each relation type has different importance which we have empirically validated also. Therefore, to properly utilize the different neighborhoods in relation type and importance of each relation type in the heterogeneous graph, we propose attention-based multi-dimensional multi-hop neighborhood-based graph convolution network for embedding that uses the two levels of an attention, namely, (i) relation level and (ii) neighborhood level, in each relation. A significant improvement over existing state-of-the-art methods in terms of various evaluation matrices has been obtained by the proposed approach.
5
Kavuri, Karunakar, e M. Kavitha. "A Word Embeddings based Approach for Author Profiling: Gender and Age Prediction". International Journal on Recent and Innovation Trends in Computing and Communication 11, n. 7s (13 luglio 2023): 239–50. http://dx.doi.org/10.17762/ijritcc.v11i7s.6996.
Abstract (sommario):
Author Profiling (AP) is a method of identifying the demographic profiles such as age, gender, location, native language and personality traits of an author by processing their written texts. The AP techniques are used in multiple applications such as literary research, marketing, forensics and security. The researchers identified various differences in the authors writing styles by analysing various datasets. The differences in writing styles are represented as stylistic features. The researchers extracted several style based features like structural, content, word, character, syntactic, readability and semantic features to recognize the profiles of the authors. Traditionally, the researchers extracted various feature combinations for differentiating the profiles of authors. Several existing works are used Machine Learning (ML) methods for predicting the author characteristics of a new author. The existing works achieved good accuracies for predicting the author characteristics by considering the both stylistic features and ML algorithms combination. Recently, in advent of Deep Learning (DL) techniques the researchers are proposed approaches to author profiling by using these techniques. Few researchers identified that the deep learning techniques performance is good for author profiles prediction than the results of style based features. In this work, a word embeddings based approach is proposed for gender and age prediction. In this approach, the experiment conducted with different word embedding models such as Word2Vec, GloVe, FastText and BERT for generating word vectors for words. The documents are converted as vectors by using the document representation technique which uses the word embeddings of words. The document vectors are transferred to three different ML algorithms such as Extreme Gradient Boosting (XGBoost), Random Forest (RF) and Logistic Regression (LR) for generating the trained model. This model is used for predicating the accuracy of age and gender prediction. The XGBoost classifier with word embeddings of BERT achieved good accuracies for age and gender prediction than other word embeddings and ML algorithms. The experiment implemented on PAN 2014 competition Reviews dataset for age and gender prediction. The proposed approach attained best accuracies for predicting age and gender than the performances of various existing approaches proposed for AP.
6
Buffone, Brittany, Ilena Djuana, Katherine Yang, Kyle J. Wilby, Maguy S. El Hajj e Kerry Wilbur. "Diversity in health professional education scholarship: a document analysis of international author representation in leading journals". BMJ Open 10, n. 11 (novembre 2020): e043970. http://dx.doi.org/10.1136/bmjopen-2020-043970.
Abstract (sommario):
ObjectivesThe global distribution of health professionals and associated training programmes is wide but prior study has demonstrated reported scholarship of teaching and learning arises from predominantly Western perspectives.DesignWe conducted a document analysis to examine authorship of recent publications to explore current international representation.Data sourcesThe table of contents of seven high-impact English-language health professional education journals between 2008 and 2018 was extracted from Embase.Eligibility criteriaThe journals were selected according to highest aggregate ranking across specific scientific impact indices and stating health professional education in scope; only original research and review articles from these publications were included for analysis.Data extraction and synthesisThe table of contents was extracted and eligible publications screened by independent reviewers who further characterised the geographic affiliations of the publishing research teams and study settings (if applicable).ResultsA total 12 018 titles were screened and 7793 (64.8%) articles included. Most were collaborations (7048, 90.4%) conducted by authors from single geographic regions (5851, 86%). Single-region teams were most often formed from countries in North America (56%), Northern Europe (14%) or Western Europe (10%). Overall lead authorship from Asian, African or South American regions was less than 15%, 5% and 1%, respectively. Geographic representation varied somewhat by journal, but not across time.ConclusionsDiversity in health professional education scholarship, as marked by nation of authors’ professional affiliations, remains low. Under-representation of published research outside Global North regions limits dissemination of novel ideas resulting in unidirectional flow of experiences and a concentrated worldview of teaching and learning.
7
Popova, Y. B., e A. V. Goloburda. "ALGORITHMIC AND PROGRAM IMPLEMENTATION OF THE PLAGIARISM DEFINITION IN LEARNING MANAGEMENT SYSTEMS". «System analysis and applied information science», n. 1 (12 giugno 2018): 71–78. http://dx.doi.org/10.21122/2309-4923-2018-1-71-78.
Abstract (sommario):
The main advantage of using information technologies in education, which consists in speeding up and simplifying of information exchange, is also its drawback, because it raises the problem of plagiarism. The purpose of this paper is to develop testing text software for uniqueness in learning management systems. To achieve this goal, it is necessary to solve a range of problems related to the choice of a method for determining plagiarism, its algorithmization and software implementation. The work deals with the methods of shingles, super-shingles, signature methods, vector models of text representation, as well as cluster analysis of text information. The authors suggest a modification of the vector model to improve the accuracy of determining similar documents by creating an N-list of each document separately. As a result, a pairwise comparison of the documents and the formation of the image of one document relative to the N-list of the other will occur. Thus, in the i-th row of the similarity matrix, the coefficients of similarity of all the documents considered relative to the i-th document will be recorded. The proposed modification will also speed up the calculation process, since there is no need to search for common terms for all documents. To analyze a large number of student’s works in order to test them for plagiarism, the authors propose using a cluster approach. Its application showed that the time for determining duplicates for one document and for all documents included in the sample is the same. For the same time it is possible to get all the options for the same works of students. Thus, the use of cluster analysis of text information in determining plagiarism significantly saves both the teacher’s time and computing resources. The software implementation of the proposed algorithms is implemented as a web service in the Java language.
8
Popova, Oleksandra. "ECONOMIC AND LEGAL DISCOURSE: PARADIGM OF CHANGES IN THE XXI CENTURY (ON THE MATERIAL OF CHINESE, ENGLISH AND UKRAINIAN LANGUAGES)". Naukovy Visnyk of South Ukrainian National Pedagogical University named after K. D. Ushynsky: Linguistic Sciences 2022, n. 34 (luglio 2022): 61–73. http://dx.doi.org/10.24195/2616-5317-2022-34-6.
Abstract (sommario):
The article is devoted to the study of the paradigm of changes in the content of official documents regulating economic and legal relations in the academic sphere in the XXI century. The author considers the factors influencing the process of changes in the content of official documents regulating economic and legal relations in the academic sphere in the context of the linguistic-translation paradigm. The concepts “economic and legal discourse”, “composition of the text of the document”, “academic sphere” have been clarified. Economic and legal discourse is determined through the prism of its dual nature (linguistic and extralinguistic) as a discourse of economics and law, education-driven discourse, its extralinguistic background being associated with the prerequisites for initiating elaborations in the area of education, for launching academic mobility programmes intended for participants of the teaching / learning process at the background of the native state development and intergovernmental cooperation. The text composition of the document is associated with the format (frame) of its representation, namely: the structural and compositional form of the document along with lexical and grammatical features of the economic and legal discourse. We interpret the academic sphere as the environment in which the acquisition of new knowledge, exchange of education-related information, implementation of scientific / research projects, practical manifestation of the outcomes, cultural exchange and intercultural communication take place due to the creation of certain conditions. Some changes in the structure and composition of the documents regulating economic and legal relations in the academic sphere have been characterised. The linguistic peculiarities of the English official documents and their variants of translation into Chinese and Ukrainian have been analysed. The author presents illustrative means demonstrating the interaction of factors influencing the content of official documents which regulate economic and legal relations in the academic sphere in the XXI century.
9
Dalyan, Tuğba, Hakan Ayral e Özgür Özdemir. "A Comprehensive Study of Learning Approaches for Author Gender Identification". Information Technology and Control 51, n. 3 (23 settembre 2022): 429–45. http://dx.doi.org/10.5755/j01.itc.51.3.29907.
Abstract (sommario):
In recent years, author gender identification is an important yet challenging task in the fields of information retrieval and computational linguistics. In this paper, different learning approaches are presented to address the problem of author gender identification for Turkish articles. First, several classification algorithms are applied to the list of representations based on different paradigms: fixed-length vector representations such as Stylometric Features (SF), Bag-of-Words (BoW) and distributed word/document embeddings such as Word2vec, fastText and Doc2vec. Secondly, deep learning architectures, Convolution Neural Network (CNN), Recurrent Neural Network (RNN), special kinds of RNN such as Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU), C-RNN, Bidirectional LSTM (bi-LSTM), Bidirectional GRU (bi-GRU), Hierarchical Attention Networks and Multi-head Attention (MHA) are designated and their comparable performances are evaluated. We conducted a variety of experiments and achieved outstanding empirical results. To conclude, ML algorithms with BoW have promising results. fast-Text is also probably suitable between embedding models. This comprehensive study contributes to literature utilizing different learning approaches based on several ways of representations. It is also first important attempt to identify author gender applying SF, fastText and DNN architectures to the Turkish language.
10
Tarmizi, Nursyahirah, Suhaila Saee e Dayang Hanani Abang Ibrahim. "TOWARDS CURBING CYBER-BULLYING IN MALAYSIA BY AUTHOR IDENTIFICATION OF IBAN AND KADAZANDUSUN OSN TEXT USING DEEP LEARNING". ASEAN Engineering Journal 13, n. 2 (31 maggio 2023): 145–57. http://dx.doi.org/10.11113/aej.v13.19171.
Abstract (sommario):
Online Social Network (OSN) is frequently used to carry out cyber-criminal actions such as cyberbullying. As a developing country in Asia that keeps abreast of ICT advancement, Malaysia is no exception when it comes to cyberbullying. Author Identification (AI) task plays a vital role in social media forensic investigation (SMF) to unveil the genuine identity of the offender by analysing the text written in OSN by the candidate culprits. Several challenges in AI dealing with OSN text, including limited text length and informal language full of internet jargon and grammatical errors that further impact AI's performance in SMF. The traditional AI system that analyses long text documents seems inadequate to analyse short OSN text's writing style. N-gram features are proven to efficiently represent the authors' writing style for shot text. However, representing N-grams in traditional representation like Tf-IDF resulted in sparse and difficult in grasping the semantic information from text. Besides, most AI works have been done in English but receive less attention in indigenous languages. In West Malaysia, the supreme languages that transcend ethnic boundaries are Iban of Sarawak and KadazanDusun of Sabah, which both are inherently under-resourced. This paper presented a proposed workflow of AI for short OSN text using two Under-Resourced Language (U-RL), Iban and KadazanDusun tweets, to curb the cyberbullying issue in Malaysia. This paper compares Tf-Idf (sparse) and SoA embedding-based (dense) feature representations to observe which representations best represent the stylistic features of the authors’ writing. N-grams of word, character, and POS were extracted as the features. The representation models were learned by different classifiers using machine learning (Naïve Bayes, Random Forest, and SVM). The convolutional neural network (CNN), a SoA deep learning model in sentence classification, was tested against the traditional classifiers. The result was observed by combining different representation models and classifiers on three datasets (English, Iban, and KadazanDusun). The best result was achieved when CNN learned embedding-based models with a combination of all features. KadazanDusun achieved the highest accuracy with 95.76%, English with 95.02%, and Iban with 94%..
Tesi sul tema "Author and Document Representation Learning":
1
Terreau, Enzo. "Apprentissage de représentations d'auteurs et d'autrices à partir de modèles de langue pour l'analyse des dynamiques d'écriture". Electronic Thesis or Diss., Lyon 2, 2024. http://www.theses.fr/2024LYO20001.
Abstract (sommario):
La démocratisation récente et massive des outils numériques a donné à tous le moyen de produire de l'information et de la partager sur le web, que ce soit à travers des blogs, des réseaux sociaux, des plateformes de partage, ... La croissance exponentielle de cette masse d'information disponible, en grande partie textuelle, nécessite le développement de modèles de traitement automatique du langage naturel (TAL), afin de la représenter mathématiquement pour ensuite la classer, la trier ou la recommander. C'est l'apprentissage de représentation. Il vise à construire un espace de faible dimension où les distances entre les objets projetées (mots, textes) reflètent les distances constatées dans le monde réel, qu'elles soient sémantique, stylistique, ...La multiplication des données disponibles, combinée à l'explosion des moyens de calculs et l'essor de l'apprentissage profond à permis de créer des modèles de langue extrêmement performant pour le plongement des mots et des documents. Ils assimilent des notions sémantiques et de langue complexes, en restant accessibles à tous et facilement spécialisables sur des tâches ou des corpus plus spécifiques. Il est possible de les utiliser pour construire des plongements d'auteurices. Seulement il est difficile de savoir sur quels aspects un modèle va se focaliser pour les rapprocher ou les éloigner. Dans un cadre littéraire, il serait préférable que les similarités se rapportent principalement au style écrit. Plusieurs problèmes se posent alors. La définition du style littéraire est floue, il est difficile d'évaluer l'écart stylistique entre deux textes et donc entre leurs plongements. En linguistique computationnelle, les approches visant à le caractériser sont principalement statistiques, s'appuyant sur des marqueurs du langage. Fort de ces constats, notre première contribution propose une méthode d'évaluation de la capacité des modèles de langue à appréhender le style écrit. Nous aurons au préalable détaillé comment le texte est représenté en apprentissage automatique puis en apprentissage profond, au niveau du mot, du document puis des auteurices. Nous aurons aussi présenté le traitement de la notion de style littéraire en TAL, base de notre méthode. Le transfert de connaissances entre les boîtes noires que sont les grands modèles de langue et ces méthodes issues de la linguistique n'en demeure pas moins complexe. Notre seconde contribution vise à réconcilier ces approches via un modèle d'apprentissage de représentations d'auteurices se focalisant sur le style, VADES (Variational Author and Document Embedding with Style). Nous nous comparons aux méthodes existantes et analysons leurs limites dans cette optique-là. Enfin, nous nous intéressons à l'apprentissage de plongements dynamiques d'auteurices et de documents. En effet, l'information temporelle est cruciale et permet une représentation plus fine des dynamiques d'écriture. Après une présentation de l'état de l'art, nous détaillons notre dernière contribution, B²ADE (Brownian Bridge for Author and Document Embedding), modélisant les auteurices comme des trajectoires. Nous finissons en décrivant plusieurs axes d'améliorations de nos méthodes ainsi que quelques problématiques pour de futurs travauxThe recent and massive democratization of digital tools has empowered individuals to generate and share information on the web through various means such as blogs, social networks, sharing platforms, and more. The exponential growth of available information, mostly textual data, requires the development of Natural Language Processing (NLP) models to mathematically represent it and subsequently classify, sort, or recommend it. This is the essence of representation learning. It aims to construct a low-dimensional space where the distances between projected objects (words, texts) reflect real-world distances, whether semantic, stylistic, and so on.The proliferation of available data, coupled with the rise in computing power and deep learning, has led to the creation of highly effective language models for word and document embeddings. These models incorporate complex semantic and linguistic concepts while remaining accessible to everyone and easily adaptable to specific tasks or corpora. One can use them to create author embeddings. However, it is challenging to determine the aspects on which a model will focus to bring authors closer or move them apart. In a literary context, it is preferable for similarities to primarily relate to writing style, which raises several issues. The definition of literary style is vague, assessing the stylistic difference between two texts and their embeddings is complex. In computational linguistics, approaches aiming to characterize it are mainly statistical, relying on language markers. In light of this, our first contribution is a framework to evaluate the ability of language models to grasp writing style. We will have previously elaborated on text embedding models in machine learning and deep learning, at the word, document, and author levels. We will also have presented the treatment of the notion of literary style in Natural Language Processing, which forms the basis of our method. Transferring knowledge between black-box large language models and these methods derived from linguistics remains a complex task. Our second contribution aims to reconcile these approaches through a representation learning model focusing on style, VADES (Variational Author and Document Embedding with Style). We compare our model to state-of-the-art ones and analyze their limitations in this context.Finally, we delve into dynamic author and document embeddings. Temporal information is crucial, allowing for a more fine-grained representation of writing dynamics. After presenting the state of the art, we elaborate on our last contribution, B²ADE (Brownian Bridge Author and Document Embedding), which models authors as trajectories. We conclude by outlining several leads for improving our methods and highlighting potential research directions for the future
2
Sayadi, Karim. "Classification du texte numérique et numérisé. Approche fondée sur les algorithmes d'apprentissage automatique". Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066079/document.
Abstract (sommario):
Différentes disciplines des sciences humaines telles la philologie ou la paléographie font face à des tâches complexes et fastidieuses pour l'examen des sources de données. La proposition d'approches computationnelles en humanités permet d'adresser les problématiques rencontrées telles que la lecture, l'analyse et l'archivage de façon systématique. Les modèles conceptuels élaborés reposent sur des algorithmes et ces derniers donnent lieu à des implémentations informatiques qui automatisent ces tâches fastidieuses. La première partie de la thèse vise, d'une part, à établir la structuration thématique d'un corpus, en construisant des espaces sémantiques de grande dimension. D'autre part, elle vise au suivi dynamique des thématiques qui constitue un réel défi scientifique, notamment en raison du passage à l'échelle. La seconde partie de la thèse traite de manière holistique la page d'un document numérisé sans aucune intervention préalable. Le but est d'apprendre automatiquement des représentations du trait de l'écriture ou du tracé d'un certain script par rapport au tracé d'un autre script. Il faut dans ce cadre tenir compte de l'environnement où se trouve le tracé : image, artefact, bruits dus à la détérioration de la qualité du papier, etc. Notre approche propose un empilement de réseaux de neurones auto-encodeurs afin de fournir une représentation alternative des données reçues en entréeDifferent disciplines in the humanities, such as philology or palaeography, face complex and time-consuming tasks whenever it comes to examining the data sources. The introduction of computational approaches in humanities makes it possible to address issues such as semantic analysis and systematic archiving. The conceptual models developed are based on algorithms that are later hard coded in order to automate these tedious tasks. In the first part of the thesis we propose a novel method to build a semantic space based on topics modeling. In the second part and in order to classify historical documents according to their script. We propose a novel representation learning method based on stacking convolutional auto-encoder. The goal is to automatically learn plot representations of the script or the written language
3
Wauquier, Pauline. "Task driven representation learning". Thesis, Lille 3, 2017. http://www.theses.fr/2017LIL30005/document.
Abstract (sommario):
De nombreux algorithmes d'Apprentissage automatique ont été proposés afin de résoudre les différentes tâches pouvant être extraites des problèmes de prédiction issus d'un contexte réel. Pour résoudre les différentes tâches pouvant être extraites, la plupart des algorithmes d'Apprentissage automatique se basent d'une manière ou d'une autre sur des relations liant les instances. Les relations entre paires d'instances peuvent être définies en calculant une distance entre les représentations vectorielles des instances. En se basant sur la représentation vectorielle des données, aucune des distances parmi celles communément utilisées n'est assurée d'être représentative de la tâche à résoudre. Dans ce document, nous étudions l'intérêt d'adapter la représentation vectorielle des données à la distance utilisée pour une meilleure résolution de la tâche. Nous nous concentrons plus précisément sur l'algorithme existant résolvant une tâche de classification en se basant sur un graphe. Nous décrivons d'abord un algorithme apprenant une projection des données dans un espace de représentation permettant une résolution, basée sur un graphe, optimale de la classification. En projetant les données dans un espace de représentation dans lequel une distance préalablement définie est représentative de la tâche, nous pouvons surpasser la représentation vectorielle des données lors de la résolution de la tâche. Une analyse théorique de l'algorithme décrit est développée afin de définir les conditions assurant une classification optimale. Un ensemble d'expériences nous permet finalement d'évaluer l'intérêt de l'approche introduite et de nuancer l'analyse théoriqueMachine learning proposes numerous algorithms to solve the different tasks that can be extracted from real world prediction problems. To solve the different concerned tasks, most Machine learning algorithms somehow rely on relationships between instances. Pairwise instances relationships can be obtained by computing a distance between the vectorial representations of the instances. Considering the available vectorial representation of the data, none of the commonly used distances is ensured to be representative of the task that aims at being solved. In this work, we investigate the gain of tuning the vectorial representation of the data to the distance to more optimally solve the task. We more particularly focus on an existing graph-based algorithm for classification task. An algorithm to learn a mapping of the data in a representation space which allows an optimal graph-based classification is first introduced. By projecting the data in a representation space in which the predefined distance is representative of the task, we aim at outperforming the initial vectorial representation of the data when solving the task. A theoretical analysis of the introduced algorithm is performed to define the conditions ensuring an optimal classification. A set of empirical experiments allows us to evaluate the gain of the introduced approach and to temper the theoretical analysis
4
Dos, Santos Ludovic. "Representation learning for relational data". Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066480/document.
Abstract (sommario):
L'utilisation croissante des réseaux sociaux et de capteurs génère une grande quantité de données qui peuvent être représentées sous forme de graphiques complexes. Il y a de nombreuses tâches allant de l'analyse de l'information à la prédiction et à la récupération que l'on peut imaginer sur ces données où la relation entre les noeuds de graphes devrait être informative. Dans cette thèse, nous avons proposé différents modèles pour trois tâches différentes: - Classification des noeuds graphiques - Prévisions de séries temporelles relationnelles - Filtrage collaboratif. Tous les modèles proposés utilisent le cadre d'apprentissage de la représentation dans sa variante déterministe ou gaussienne. Dans un premier temps, nous avons proposé deux algorithmes pour la tâche de marquage de graphe hétérogène, l'un utilisant des représentations déterministes et l'autre des représentations gaussiennes. Contrairement à d'autres modèles de pointe, notre solution est capable d'apprendre les poids de bord lors de l'apprentissage simultané des représentations et des classificateurs. Deuxièmement, nous avons proposé un algorithme pour la prévision des séries chronologiques relationnelles où les observations sont non seulement corrélées à l'intérieur de chaque série, mais aussi entre les différentes séries. Nous utilisons des représentations gaussiennes dans cette contribution. C'était l'occasion de voir de quelle manière l'utilisation de représentations gaussiennes au lieu de représentations déterministes était profitable. Enfin, nous appliquons l'approche d'apprentissage de la représentation gaussienne à la tâche de filtrage collaboratif. Ceci est un travail préliminaire pour voir si les propriétés des représentations gaussiennes trouvées sur les deux tâches précédentes ont également été vérifiées pour le classement. L'objectif de ce travail était de généraliser ensuite l'approche à des données plus relationnelles et pas seulement des graphes bipartis entre les utilisateurs et les itemsThe increasing use of social and sensor networks generates a large quantity of data that can be represented as complex graphs. There are many tasks from information analysis, to prediction and retrieval one can imagine on those data where relation between graph nodes should be informative. In this thesis, we proposed different models for three different tasks: - Graph node classification - Relational time series forecasting - Collaborative filtering. All the proposed models use the representation learning framework in its deterministic or Gaussian variant. First, we proposed two algorithms for the heterogeneous graph labeling task, one using deterministic representations and the other one Gaussian representations. Contrary to other state of the art models, our solution is able to learn edge weights when learning simultaneously the representations and the classifiers. Second, we proposed an algorithm for relational time series forecasting where the observations are not only correlated inside each series, but also across the different series. We use Gaussian representations in this contribution. This was an opportunity to see in which way using Gaussian representations instead of deterministic ones was profitable. At last, we apply the Gaussian representation learning approach to the collaborative filtering task. This is a preliminary work to see if the properties of Gaussian representations found on the two previous tasks were also verified for the ranking one. The goal of this work was to then generalize the approach to more relational data and not only bipartite graphs between users and items
5
Belharbi, Soufiane. "Neural networks regularization through representation learning". Thesis, Normandie, 2018. http://www.theses.fr/2018NORMIR10/document.
Abstract (sommario):
Les modèles de réseaux de neurones et en particulier les modèles profonds sont aujourd'hui l'un des modèles à l'état de l'art en apprentissage automatique et ses applications. Les réseaux de neurones profonds récents possèdent de nombreuses couches cachées ce qui augmente significativement le nombre total de paramètres. L'apprentissage de ce genre de modèles nécessite donc un grand nombre d'exemples étiquetés, qui ne sont pas toujours disponibles en pratique. Le sur-apprentissage est un des problèmes fondamentaux des réseaux de neurones, qui se produit lorsque le modèle apprend par coeur les données d'apprentissage, menant à des difficultés à généraliser sur de nouvelles données. Le problème du sur-apprentissage des réseaux de neurones est le thème principal abordé dans cette thèse. Dans la littérature, plusieurs solutions ont été proposées pour remédier à ce problème, tels que l'augmentation de données, l'arrêt prématuré de l'apprentissage ("early stopping"), ou encore des techniques plus spécifiques aux réseaux de neurones comme le "dropout" ou la "batch normalization". Dans cette thèse, nous abordons le sur-apprentissage des réseaux de neurones profonds sous l'angle de l'apprentissage de représentations, en considérant l'apprentissage avec peu de données. Pour aboutir à cet objectif, nous avons proposé trois différentes contributions. La première contribution, présentée dans le chapitre 2, concerne les problèmes à sorties structurées dans lesquels les variables de sortie sont à grande dimension et sont généralement liées par des relations structurelles. Notre proposition vise à exploiter ces relations structurelles en les apprenant de manière non-supervisée avec des autoencodeurs. Nous avons validé notre approche sur un problème de régression multiple appliquée à la détection de points d'intérêt dans des images de visages. Notre approche a montré une accélération de l'apprentissage des réseaux et une amélioration de leur généralisation. La deuxième contribution, présentée dans le chapitre 3, exploite la connaissance a priori sur les représentations à l'intérieur des couches cachées dans le cadre d'une tâche de classification. Cet à priori est basé sur la simple idée que les exemples d'une même classe doivent avoir la même représentation interne. Nous avons formalisé cet à priori sous la forme d'une pénalité que nous avons rajoutée à la fonction de perte. Des expérimentations empiriques sur la base MNIST et ses variantes ont montré des améliorations dans la généralisation des réseaux de neurones, particulièrement dans le cas où peu de données d'apprentissage sont utilisées. Notre troisième et dernière contribution, présentée dans le chapitre 4, montre l'intérêt du transfert d'apprentissage ("transfer learning") dans des applications dans lesquelles peu de données d'apprentissage sont disponibles. L'idée principale consiste à pré-apprendre les filtres d'un réseau à convolution sur une tâche source avec une grande base de données (ImageNet par exemple), pour les insérer par la suite dans un nouveau réseau sur la tâche cible. Dans le cadre d'une collaboration avec le centre de lutte contre le cancer "Henri Becquerel de Rouen", nous avons construit un système automatique basé sur ce type de transfert d'apprentissage pour une application médicale où l'on dispose d’un faible jeu de données étiquetées. Dans cette application, la tâche consiste à localiser la troisième vertèbre lombaire dans un examen de type scanner. L’utilisation du transfert d’apprentissage ainsi que de prétraitements et de post traitements adaptés a permis d’obtenir des bons résultats, autorisant la mise en oeuvre du modèle en routine cliniqueNeural network models and deep models are one of the leading and state of the art models in machine learning. They have been applied in many different domains. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such models requires a large number of training samples which is not always available. One of the fundamental issues in neural networks is overfitting which is the issue tackled in this thesis. Such problem often occurs when the training of large models is performed using few training samples. Many approaches have been proposed to prevent the network from overfitting and improve its generalization performance such as data augmentation, early stopping, parameters sharing, unsupervised learning, dropout, batch normalization, etc. In this thesis, we tackle the neural network overfitting issue from a representation learning perspective by considering the situation where few training samples are available which is the case of many real world applications. We propose three contributions. The first one presented in chapter 2 is dedicated to dealing with structured output problems to perform multivariate regression when the output variable y contains structural dependencies between its components. Our proposal aims mainly at exploiting these dependencies by learning them in an unsupervised way. Validated on a facial landmark detection problem, learning the structure of the output data has shown to improve the network generalization and speedup its training. The second contribution described in chapter 3 deals with the classification task where we propose to exploit prior knowledge about the internal representation of the hidden layers in neural networks. This prior is based on the idea that samples within the same class should have the same internal representation. We formulate this prior as a penalty that we add to the training cost to be minimized. Empirical experiments over MNIST and its variants showed an improvement of the network generalization when using only few training samples. Our last contribution presented in chapter 4 showed the interest of transfer learning in applications where only few samples are available. The idea consists in re-using the filters of pre-trained convolutional networks that have been trained on large datasets such as ImageNet. Such pre-trained filters are plugged into a new convolutional network with new dense layers. Then, the whole network is trained over a new task. In this contribution, we provide an automatic system based on such learning scheme with an application to medical domain. In this application, the task consists in localizing the third lumbar vertebra in a 3D CT scan. A pre-processing of the 3D CT scan to obtain a 2D representation and a post-processing to refine the decision are included in the proposed system. This work has been done in collaboration with the clinic "Rouen Henri Becquerel Center" who provided us with data
6
Vukotic, Verdran. "Deep Neural Architectures for Automatic Representation Learning from Multimedia Multimodal Data". Thesis, Rennes, INSA, 2017. http://www.theses.fr/2017ISAR0015/document.
Abstract (sommario):
La thèse porte sur le développement d'architectures neuronales profondes permettant d'analyser des contenus textuels ou visuels, ou la combinaison des deux. De manière générale, le travail tire parti de la capacité des réseaux de neurones à apprendre des représentations abstraites. Les principales contributions de la thèse sont les suivantes: 1) Réseaux récurrents pour la compréhension de la parole: différentes architectures de réseaux sont comparées pour cette tâche sur leurs facultés à modéliser les observations ainsi que les dépendances sur les étiquettes à prédire. 2) Prédiction d’image et de mouvement : nous proposons une architecture permettant d'apprendre une représentation d'une image représentant une action humaine afin de prédire l'évolution du mouvement dans une vidéo ; l'originalité du modèle proposé réside dans sa capacité à prédire des images à une distance arbitraire dans une vidéo. 3) Encodeurs bidirectionnels multimodaux : le résultat majeur de la thèse concerne la proposition d'un réseau bidirectionnel permettant de traduire une modalité en une autre, offrant ainsi la possibilité de représenter conjointement plusieurs modalités. L'approche été étudiée principalement en structuration de collections de vidéos, dons le cadre d'évaluations internationales où l'approche proposée s'est imposée comme l'état de l'art. 4) Réseaux adverses pour la fusion multimodale: la thèse propose d'utiliser les architectures génératives adverses pour apprendre des représentations multimodales en offrant la possibilité de visualiser les représentations dans l'espace des imagesIn this dissertation, the thesis that deep neural networks are suited for analysis of visual, textual and fused visual and textual content is discussed. This work evaluates the ability of deep neural networks to learn automatic multimodal representations in either unsupervised or supervised manners and brings the following main contributions:1) Recurrent neural networks for spoken language understanding (slot filling): different architectures are compared for this task with the aim of modeling both the input context and output label dependencies.2) Action prediction from single images: we propose an architecture that allow us to predict human actions from a single image. The architecture is evaluated on videos, by utilizing solely one frame as input.3) Bidirectional multimodal encoders: the main contribution of this thesis consists of neural architecture that translates from one modality to the other and conversely and offers and improved multimodal representation space where the initially disjoint representations can translated and fused. This enables for improved multimodal fusion of multiple modalities. The architecture was extensively studied an evaluated in international benchmarks within the task of video hyperlinking where it defined the state of the art today.4) Generative adversarial networks for multimodal fusion: continuing on the topic of multimodal fusion, we evaluate the possibility of using conditional generative adversarial networks to lean multimodal representations in addition to providing multimodal representations, generative adversarial networks permit to visualize the learned model directly in the image domain
7
Karpate, Yogesh. "Enhanced representation & learning of magnetic resonance signatures in multiple sclerosis". Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S068/document.
Abstract (sommario):
La sclérose en plaques (SEP) est une maladie auto-immune inflammatoire du jeune adulte causant des handicaps variables et progressifs irréversibles. Cette maladie est présente de manière prépondérante dans l’hémisphère nord. Cette thèse s’attache à la caractérisation et à la modélisation de signatures IRM multimodales des lésions de sclérose en plaques. L’objectif est d’améliorer les modèles de représentation de l’image et d’adapter les méthodes d’apprentissage pour la reconnaissance visuelle, dans le cas où des informations de haut niveau telles que les lésions SEP incluses dans l’IRM sont extraites. Nous proposons dans cette thèse un nouvel algorithme de normalisation d’intensité en IRM, particulièrement centré sur la normalisation d’images longitudinales multimodales, afin de produire des détections d’évolution de lésion robustes. Cette normalisation est centrée sur la modélisation de l’histogramme de l’image par un modèle de mixture de Gaussiennes robuste à la présence de lésions. Faisant suite à cet algorithme, nous proposons également deux nouvelles méthodes de détection de lésions SEP basées sur (1) une comparaison statistique du patient vis à vis d’une population de sujets contrôle et (2) un cadre probabiliste de détection basé sur un apprentissage d’une classe (tissus sains). Nous avons évalué les algorithmes proposés sur plusieurs jeux de données multi-centriques et vérifié leur efficacité dans la détection de lésionsMultiple Sclerosis (MS) is an acquired inflammatory disease, which causes disabilities in young adults and it is common in northern hemisphere. This PhD work focuses on characterization and modeling of multidimensional MRI signatures in MS Lesions (MSL). The objective is to improve image representation and learning for visual recognition, where high level information such as MSL contained in MRI are automatically extracted. We propose a new longitudinal intensity normalization algorithm for multichannel MRI in the presence of MS lesions, which provides consistent and reliable longitudinal detections. This is primarily based on learning the tissue intensities from multichannel MRI using robust Gaussian Mixture Modeling. Further, we proposed two MSL detection methods based on a statistical patient to population comparison framework and probabilistic one class learning. We evaluated our proposed algorithms on multi-center databases to verify its efficacy
8
Soltan-Zadeh, Yasaman. "Improved rule-based document representation and classification using genetic programming". Thesis, Royal Holloway, University of London, 2011. http://repository.royalholloway.ac.uk/items/479a1773-779b-8b24-b334-7ed485311abe/8/.
9
Lu, Ying. "Transfer Learning for Image Classification". Thesis, Lyon, 2017. http://www.theses.fr/2017LYSEC045/document.
Abstract (sommario):
Lors de l’apprentissage d’un modèle de classification pour un nouveau domaine cible avec seulement une petite quantité d’échantillons de formation, l’application des algorithmes d’apprentissage automatiques conduit généralement à des classifieurs surdimensionnés avec de mauvaises compétences de généralisation. D’autre part, recueillir un nombre suffisant d’échantillons de formation étiquetés manuellement peut s’avérer très coûteux. Les méthodes de transfert d’apprentissage visent à résoudre ce type de problèmes en transférant des connaissances provenant d’un domaine source associé qui contient beaucoup plus de données pour faciliter la classification dans le domaine cible. Selon les différentes hypothèses sur le domaine cible et le domaine source, l’apprentissage par transfert peut être classé en trois catégories: apprentissage par transfert inductif, apprentissage par transfert transducteur (adaptation du domaine) et apprentissage par transfert non surveillé. Nous nous concentrons sur le premier qui suppose que la tâche cible et la tâche source sont différentes mais liées. Plus précisément, nous supposons que la tâche cible et la tâche source sont des tâches de classification, tandis que les catégories cible et les catégories source sont différentes mais liées. Nous proposons deux méthodes différentes pour aborder ce problème. Dans le premier travail, nous proposons une nouvelle méthode d’apprentissage par transfert discriminatif, à savoir DTL(Discriminative Transfer Learning), combinant une série d’hypothèses faites à la fois par le modèle appris avec les échantillons de cible et les modèles supplémentaires appris avec des échantillons des catégories sources. Plus précisément, nous utilisons le résidu de reconstruction creuse comme discriminant de base et améliore son pouvoir discriminatif en comparant deux résidus d’un dictionnaire positif et d’un dictionnaire négatif. Sur cette base, nous utilisons des similitudes et des dissemblances en choisissant des catégories sources positivement corrélées et négativement corrélées pour former des dictionnaires supplémentaires. Une nouvelle fonction de coût basée sur la statistique de Wilcoxon-Mann-Whitney est proposée pour choisir les dictionnaires supplémentaires avec des données non équilibrées. En outre, deux processus de Boosting parallèles sont appliqués à la fois aux distributions de données positives et négatives pour améliorer encore les performances du classificateur. Sur deux bases de données de classification d’images différentes, la DTL proposée surpasse de manière constante les autres méthodes de l’état de l’art du transfert de connaissances, tout en maintenant un temps d’exécution très efficace. Dans le deuxième travail, nous combinons le pouvoir du transport optimal (OT) et des réseaux de neurones profond (DNN) pour résoudre le problème ITL. Plus précisément, nous proposons une nouvelle méthode pour affiner conjointement un réseau de neurones avec des données source et des données cibles. En ajoutant une fonction de perte du transfert optimal (OT loss) entre les prédictions du classificateur source et cible comme une contrainte sur le classificateur source, le réseau JTLN (Joint Transfer Learning Network) proposé peut effectivement apprendre des connaissances utiles pour la classification cible à partir des données source. En outre, en utilisant différents métriques comme matrice de coût pour la fonction de perte du transfert optimal, JTLN peut intégrer différentes connaissances antérieures sur la relation entre les catégories cibles et les catégories sources. Nous avons effectué des expérimentations avec JTLN basées sur Alexnet sur les jeux de données de classification d’image et les résultats vérifient l’efficacité du JTLN proposé. A notre connaissances, ce JTLN proposé est le premier travail à aborder ITL avec des réseaux de neurones profond (DNN) tout en intégrant des connaissances antérieures sur la relation entre les catégories cible et sourceWhen learning a classification model for a new target domain with only a small amount of training samples, brute force application of machine learning algorithms generally leads to over-fitted classifiers with poor generalization skills. On the other hand, collecting a sufficient number of manually labeled training samples may prove very expensive. Transfer Learning methods aim to solve this kind of problems by transferring knowledge from related source domain which has much more data to help classification in the target domain. Depending on different assumptions about target domain and source domain, transfer learning can be further categorized into three categories: Inductive Transfer Learning, Transductive Transfer Learning (Domain Adaptation) and Unsupervised Transfer Learning. We focus on the first one which assumes that the target task and source task are different but related. More specifically, we assume that both target task and source task are classification tasks, while the target categories and source categories are different but related. We propose two different methods to approach this ITL problem. In the first work we propose a new discriminative transfer learning method, namely DTL, combining a series of hypotheses made by both the model learned with target training samples, and the additional models learned with source category samples. Specifically, we use the sparse reconstruction residual as a basic discriminant, and enhance its discriminative power by comparing two residuals from a positive and a negative dictionary. On this basis, we make use of similarities and dissimilarities by choosing both positively correlated and negatively correlated source categories to form additional dictionaries. A new Wilcoxon-Mann-Whitney statistic based cost function is proposed to choose the additional dictionaries with unbalanced training data. Also, two parallel boosting processes are applied to both the positive and negative data distributions to further improve classifier performance. On two different image classification databases, the proposed DTL consistently out performs other state-of-the-art transfer learning methods, while at the same time maintaining very efficient runtime. In the second work we combine the power of Optimal Transport and Deep Neural Networks to tackle the ITL problem. Specifically, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and target classifier predictions as a constraint on the source classifier, the proposed Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data. Furthermore, by using different kind of metric as cost matrix for the OT loss, JTLN can incorporate different prior knowledge about the relatedness between target categories and source categories. We carried out experiments with JTLN based on Alexnet on image classification datasets and the results verify the effectiveness of the proposed JTLN in comparison with standard consecutive fine-tuning. To the best of our knowledge, the proposed JTLN is the first work to tackle ITL with Deep Neural Networks while incorporating prior knowledge on relatedness between target and source categories. This Joint Transfer Learning with OT loss is general and can also be applied to other kind of Neural Networks
10
Alaverdyan, Zaruhi. "Unsupervised representation learning for anomaly detection on neuroimaging. Application to epilepsy lesion detection on brain MRI". Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI005/document.
Abstract (sommario):
Cette étude vise à développer un système d’aide au diagnostic (CAD) pour la détection de lésions épileptogènes, reposant sur l’analyse de données de neuroimagerie, notamment, l’IRM T1 et FLAIR. L’approche adoptée, introduite précédemment par Azami et al., 2016, consiste à placer la tâche de détection dans le cadre de la détection de changement à l'échelle du voxel, basée sur l’apprentissage d’un modèle one-class SVM pour chaque voxel dans le cerveau. L'objectif principal de ce travail est de développer des mécanismes d’apprentissage de représentations, qui capturent les informations les plus discriminantes à partir de l’imagerie multimodale. Les caractéristiques manuelles ne sont pas forcément les plus pertinentes pour la tâche visée. Notre première contribution porte sur l'intégration de différents réseaux profonds non-supervisés, pour extraire des caractéristiques dans le cadre du problème de détection de changement. Nous introduisons une nouvelle configuration des réseaux siamois, mieux adaptée à ce contexte. Le système CAD proposé a été évalué sur l’ensemble d’images IRM T1 des patients atteints d'épilepsie. Afin d'améliorer la performance obtenue, nous avons proposé d'étendre le système pour intégrer des données multimodales qui possèdent des informations complémentaires sur la pathologie. Notre deuxième contribution consiste donc à proposer des stratégies de combinaison des différentes modalités d’imagerie dans un système pour la détection de changement. Ce système multimodal a montré une amélioration importante sur la tâche de détection de lésions épileptogènes sur les IRM T1 et FLAIR. Notre dernière contribution se focalise sur l'intégration des données TEP dans le système proposé. Etant donné le nombre limité des images TEP, nous envisageons de synthétiser les données manquantes à partir des images IRM disponibles. Nous démontrons que le système entraîné sur les données réelles et synthétiques présente une amélioration importante par rapport au système entraîné sur les images réelles uniquementThis work represents one attempt to develop a computer aided diagnosis system for epilepsy lesion detection based on neuroimaging data, in particular T1-weighted and FLAIR MR sequences. Given the complexity of the task and the lack of a representative voxel-level labeled data set, the adopted approach, first introduced in Azami et al., 2016, consists in casting the lesion detection task as a per-voxel outlier detection problem. The system is based on training a one-class SVM model for each voxel in the brain on a set of healthy controls, so as to model the normality of the voxel. The main focus of this work is to design representation learning mechanisms, capturing the most discriminant information from multimodality imaging. Manual features, designed to mimic the characteristics of certain epilepsy lesions, such as focal cortical dysplasia (FCD), on neuroimaging data, are tailored to individual pathologies and cannot discriminate a large range of epilepsy lesions. Such features reflect the known characteristics of lesion appearance; however, they might not be the most optimal ones for the task at hand. Our first contribution consists in proposing various unsupervised neural architectures as potential feature extracting mechanisms and, eventually, introducing a novel configuration of siamese networks, to be plugged into the outlier detection context. The proposed system, evaluated on a set of T1-weighted MRIs of epilepsy patients, showed a promising performance but a room for improvement as well. To this end, we considered extending the CAD system so as to accommodate multimodality data which offers complementary information on the problem at hand. Our second contribution, therefore, consists in proposing strategies to combine representations of different imaging modalities into a single framework for anomaly detection. The extended system showed a significant improvement on the task of epilepsy lesion detection on T1-weighted and FLAIR MR images. Our last contribution focuses on the integration of PET data into the system. Given the small number of available PET images, we make an attempt to synthesize PET data from the corresponding MRI acquisitions. Eventually we show an improved performance of the system when trained on the mixture of synthesized and real images
Libri sul tema "Author and Document Representation Learning":
1
Edwards, Carolyn, Lella Gandini e George Forman, a cura di. The Hundred Languages of Children. 3a ed. ABC-CLIO, LLC, 2011. http://dx.doi.org/10.5040/9798400667664.
Abstract (sommario):
Why does the city of Reggio Emilia in northern Italy feature one of the best public systems of early education in the world? This book documents the comprehensive and innovative approach that utilizes the "hundred languages of children" to support their well-being and foster their intellectual development. Educators in Reggio Emilia, Italy, use a distinctive innovative approach that supports children's well-being and fosters their intellectual development through a systematic focus on symbolic representation. From birth through age six, young children are encouraged to explore their environment and express their understanding through many modes of expression or "languages," including verbal communication, movement, drawing, painting, sculpture, shadow play, collage, and music. This organic strategy has been shown to be highly effective, as the children in Reggio Emilia display surprising examples of symbolic skill and creativity. This book describes how the world-renowned preschool services and accompanying practical strategies for children under six in Reggio Emilia have evolved in response to the community's demographic and political transformations, and to generational changes in both the educators and the parents of the children. The authors provide the reader with a comprehensive introduction to the Reggio Emilia experience, and address three of the most important central themes of the work in Reggio in detail: teaching and learning through relationships; the hundred languages of children, and how this concept has evolved; and integrating documentation into the process of observing, reflecting, and communicating.
Capitoli di libri sul tema "Author and Document Representation Learning":
1
Liu, Zhiyuan, Yankai Lin e Maosong Sun. "Document Representation". In Representation Learning for Natural Language Processing, 91–123. Singapore: Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-15-5573-2_5.
2
Kamkarhaghighi, Mehran, Eren Gultepe e Masoud Makrehchi. "Deep Learning for Document Representation". In Handbook of Deep Learning Applications, 101–10. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-11479-4_5.
3
Ding, Ning, Yankai Lin, Zhiyuan Liu e Maosong Sun. "Sentence and Document Representation Learning". In Representation Learning for Natural Language Processing, 81–125. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-1600-9_4.
Abstract (sommario):
AbstractSentence and document are high-level linguistic units of natural languages. Representation learning of sentences and documents remains a core and challenging task because many important applications of natural language processing (NLP) lie in understanding sentences and documents. This chapter first introduces symbolic methods to sentence and document representation learning. Then we extensively introduce neural network-based methods for the far-reaching language modeling task, including feed-forward neural networks, convolutional neural networks, recurrent neural networks, and Transformers. Regarding the characteristics of a document consisting of multiple sentences, we particularly introduce memory-based and hierarchical approaches to document representation learning. Finally, we present representative applications of sentence and document representation, including text classification, sequence labeling, reading comprehension, question answering, information retrieval, and sequence-to-sequence generation.
4
Cosma, Adrian, Mihai Ghidoveanu, Michael Panaitescu-Liess e Marius Popescu. "Self-supervised Representation Learning on Document Images". In Document Analysis Systems, 103–17. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-57058-3_8.
5
Wu, Xiaoyun, Rohini Srihari e Zhaohui Zheng. "Document Representation for One-Class SVM". In Machine Learning: ECML 2004, 489–500. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004. http://dx.doi.org/10.1007/978-3-540-30115-8_45.
6
Saeidi, Mozhgan, Evangelos Milios e Norbert Zeh. "Graph Representation Learning in Document Wikification". In Document Analysis and Recognition – ICDAR 2021 Workshops, 509–24. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86159-9_37.
7
López-Monroy, Adrián Pastor, Manuel Montes-y-Gómez, Luis Villaseñor-Pineda, Jesús Ariel Carrasco-Ochoa e José Fco Martínez-Trinidad. "A New Document Author Representation for Authorship Attribution". In Lecture Notes in Computer Science, 283–92. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-31149-9_29.
8
Zhang, Yue, Liying Zhang e Yao Liu. "Linked Document Classification by Network Representation Learning". In Lecture Notes in Computer Science, 302–13. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-01716-3_25.
9
Feng, Hao, Wengang Zhou, Jiajun Deng, Yuechen Wang e Houqiang Li. "Geometric Representation Learning for Document Image Rectification". In Lecture Notes in Computer Science, 475–92. Cham: Springer Nature Switzerland, 2022. http://dx.doi.org/10.1007/978-3-031-19836-6_27.
10
Li, Luyang, Wenjing Ren, Bing Qin e Ting Liu. "Learning Document Representation for Deceptive Opinion Spam Detection". In Lecture Notes in Computer Science, 393–404. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-25816-4_32.
Atti di convegni sul tema "Author and Document Representation Learning":
1
Li, Peizhao, Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, Handong Zhao, Rajiv Jain, Varun Manjunatha e Hongfu Liu. "SelfDoc: Self-Supervised Document Representation Learning". In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021. http://dx.doi.org/10.1109/cvpr46437.2021.00560.
2
Frery, Jordan, Christine Largeron e Mihaela Juganaru-Mathieu. "Author identification by automatic learning". In 2015 13th International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2015. http://dx.doi.org/10.1109/icdar.2015.7333748.
3
Chen, Xiuying, Shen Gao, Chongyang Tao, Yan Song, Dongyan Zhao e Rui Yan. "Iterative Document Representation Learning Towards Summarization with Polishing". In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2018. http://dx.doi.org/10.18653/v1/d18-1442.
4
Menon, Remya, K. Harikrishnan e Ganesh Varier. "Parallel Approach for Document Representation using Dictionary Learning". In 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). IEEE, 2019. http://dx.doi.org/10.1109/icicict46008.2019.8993114.
5
Xu, Peng, Xinchi Chen, Xiaofei Ma, Zhiheng Huang e Bing Xiang. "Contrastive Document Representation Learning with Graph Attention Networks". In Findings of the Association for Computational Linguistics: EMNLP 2021. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.findings-emnlp.327.
6
Dewalkar, Swapnil, e Maunendra Sankar Desarkar. "Multi-Context Information for Word Representation Learning". In DocEng '19: ACM Symposium on Document Engineering 2019. New York, NY, USA: ACM, 2019. http://dx.doi.org/10.1145/3342558.3345418.
7
Peng, Liwen, Siqi Shen, Dongsheng Li, Jun Xu, Yongquan Fu e Huayou Su. "Author Disambiguation through Adversarial Network Representation Learning". In 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019. http://dx.doi.org/10.1109/ijcnn.2019.8852233.
8
"Author index". In 2018 First International Workshop on Deep and Representation Learning (IWDRL). IEEE, 2018. http://dx.doi.org/10.1109/iwdrl.2018.8358216.
9
Zhou, Xinjie, Xiaojun Wan e Jianguo Xiao. "Cross-Lingual Sentiment Classification with Bilingual Document Representation Learning". In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2016. http://dx.doi.org/10.18653/v1/p16-1133.
10
Tang, Duyu. "Sentiment-Specific Representation Learning for Document-Level Sentiment Analysis". In WSDM 2015: Eighth ACM International Conference on Web Search and Data Mining. New York, NY, USA: ACM, 2015. http://dx.doi.org/10.1145/2684822.2697035.
Rapporti di organizzazioni sul tema "Author and Document Representation Learning":
1
Church, Joshua, LaKenya Walker e Amy Bednar. Iterative Learning Algorithm for Records Analysis (ILARA) user manual. Engineer Research and Development Center (U.S.), settembre 2021. http://dx.doi.org/10.21079/11681/41845.
Abstract (sommario):
This manual is intended for new users with minimal or no experience with using the Iterative Learning Algorithm for Records Analysis (ILARA) tool. The goal of this document is to give an overview of the main functions of ILARA. The primary focus of this document is to demonstrate functionality. Every effort has been made to ensure this document is an accurate representation of the functionality of the ILARA tool. For additional information about this manual, contact ERDC.JAIC@erdc.dren.mil.
2
Learning About Women and Urban Services in Latin America and the Caribbean. Population Council, 1986. http://dx.doi.org/10.31899/pgy1986.1000.
Abstract (sommario):
In 1978 when the Population Council formulated a program to learn more about low-income urban women’s access to services, the dearth of information was striking, particularly in contrast to the emerging body of information delineating access to credit, extension, membership in rural institutions, and representation in local governments. Access to services was much less well-defined owing to the diverse cultures that meet in the urban environment, the mobility of city life, and the fluidity of households. Urban development planners, researchers, and those involved in community action projects in a number of South American cities were approached to find out what they knew, and there was much interest on the part of urban planners in learning how their programs affected men and women differentially. The interest of these diverse groups called for a long-term approach. Three working groups on Women, Low-Income Households, and Urban Services evolved in Kingston, Jamaica; Lima, Peru; and Mexico City, Mexico. Much detail is provided in this volume on how these groups function and arrive at their priorities. Rather than confining this report to a lengthy internal document, this work was brought to the attention of a broader audience through summary articles.