Federated learning is a widely established modern machine learning methodology where training is done directly on the client device with local client data and the local training results are shared to compute a global model. Federated learning emerged as a result of data ownership and the privacy concerns of traditional machine learning methodologies where data is collected and trained at a central location. However, in a distributed data environment, the training suffers significantly when the client data is not identically distributed. Hence, clustered federated learning was proposed where similar clients are clustered and trained independently to form specialized cluster models which are then used to compute a global model. In this approach, the cluster selection for clustered federated learning is a major factor that affects the effectiveness of the global model. This research presents two approaches for client clustering using local client data for clustered federated learning while preserving data privacy. The two proposed approaches use min-wise independent permutations to compute client signatures using text and word embeddings. These client signatures are then used as a representation of client data to cluster clients using agglomerative hierarchical clustering. Unlike previously proposed clustering methods, the two presented approaches do not use model updates, provide a better privacy-preserving mechanism and have a lower communication overhead. With extensive experimentation, we show that the proposed approaches outperform the random clustering approach. Finally, we present a client clustering methodology that can be utilized in a practical clustered federated learning environment. / Federerad inlärning är en etablerad och modern maskininlärnings metod. Träningen är utförd direkt på klientenheten med lokal klient data. Sen är dem lokala träningsresultat delad för att beräkna en global modell. Federerad inlärning har utvecklats på grund av dataägarskap- och dataintegritetsproblem vid traditionella maskininlärnings metoder. Dessa metoder samlar och tränar data på en central enhet. I den här metoden är kluster selektionen en viktig faktor som påverkar effektiviteten av den globala modellen. Detta forskningsarbete presenterar två metoder för klient klustring med hjälp av lokala klientdata för federerad inlärning samtidigt tar metoderna hänsyn på dataintegritet. Metoderna använder “min-wise” oberoende permutations och förtränade (“text och word”) inbäddningar. Dessa klientsignaturer används som en klientdata representation för att klustrar klienter med hjälp av agglomerativ hierarkisk klustring. Till skillnad från tidigare klustringsmetoder använder de två presenterade metoderna inte modelluppdateringar. Detta ger en bättre sekretessbevarande mekanism och har lägre kommunikationskostnader. De två presenterade metoderna överträffar den slumpmässiga klustringsmetoden genom omfattande experiment och analys. Till slut presenterar vi en klientklustermetodik som kan användas i en praktisk klustrad federerad inlärningsmiljö.

This thesis explores the possibility to extend monolingual and bilingual text classifiers to multiple languages. Two different language models are explored, language aligned word embeddings and a transformer model. The goal was to take a classifier based on Swedish and English samples and extend it to Danish, German, and Finnish samples. The result shows that extending a text classifier by word embeddings alignment or by finetuning a multilingual transformer model is possible but with varying accuracy depending on the language. / Denna avhandling undersöker möjligheten att utvidga enspråkiga och tvåspråkiga textklassificatorer till flera språk. Två olika språkmodeller utforskas, justeras ordinbäddningar och en transformatormodell. Målet var att ta en klassificerare baserad på svenska och engelska texter och utvidga den till danska, tyska och finska texter. Resultatet visar att det är möjligt att utöka en textklassificering med ordinbäddning eller genom att finjustera en flerspråkig transformatormodell, men träffsäkerheten varierar beroende på språk.

Readability metrics assess the ease with which human beings read and understand written texts. With the advent of machine learning techniques that allow computers to also analyse text, this provides an interesting opportunity to investigate whether readability metrics can be used to inform on the ease with which machines understand texts. To that end, the specific machine analysed in this paper uses word embeddings to conduct unsupervised sentiment analysis. This specification minimises the need for labelling and human intervention, thus relying heavily on the machine instead of the human. Across two different datasets, sentiment predictions are made using Google’s Word2Vec word embedding algorithm, and are evaluated to produce a dichotomous output variable per sentiment. This variable, representing whether a prediction is correct or not, is then used as the dependent variable in a logistic regression with 17 readability metrics as independent variables. The resulting model has high explanatory power and the effects of readability metrics on the results from the sentiment analysis are mostly statistically significant. However, metrics affect sentiment classification in the two datasets differently, indicating that the metrics are expressions of linguistic behaviour unique to the datasets. The implication of the findings is that readability metrics could be used directly in sentiment classification models to improve modelling accuracy. Moreover, the results also indicate that machines are able to pick up on information that human beings do not pick up on, for instance that certain words are associated with more positive or negative sentiments. / Läsbarhetsmått bedömer hur lätt eller svårt det är för människor att läsa och förstå skrivna texter. Eftersom nya maskininlärningstekniker har utvecklats kan datorer numera också analysera texter. Därför är en intressant infallsvinkel huruvida läsbarhetsmåtten också kan användas för att bedöma hur lätt eller svårt det är för maskiner att förstå texter. Mot denna bakgrund använder den specifika maskinen i denna uppsats ordinbäddningar i syfte att utföra oövervakad sentimentanalys. Således minimeras behovet av etikettering och mänsklig handpåläggning, vilket resulterar i en mer djupgående analys av maskinen istället för människan. I två olika dataset jämförs rätt svar mot sentimentförutsägelser från Googles ordinbäddnings-algoritm Word2Vec för att producera en binär utdatavariabel per sentiment. Denna variabel, som representerar om en förutsägelse är korrekt eller inte, används sedan som beroende variabel i en logistisk regression med 17 olika läsbarhetsmått som oberoende variabler. Den resulterande modellen har högt förklaringsvärde och effekterna av läsbarhetsmåtten på resultaten från sentimentanalysen är mestadels statistiskt signifikanta. Emellertid är effekten på klassificeringen beroende på dataset, vilket indikerar att läsbarhetsmåtten ger uttryck för olika lingvistiska beteenden som är unika till datamängderna. Implikationen av resultaten är att läsbarhetsmåtten kan användas direkt i modeller som utför sentimentanalys för att förbättra deras prediktionsförmåga. Dessutom indikerar resultaten också att maskiner kan plocka upp på information som människor inte kan, exempelvis att vissa ord är associerade med positiva eller negativa sentiment.

No description available.

Nous abordons, dans cette thèse, une étude sur les représentations continues de mots (en anglais word embeddings) appliquées à la détection automatique des erreurs dans les transcriptions de la parole. Notre étude se concentre sur l’utilisation d’une approche neuronale pour améliorer la détection automatique des erreurs dans les transcriptions automatiques, en exploitant les word embeddings. L’exploitation des embeddings repose sur l’idée que la détection d’erreurs consiste à trouver les possibles incongruités linguistiques ou acoustiques au sein des transcriptions automatiques. L’intérêt est donc de trouver la représentation appropriée du mot qui permet de capturer des informations pertinentes pour pouvoir détecter ces anomalies. Notre contribution dans le cadre de cette thèse porte sur plusieurs axes. D’abord, nous commençons par une étude préliminaire dans laquelle nous proposons une architecture neuronale capable d’intégrer différents types de descripteurs, y compris les embeddings. Ensuite, nous nous focalisons sur une étude approfondie des représentations continues de mots. Cette étude porte d’une part sur l’évaluation de différents types d’embeddings linguistiques puis sur leurs combinaisons. D’autre part, elle s’intéresse aux embeddings acoustiques de mots. Puis, nous présentons une étude sur l’analyse des erreurs de classifications, qui a pour objectif de percevoir les erreurs difficiles à détecter.Finalement, nous exploitons les embeddings linguistiques et acoustiques ainsi que l’information fournie par notre système de détections d’erreurs dans plusieurs cadres applicatifs. / My thesis concerns a study of continuous word representations applied to the automatic detection of speech recognition errors. Our study focuses on the use of a neural approach to improve ASR errors detection, using word embeddings. The exploitation of continuous word representations is motivated by the fact that ASR error detection consists on locating the possible linguistic or acoustic incongruities in automatic transcriptions. The aim is therefore to find the appropriate word representation which makes it possible to capture pertinent information in order to be able to detect these anomalies. Our contribution in this thesis concerns several initiatives. First, we start with a preliminary study in which we propose a neural architecture able to integrate different types of features, including word embeddings. Second, we propose a deep study of continuous word representations. This study focuses on the evaluation of different types of linguistic word embeddings and their combination in order to take advantage of their complementarities. On the other hand, it focuses on acoustic word embeddings. Then, we present a study on the analysis of classification errors, with the aim of perceiving the errors that are difficult to detect. Perspectives for improving the performance of our system are also proposed, by modeling the errors at the sentence level. Finally, we exploit the linguistic and acoustic embeddings as well as the information provided by our ASR error detection system in several downstream applications.

La recherche d'informations s'intéresse, entre autres, à répondre à des questions comme: est-ce qu'un document est pertinent à une requête ? Est-ce que deux requêtes ou deux documents sont similaires ? Comment la similarité entre deux requêtes ou documents peut être utilisée pour améliorer l'estimation de la pertinence ? Pour donner réponse à ces questions, il est nécessaire d'associer chaque document et requête à des représentations interprétables par ordinateur. Une fois ces représentations estimées, la similarité peut correspondre, par exemple, à une distance ou une divergence qui opère dans l'espace de représentation. On admet généralement que la qualité d'une représentation a un impact direct sur l'erreur d'estimation par rapport à la vraie pertinence, jugée par un humain. Estimer de bonnes représentations des documents et des requêtes a longtemps été un problème central de la recherche d'informations. Le but de cette thèse est de proposer des nouvelles méthodes pour estimer les représentations des documents et des requêtes, la relation de pertinence entre eux et ainsi modestement avancer l'état de l'art du domaine. Nous présentons quatre articles publiés dans des conférences internationales et un article publié dans un forum d'évaluation. Les deux premiers articles concernent des méthodes qui créent l'espace de représentation selon une connaissance à priori sur les caractéristiques qui sont importantes pour la tâche à accomplir. Ceux-ci nous amènent à présenter un nouveau modèle de recherche d'informations qui diffère des modèles existants sur le plan théorique et de l'efficacité expérimentale. Les deux derniers articles marquent un changement fondamental dans l'approche de construction des représentations. Ils bénéficient notamment de l'intérêt de recherche dont les techniques d'apprentissage profond par réseaux de neurones, ou deep learning, ont fait récemment l'objet. Ces modèles d'apprentissage élicitent automatiquement les caractéristiques importantes pour la tâche demandée à partir d'une quantité importante de données. Nous nous intéressons à la modélisation des relations sémantiques entre documents et requêtes ainsi qu'entre deux ou plusieurs requêtes. Ces derniers articles marquent les premières applications de l'apprentissage de représentations par réseaux de neurones à la recherche d'informations. Les modèles proposés ont aussi produit une performance améliorée sur des collections de test standard. Nos travaux nous mènent à la conclusion générale suivante: la performance en recherche d'informations pourrait drastiquement être améliorée en se basant sur les approches d'apprentissage de représentations. / Information retrieval is generally concerned with answering questions such as: is this document relevant to this query? How similar are two queries or two documents? How query and document similarity can be used to enhance relevance estimation? In order to answer these questions, it is necessary to access computational representations of documents and queries. For example, similarities between documents and queries may correspond to a distance or a divergence defined on the representation space. It is generally assumed that the quality of the representation has a direct impact on the bias with respect to the true similarity, estimated by means of human intervention. Building useful representations for documents and queries has always been central to information retrieval research. The goal of this thesis is to provide new ways of estimating such representations and the relevance relationship between them. We present four articles that have been published in international conferences and one published in an information retrieval evaluation forum. The first two articles can be categorized as feature engineering approaches, which transduce a priori knowledge about the domain into the features of the representation. We present a novel retrieval model that compares favorably to existing models in terms of both theoretical originality and experimental effectiveness. The remaining two articles mark a significant change in our vision and originate from the widespread interest in deep learning research that took place during the time they were written. Therefore, they naturally belong to the category of representation learning approaches, also known as feature learning. Differently from previous approaches, the learning model discovers alone the most important features for the task at hand, given a considerable amount of labeled data. We propose to model the semantic relationships between documents and queries and between queries themselves. The models presented have also shown improved effectiveness on standard test collections. These last articles are amongst the first applications of representation learning with neural networks for information retrieval. This series of research leads to the following observation: future improvements of information retrieval effectiveness has to rely on representation learning techniques instead of manually defining the representation space.

Semantic parsing is the process of mapping a natural-language sentence into a machine-readable, formal representation of its meaning. The LSTM Encoder-Decoder is a neural architecture with the ability to map a source language into a target one. We are interested in the problem of mapping natural language into SPARQL queries, and we seek to contribute with strategies that do not rely on handcrafted rules, high-quality lexicons, manually-built templates or other handmade complex structures. In this context, we present two contributions to the problem of semantic parsing departing from the LSTM encoder-decoder. While natural language has well defined vector representation methods that use a very large volume of texts, formal languages, like SPARQL queries, suffer from lack of suitable methods for vector representation. In the first contribution we improve the representation of SPARQL vectors. We start by obtaining an alignment matrix between the two vocabularies, natural language and SPARQL terms, which allows us to refine a vectorial representation of SPARQL items. With this refinement we obtained better results in the posterior training for the semantic parsing model. In the second contribution we propose a neural architecture, that we call Encoder CFG-Decoder, whose output conforms to a given context-free grammar. Unlike the traditional LSTM encoder-decoder, our model provides a grammatical guarantee for the mapping process, which is particularly important for practical cases where grammatical errors can cause critical failures. Results confirm that any output generated by our model obeys the given CFG, and we observe a translation accuracy improvement when compared with other results from the literature. / A análise semântica é o processo de mapear uma sentença em linguagem natural para uma representação formal, interpretável por máquina, do seu significado. O LSTM Encoder-Decoder é uma arquitetura de rede neural com a capacidade de mapear uma sequência de origem para uma sequência de destino. Estamos interessados no problema de mapear a linguagem natural em consultas SPARQL e procuramos contribuir com estratégias que não dependam de regras artesanais, léxico de alta qualidade, modelos construídos manualmente ou outras estruturas complexas feitas à mão. Neste contexto, apresentamos duas contribuições para o problema de análise semântica partindo da arquitetura LSTM Encoder-Decoder. Enquanto para a linguagem natural existem métodos de representação vetorial bem definidos que usam um volume muito grande de textos, as linguagens formais, como as consultas SPARQL, sofrem com a falta de métodos adequados para representação vetorial. Na primeira contribuição, melhoramos a representação dos vetores SPARQL. Começamos obtendo uma matriz de alinhamento entre os dois vocabulários, linguagem natural e termos SPARQL, o que nos permite refinar uma representação vetorial dos termos SPARQL. Com esse refinamento, obtivemos melhores resultados no treinamento posterior para o modelo de análise semântica. Na segunda contribuição, propomos uma arquitetura neural, que chamamos de Encoder CFG-Decoder, cuja saída está de acordo com uma determinada gramática livre de contexto. Ao contrário do modelo tradicional LSTM Encoder-Decoder, nosso modelo fornece uma garantia gramatical para o processo de mapeamento, o que é particularmente importante para casos práticos nos quais erros gramaticais podem causar falhas críticas em um compilador ou interpretador. Os resultados confirmam que qualquer resultado gerado pelo nosso modelo obedece à CFG dada, e observamos uma melhora na precisão da tradução quando comparada com outros resultados da literatura.

Submitted by JOSIANE SANTOS DE OLIVEIRA (josianeso) on 2019-03-07T14:41:05Z No. of bitstreams: 1 Roger Alan Stein_.pdf: 476239 bytes, checksum: a87a32ffe84d0e5d7a882e0db7b03847 (MD5) / Made available in DSpace on 2019-03-07T14:41:05Z (GMT). No. of bitstreams: 1 Roger Alan Stein_.pdf: 476239 bytes, checksum: a87a32ffe84d0e5d7a882e0db7b03847 (MD5) Previous issue date: 2018-03-28 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Efficient distributed numerical word representation models (word embeddings) combined with modern machine learning algorithms have recently yielded considerable improvement on automatic document classification tasks. However, the effectiveness of such techniques has not been assessed for the hierarchical text classification (HTC) yet. This study investigates application of those models and algorithms on this specific problem by means of experimentation and analysis. Classification models were trained with prominent machine learning algorithm implementations—fastText, XGBoost, and Keras’ CNN—and noticeable word embeddings generation methods—GloVe, word2vec, and fastText—with publicly available data and evaluated them with measures specifically appropriate for the hierarchical context. FastText achieved an LCAF1 of 0.871 on a single-labeled version of the RCV1 dataset. The results analysis indicates that using word embeddings is a very promising approach for HTC. / Modelos eficientes de representação numérica textual (word embeddings) combinados com algoritmos modernos de aprendizado de máquina têm recentemente produzido uma melhoria considerável em tarefas de classificação automática de documentos. Contudo, a efetividade de tais técnicas ainda não foi avaliada com relação à classificação hierárquica de texto. Este estudo investiga a aplicação daqueles modelos e algoritmos neste problema em específico através de experimentação e análise. Modelos de classificação foram treinados usando implementações proeminentes de algoritmos de aprendizado de máquina—fastText, XGBoost e CNN (Keras)— e notórios métodos de geração de word embeddings—GloVe, word2vec e fastText—com dados disponíveis publicamente e avaliados usando métricas especificamente adequadas ao contexto hierárquico. Nesses experimentos, fastText alcançou um LCAF1 de 0,871 usando uma versão da base de dados RCV1 com apenas uma categoria por tupla. A análise dos resultados indica que a utilização de word embeddings é uma abordagem muito promissora para classificação hierárquica de texto.

<div>Biomedical data exists in the form of journal articles, research studies, electronic health records, care guidelines, etc. While text mining and natural language processing tools have been widely employed across various domains, these are just taking off in the healthcare space.</div><div><br></div><div>A primary hurdle that makes it difficult to build artificial intelligence models that use biomedical data, is the limited amount of labelled data available. Since most models rely on supervised or semi-supervised methods, generating large amounts of pre-processed labelled data that can be used for training purposes becomes extremely costly. Even for datasets that are labelled, the lack of normalization of biomedical concepts further affects the quality of results produced and limits the application to a restricted dataset. This affects reproducibility of the results and techniques across datasets, making it difficult to deploy research solutions to improve healthcare services.</div><div><br></div><div>The research presented in this thesis focuses on reducing the need to create labels for biomedical text mining by using unsupervised recurrent neural networks. The proposed method utilizes word embeddings to generate vector representations of biomedical concepts based on semantics and context. Experiments with unsupervised clustering of these biomedical concepts show that concepts that are similar to each other are clustered together. While this clustering captures different synonyms of the same concept, it also captures the similarities between various diseases and the symptoms that those diseases are symptomatic of.</div><div><br></div><div>To test the performance of the concept vectors on corpora of documents, a document vector generation method that utilizes these concept vectors is also proposed. The document vectors thus generated are used as an input to clustering algorithms, and the results show that across multiple corpora, the proposed methods of concept and document vector generation outperform the baselines and provide more meaningful clustering. The applications of this document clustering are huge, especially in the search and retrieval space, providing clinicians, researchers and patients more holistic and comprehensive results than relying on the exclusive term that they search for.</div><div><br></div><div>At the end, a framework for extracting clinical information that can be mapped to electronic health records from preventive care guidelines is presented. The extracted information can be integrated with the clinical decision support system of an electronic health record. A visualization tool to better understand and observe patient trajectories is also explored. Both these methods have potential to improve the preventive care services provided to patients.</div>

Spoken dialogue systems provide a natural conversational interface to computer applications. In recent years, the substantial improvements in the performance of speech recognition engines have helped shift the research focus to the next component of the dialogue system pipeline: the one in charge of language understanding. The role of this module is to translate user inputs into accurate representations of the user goal in the form that can be used by the system to interact with the underlying application. The challenges include the modelling of linguistic variation, speech recognition errors and the effects of dialogue context. Recently, the focus of language understanding research has moved to making use of word embeddings induced from large textual corpora using unsupervised methods. The work presented in this thesis demonstrates how these methods can be adapted to overcome the limitations of language understanding pipelines currently used in spoken dialogue systems. The thesis starts with a discussion of the pros and cons of language understanding models used in modern dialogue systems. Most models in use today are based on the delexicalisation paradigm, where exact string matching supplemented by a list of domain-specific rephrasings is used to recognise users' intents and update the system's internal belief state. This is followed by an attempt to use pretrained word vector collections to automatically induce domain-specific semantic lexicons, which are typically hand-crafted to handle lexical variation and account for a plethora of system failure modes. The results highlight the deficiencies of distributional word vectors which must be overcome to make them useful for downstream language understanding models. The thesis next shifts focus to overcoming the language understanding models' dependency on semantic lexicons. To achieve that, the proposed Neural Belief Tracking (NBT) model forsakes the use of standard one-hot n-gram representations used in Natural Language Processing in favour of distributed representations of user utterances, dialogue context and domain ontologies. The NBT model makes use of external lexical knowledge embedded in semantically specialised word vectors, obviating the need for domain-specific semantic lexicons. Subsequent work focuses on semantic specialisation, presenting an efficient method for injecting external lexical knowledge into word vector spaces. The proposed Attract-Repel algorithm boosts the semantic content of existing word vectors while simultaneously inducing high-quality cross-lingual word vector spaces. Finally, NBT models powered by specialised cross-lingual word vectors are used to train multilingual belief tracking models. These models operate across many languages at once, providing an efficient method for bootstrapping language understanding models for lower-resource languages with limited training data.