Du point de vue du traitement automatique des langues (TAL), l’extraction des événements dans les textes est la forme la plus complexe des processus d’extraction d’information, qui recouvrent de façon plus générale l’extraction des entités nommées et des relations qui les lient dans les textes. Le cas des événements est particulièrement ardu car un événement peut être assimilé à une relation n-aire ou à une configuration de relations. Alors que la recherche en extraction d’information a largement bénéficié des jeux de données étiquetés manuellement pour apprendre des modèles permettant l’analyse des textes, la disponibilité de ces ressources reste un problème important. En outre, de nombreuses approches en extraction d’information fondées sur l’apprentissage automatique reposent sur la possibilité d’extraire à partir des textes de larges en sembles de traits définis manuellement grâce à des outils de TAL élaborés. De ce fait, l’adaptation à un nouveau domaine constitue un défi supplémentaire. Cette thèse présente plusieurs stratégies pour améliorer la performance d’un système d’extraction d’événements en utilisant des approches fondées sur les réseaux de neurones et en exploitant les propriétés morphologiques, syntaxiques et sémantiques des plongements de mots. Ceux-ci ont en effet l’avantage de ne pas nécessiter une modélisation a priori des connaissances du domaine et de générer automatiquement un ensemble de traits beaucoup plus vaste pour apprendre un modèle. Nous avons proposé plus spécifiquement différents modèles d’apprentissage profond pour les deux sous-tâches liées à l’extraction d’événements : la détection d’événements et la détection d’arguments. La détection d’événements est considérée comme une sous-tâche importante de l’extraction d’événements dans la mesure où la détection d’arguments est très directement dépendante de son résultat. La détection d’événements consiste plus précisément à identifier des instances d’événements dans les textes et à les classer en types d’événements précis. En préalable à l’introduction de nos nouveaux modèles, nous commençons par présenter en détail le modèle de l’état de l’art qui en constitue la base. Des expériences approfondies sont menées sur l’utilisation de différents types de plongements de mots et sur l’influence des différents hyperparamètres du modèle en nous appuyant sur le cadre d’évaluation ACE 2005, standard d’évaluation pour cette tâche. Nous proposons ensuite deux nouveaux modèles permettant d’améliorer un système de détection d’événements. L’un permet d’augmenter le contexte pris en compte lors de la prédiction d’une instance d’événement (déclencheur d’événement) en utilisant un contexte phrastique, tandis que l’autre exploite la structure interne des mots en profitant de connaissances morphologiques en apparence moins nécessaires mais dans les faits importantes. Nous proposons enfin de reconsidérer la détection des arguments comme une extraction de relation d’ordre supérieur et nous analysons la dépendance de cette détection vis-à-vis de la détection d’événements. / With the increasing amount of data and the exploding number data sources, the extraction of information about events, whether from the perspective of acquiring knowledge or from a more directly operational perspective, becomes a more and more obvious need. This extraction nevertheless comes up against a recurring difficulty: most of the information is present in documents in a textual form, thus unstructured and difficult to be grasped by the machine. From the point of view of Natural Language Processing (NLP), the extraction of events from texts is the most complex form of Information Extraction (IE) techniques, which more generally encompasses the extraction of named entities and relationships that bind them in the texts. The event extraction task can be represented as a complex combination of relations linked to a set of empirical observations from texts. Compared to relations involving only two entities, there is, therefore, a new dimension that often requires going beyond the scope of the sentence, which constitutes an additional difficulty. In practice, an event is described by a trigger and a set of participants in that event whose values are text excerpts. While IE research has benefited significantly from manually annotated datasets to learn patterns for text analysis, the availability of these resources remains a significant problem. These datasets are often obtained through the sustained efforts of research communities, potentially complemented by crowdsourcing. In addition, many machine learning-based IE approaches rely on the ability to extract large sets of manually defined features from text using sophisticated NLP tools. As a result, adaptation to a new domain is an additional challenge. This thesis presents several strategies for improving the performance of an Event Extraction (EE) system using neural-based approaches exploiting morphological, syntactic, and semantic properties of word embeddings. These have the advantage of not requiring a priori modeling domain knowledge and automatically generate a much larger set of features to learn a model. More specifically, we proposed different deep learning models for two sub-tasks related to EE: event detection and argument detection and classification. Event Detection (ED) is considered an important subtask of event extraction since the detection of arguments is very directly dependent on its outcome. ED specifically involves identifying instances of events in texts and classifying them into specific event types. Classically, the same event may appear as different expressions and these expressions may themselves represent different events in different contexts, hence the difficulty of the task. The detection of the arguments is based on the detection of the expression considered as triggering the event and ensures the recognition of the participants of the event. Among the difficulties to take into account, it should be noted that an argument can be common to several events and that it does not necessarily identify with an easily recognizable named entity. As a preliminary to the introduction of our proposed models, we begin by presenting in detail a state-of-the-art model which constitutes the baseline. In-depth experiments are conducted on the use of different types of word embeddings and the influence of the different hyperparameters of the model using the ACE 2005 evaluation framework, a standard evaluation for this task. We then propose two new models to improve an event detection system. One allows increasing the context taken into account when predicting an event instance by using a sentential context, while the other exploits the internal structure of words by taking advantage of seemingly less obvious but essentially important morphological knowledge. We also reconsider the detection of arguments as a high-order relation extraction and we analyze the dependence of arguments on the ED task.

Word embeddings are utilized in various natural language processing tasks. Although effective in helping computers learn linguistic patterns employed in natural language, word embeddings also tend to learn unwanted word associations. This affects the performance of NLP tasks, as unwanted word associations propagate and amplify biases. Current word association evaluation methods for word embeddings do not account for changes in word embedding models and training corpora, when creating the rubric for word association evaluation. Current literature also lacks a consistent training and evaluation protocol for comparison of word associations across varying word embedding models and varying training corpora. In order to address this gap in prior literature, this research aims to evaluate different types of word associations, not limited to gender, racial or religious attributes, incorporating and evaluating the diachronic and variable nature of words over text data collected over a period of 200 years. This thesis introduces a framework to track changes in word associations between neutral words (proper nouns) and attributes (adjectives), across different word embedding models, over a temporal dimension, by evaluating clustering tendencies between neutral words (proper nouns) and attributive words (adjectives) over five different word embedding frameworks: Word2vec (CBOW), Word2vec (Skip-gram), GloVe, fastText (CBOW) and fastText (Skip-gram) and 20 decades of text data from 1810s to 2000s. <a>Finally, various cluster level and corpus level measurements will be compared across aforementioned word embedding frameworks, to find how</a> word associations evolve with changes in the embedding model and the training corpus.

Word embeddings are useful in many tasks in Natural Language Processing and Information Retrieval, such as text mining and classification, sentiment analysis, sentence completion, or dictionary construction. Word2vec and its predecessor fastText, both well-known models to produce word embeddings, are powerful techniques to study the syntactic and semantic relations between words by representing them in a low-dimensional vector. By applying algebraic operations on these vectors semantic relationships such as word analogies, gender-inflections, or geographical relationships can be easily recovered. The aim of this work is to investigate how word embeddings could be utilized to augment and enrich queries in DBMSs, e.g. to compare text values according to their semantic relation or to group rows according to the similarity of their text values. For this purpose, we use pre-trained word embedding models of large text corpora such as Wikipedia. By exploiting this external knowledge during query processing we are able to apply inductive reasoning on text values. Thereby, we reduce the demand for explicit knowledge in database systems. In the context of the IMDB database schema, this allows for example to query movies that are semantically close to genres such as historical fiction or road movie without maintaining this information. Another example query is sketched in Listing 1, that returns the top-3 nearest neighbors (NN) of each movie in IMDB. Given the movie “Godfather” as input this results in “Scarface”, “Goodfellas” and “Untouchables”.

This work focuses on the design of a system that identifies frequently discussed product features in product reviews, summarizes them, and displays them to the user in terms of sentiment. The work deals with the issue of natural language processing, with a specific focus on Czech languague. The reader will be introduced the methods of preprocessing the text and their impact on the quality of the analysis results. The identification of the mainly discussed products features is carried out by cluster analysis using the K-Means algorithm, where we assume that sufficiently internally homogeneous clusters will represent the individual features of the products. A new area that will be explored in this work is the representation of documents using the Word embeddings technique, and its potential of using vector space as input for machine learning algorithms.

The creation of word embeddings is one of the key breakthroughs in natural language processing. Word embeddings allow for words to be represented semantically, opening the way to many new deep learning methods. Understanding what information is in word embeddings will help understanding the behaviour of embeddings in natural language processing tasks, but also allows for the quantitative study of the linguistic features such as grammatical gender. This thesis attempts to explore how grammatical gender is encoded in word embeddings, through analysing the performance of a neural network classifier on the classification of nouns by gender. This analysis is done in three experiments: an analysis of contextualized embeddings, an analysis of embeddings learned from modified corpora and an analysis of aligned embeddings in many languages. The contextualized word embedding model ELMo has multiple output layers with a gradual increasing presence of semantic information in the embedding. This differing presence of semantic information was used to test the classifier's reliance on semantic information. Swedish, German, Spanish and Russian embeddings were classified at all layers of a three layered ELMo model. The word representation layer without any contextualization was found to produce the best accuracy, indicating the noise introduced by the contextualization was more impactful than any potential extra semantic information. Swedish embeddings were learned from a corpus stripped of articles and a stemmed corpus. Both sets of embeddings showed an drop of about 6% in accuracy in comparison with the embeddings from a non-augmented corpus, indicating agreement plays a large role in the classification. Aligned multilingual embeddings were used to measure the accuracy of a grammatical gender classifier in 24 languages. The classifier models were applied to data of other languages to determine the similarity of the encoding of grammatical gender in these embeddings. Correcting the results with a random guessing baseline shows that transferred models can be highly accurate in certain language combinations and in some cases almost approach the accuracy of the model on its source data. A comparison between transfer accuracy and phylogenetic distance showed that the model transferability follows a pattern that resembles the phylogenetic distance.

Les plongements lexicaux sont un composant standard des architectures modernes de traitement automatique des langues (TAL). Chaque fois qu'une avancée est obtenue dans l'apprentissage de plongements lexicaux, la grande majorité des tâches de traitement automatique des langues, telles que l'étiquetage morphosyntaxique, la reconnaissance d'entités nommées, la recherche de réponses à des questions, ou l'inférence textuelle, peuvent en bénéficier. Ce travail explore la question de l'amélioration de la qualité de plongements lexicaux monolingues appris par des modèles prédictifs et celle de la mise en correspondance entre langues de plongements lexicaux contextuels créés par des modèles préentraînés de représentation de la langue comme ELMo ou BERT.Pour l'apprentissage de plongements lexicaux monolingues, je prends en compte des informations globales au corpus et génère une distribution de bruit différente pour l'échantillonnage d'exemples négatifs dans word2vec. Dans ce but, je précalcule des statistiques de cooccurrence entre mots avec corpus2graph, un paquet Python en source ouverte orienté vers les applications en TAL : il génère efficacement un graphe de cooccurrence à partir d'un grand corpus, et lui applique des algorithmes de graphes tels que les marches aléatoires. Pour la mise en correspondance translingue de plongements lexicaux, je relie les plongements lexicaux contextuels à des plongements de sens de mots. L'algorithme amélioré de création d'ancres que je propose étend également la portée des algorithmes de mise en correspondance de plongements lexicaux du cas non-contextuel au cas des plongements contextuels. / Word embeddings are a standard component of modern natural language processing architectures. Every time there is a breakthrough in word embedding learning, the vast majority of natural language processing tasks, such as POS-tagging, named entity recognition (NER), question answering, natural language inference, can benefit from it. This work addresses the question of how to improve the quality of monolingual word embeddings learned by prediction-based models and how to map contextual word embeddings generated by pretrained language representation models like ELMo or BERT across different languages.For monolingual word embedding learning, I take into account global, corpus-level information and generate a different noise distribution for negative sampling in word2vec. In this purpose I pre-compute word co-occurrence statistics with corpus2graph, an open-source NLP-application-oriented Python package that I developed: it efficiently generates a word co-occurrence network from a large corpus, and applies to it network algorithms such as random walks. For cross-lingual contextual word embedding mapping, I link contextual word embeddings to word sense embeddings. The improved anchor generation algorithm that I propose also expands the scope of word embedding mapping algorithms from context independent to contextual word embeddings.

Indiana University-Purdue University Indianapolis (IUPUI) / 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. 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. 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. 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. 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.

An event is something that happens at a time and location. Events include major life events such as graduating college or getting married, and also simple day-to-day activities such as commuting to work or eating lunch. Most work on event extraction detects events and the entities involved in events. For example, cooking events will usually involve a cook, some utensils and appliances, and a final product. In this work, we target the task of determining whether events result in their expected outcomes. Specifically, we target cooking and baking events, and characterize event outcomes into two categories. First, we distinguish whether something edible resulted from the event. Second, if something edible resulted, we distinguish between perfect, partial and alternative outcomes. The main contributions of this thesis are a corpus of 4,000 tweets annotated with event outcome information and experimental results showing that the task can be automated. The corpus includes tweets that have only text as well as tweets that have text and an image.

No description available.

No description available.