O treinamento de sistemas de Tradução de Máquina baseada em Estatística (TME) é bastante dependente da disponibilidade de corpora paralelos. Entretanto, este tipo de recurso costuma ser difícil de ser encontrado, especialmente quando lida com idiomas com poucos recursos ou com tópicos muito específicos, como, por exemplo, dermatologia. Para contornar esta situação, uma possibilidade é utilizar corpora comparáveis, que são recursos muito mais abundantes. Um modo de adquirir corpora comparáveis é a aplicação de algoritmos de Coleta Focada (CF). Neste trabalho, são propostas novas abordagens para CF, algumas baseadas em n-gramas e outras no poder expressivo das expressões multipalavra. Também são avaliadas a viabilidade do uso de CF para realização de adaptação de domínio para sistemas genéricos de TME e se há alguma correlação entre a qualidade dos algoritmos de CF e dos sistemas de TME que podem ser construídos a partir dos respectivos dados coletados. Os resultados indicam que algoritmos de CF podem ser bons meios para adquirir corpora comparáveis para realizar adaptação de domínio para TME e que há uma correlação entre a qualidade dos dois processos. / Statistical Machine Translation (SMT) is highly dependent on the availability of parallel corpora for training. However, these kinds of resource may be hard to be found, especially when dealing with under-resourced languages or very specific domains, like the dermatology. For working this situation around, one possibility is the use of comparable corpora, which are much more abundant resources. One way of acquiring comparable corpora is to apply Focused Crawling (FC) algorithms. In this work we propose novel approach for FC algorithms, some based on n-grams and other on the expressive power of multiword expressions. We also assess the viability of using FC for performing domain adaptations for generic SMT systems and whether there is a correlation between the quality of the FC algorithms and of the SMT systems that can be built with its collected data. Results indicate that the use of FCs is, indeed, a good way for acquiring comparable corpora for SMT domain adaptation and that there is a correlation between the qualities of both processes.

Remotely-sensed hyperspectral imagery has become one the most advanced tools for analyzing the processes that shape the Earth and other planets. Effective, rapid analysis of high-volume, high-dimensional hyperspectral image data sets demands efficient, automated techniques to identify signatures of known materials in such imagery. In this thesis, we develop a framework for automatic material identification in hyperspectral imagery using adaptive similarity measures. We frame the material identification problem as a multiclass similarity-based classification problem, where our goal is to predict material labels for unlabeled target spectra based upon their similarities to source spectra with known material labels. As differences in capture conditions affect the spectral representations of materials, we divide the material identification problem into intra-domain (i.e., source and target spectra captured under identical conditions) and inter-domain (i.e., source and target spectra captured under different conditions) settings. The first component of this thesis develops adaptive similarity measures for intra-domain settings that measure the relevance of spectral features to the given classification task using small amounts of labeled data. We propose a technique based on multiclass Linear Discriminant Analysis (LDA) that combines several distinct similarity measures into a single hybrid measure capturing the strengths of each of the individual measures. We also provide a comparative survey of techniques for low-rank Mahalanobis metric learning, and demonstrate that regularized LDA yields competitive results to the state-of-the-art, at substantially lower computational cost. The second component of this thesis shifts the focus to inter-domain settings, and proposes a multiclass domain adaptation framework that reconciles systematic differences between spectra captured under similar, but not identical, conditions. Our framework computes a similarity-based mapping that captures structured, relative relationships between classes shared between source and target domains, allowing us apply a classifier trained using labeled source spectra to classify target spectra. We demonstrate improved domain adaptation accuracy in comparison to recently-proposed multitask learning and manifold alignment techniques in several case studies involving state-of-the-art synthetic and real-world hyperspectral imagery.

Traditional supervised machine learning algorithms are expected to have access to a large corpus of labeled examples, but the massive amount of data available in the modern world has made unlabeled data much easier to acquire than accompanying labels. Active learning is an extension of the classical paradigm intended to lessen the expense of the labeling process by allowing the learning algorithm to intelligently choose which examples should be labeled. In this dissertation, we demonstrate that the power to make adaptive label queries has benefits beyond reducing labeling effort over passive learning. We develop and explore several novel methods for active learning that exemplify these new capabilities. Some of these methods use active learning for a non-standard purpose, such as computational speedup, structure discovery, and domain adaptation. Others successfully apply active learning in situations where prior results have given evidence of its ineffectiveness. Specifically, we first give an active algorithm for learning disjunctions that is able to overcome a computational intractability present in the semi-supervised version of the same problem. This is the first known example of the computational advantages of active learning. Next, we investigate using active learning to determine structural properties (margins) of the data-generating distribution that can further improve learning rates. This is in contrast to most active learning algorithms which either assume or ignore structure rather than seeking to identify and exploit it. We then give an active nearest neighbors algorithm for domain adaptation, the task of learning a predictor for some target domain using mostly examples from a different source domain. This is the first formal analysis of the generalization and query behavior of an active domain adaptation algorithm. Finally, we show a situation where active learning can outperform passive learning on very noisy data, circumventing prior results that active learning cannot have a significant advantage over passive learning in high-noise regimes.

Master of Science / Department of Computer Science / Doina Caragea / Huge amounts of data that are generated on social media during emergency situations are regarded as troves of critical information. The use of supervised machine learning techniques in the early stages of a disaster is challenged by the lack of labeled data for that particular disaster. Furthermore, supervised models trained on labeled data from a prior disaster may not produce accurate results. To address these challenges, domain adaptation approaches, which learn models for predicting the target, by using unlabeled data from the target disaster in addition to labeled data from prior source disasters, can be used. However, the resulting models can still be affected by the variance between the target domain and the source domain. In this context, we propose to use a hybrid feature-instance adaptation approach based on matrix factorization and the k-nearest neighbors algorithm, respectively. The proposed hybrid adaptation approach is used to select a subset of the source disaster data that is representative of the target disaster. The selected subset is subsequently used to learn accurate supervised or domain adaptation Naïve Bayes classifiers for the target disaster. In other words, this study focuses on transforming the existing source data to bring it closer to the target data, thus overcoming the domain variance which may prevent effective transfer of information from source to target. A combination of selective and transformative methods are used on instances and features, respectively. We show experimentally that the proposed approaches are effective in transferring information from source to target. Furthermore, we provide insights with respect to what types and combinations of selections/transformations result in more accurate models for the target.

O treinamento de sistemas de Tradução de Máquina baseada em Estatística (TME) é bastante dependente da disponibilidade de corpora paralelos. Entretanto, este tipo de recurso costuma ser difícil de ser encontrado, especialmente quando lida com idiomas com poucos recursos ou com tópicos muito específicos, como, por exemplo, dermatologia. Para contornar esta situação, uma possibilidade é utilizar corpora comparáveis, que são recursos muito mais abundantes. Um modo de adquirir corpora comparáveis é a aplicação de algoritmos de Coleta Focada (CF). Neste trabalho, são propostas novas abordagens para CF, algumas baseadas em n-gramas e outras no poder expressivo das expressões multipalavra. Também são avaliadas a viabilidade do uso de CF para realização de adaptação de domínio para sistemas genéricos de TME e se há alguma correlação entre a qualidade dos algoritmos de CF e dos sistemas de TME que podem ser construídos a partir dos respectivos dados coletados. Os resultados indicam que algoritmos de CF podem ser bons meios para adquirir corpora comparáveis para realizar adaptação de domínio para TME e que há uma correlação entre a qualidade dos dois processos. / Statistical Machine Translation (SMT) is highly dependent on the availability of parallel corpora for training. However, these kinds of resource may be hard to be found, especially when dealing with under-resourced languages or very specific domains, like the dermatology. For working this situation around, one possibility is the use of comparable corpora, which are much more abundant resources. One way of acquiring comparable corpora is to apply Focused Crawling (FC) algorithms. In this work we propose novel approach for FC algorithms, some based on n-grams and other on the expressive power of multiword expressions. We also assess the viability of using FC for performing domain adaptations for generic SMT systems and whether there is a correlation between the quality of the FC algorithms and of the SMT systems that can be built with its collected data. Results indicate that the use of FCs is, indeed, a good way for acquiring comparable corpora for SMT domain adaptation and that there is a correlation between the qualities of both processes.

Master of Science / Department of Computer Science / Doina Caragea / Twitter is one of the most active social media sites today. Almost everyone is using it, as it is a medium by which people stay in touch and inform others about events in their lives. Among many other types of events, people tweet about disaster events. Both man made and natural disasters, unfortunately, occur all the time. When these tragedies transpire, people tend to cope in their own ways. One of the most popular ways people convey their feelings towards disaster events is by offering or asking for support, providing valuable information about the disaster, and voicing their disapproval towards those who may be the cause. However, not all of the tweets posted during a disaster are guaranteed to be useful or informative to authorities nor to the general public. As the number of tweets that are posted during a disaster can reach the hundred thousands range, it is necessary to automatically distinguish tweets that provide useful information from those that don't. Manual annotation cannot scale up to the large number of tweets, as it takes significant time and effort, which makes it unsuitable for real-time disaster tweet annotation. Alternatively, supervised machine learning has been traditionally used to learn classifiers that can quickly annotate new unseen tweets. But supervised machine learning algorithms make use of labeled training data from the disaster of interest, which is presumably not available for a current target disaster. However, it is reasonable to assume that some amount of labeled data is available for a prior source disaster. Therefore, domain adaptation algorithms that make use of labeled data from a source disaster to learn classifiers for the target disaster provide a promising direction in the area of tweet classification for disaster management. In prior work, domain adaptation algorithms have been trained based on tweets represented as bag-of-words. In this research, I studied the effect of Part of Speech (POS) tag unigrams and bigrams on the performance of the domain adaptation classifiers. Specifically, I used POS tag unigram and bigram features in conjunction with a Naive Bayes Domain Adaptation algorithm to learn classifiers from source labeled data together with target unlabeled data, and subsequently used the resulting classifiers to classify target disaster tweets. The main research question addressed through this work was if the POS tags can help improve the performance of the classifiers learned from tweet bag-of-words representations only. Experimental results have shown that the POS tags can improve the performance of the classifiers learned from words only, but not always. Furthermore, the results of the experiments show that POS tag bigrams contain more information as compared to POS tag unigrams, as the classifiers learned from bigrams have better performance than those learned from unigrams.

abstract: The widespread adoption of computer vision models is often constrained by the issue of domain mismatch. Models that are trained with data belonging to one distribution, perform poorly when tested with data from a different distribution. Variations in vision based data can be attributed to the following reasons, viz., differences in image quality (resolution, brightness, occlusion and color), changes in camera perspective, dissimilar backgrounds and an inherent diversity of the samples themselves. Machine learning techniques like transfer learning are employed to adapt computational models across distributions. Domain adaptation is a special case of transfer learning, where knowledge from a source domain is transferred to a target domain in the form of learned models and efficient feature representations. The dissertation outlines novel domain adaptation approaches across different feature spaces; (i) a linear Support Vector Machine model for domain alignment; (ii) a nonlinear kernel based approach that embeds domain-aligned data for enhanced classification; (iii) a hierarchical model implemented using deep learning, that estimates domain-aligned hash values for the source and target data, and (iv) a proposal for a feature selection technique to reduce cross-domain disparity. These adaptation procedures are tested and validated across a range of computer vision applications like object classification, facial expression recognition, digit recognition, and activity recognition. The dissertation also provides a unique perspective of domain adaptation literature from the point-of-view of linear, nonlinear and hierarchical feature spaces. The dissertation concludes with a discussion on the future directions for research that highlight the role of domain adaptation in an era of rapid advancements in artificial intelligence. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2017

abstract: Machine learning models convert raw data in the form of video, images, audio, text, etc. into feature representations that are convenient for computational process- ing. Deep neural networks have proven to be very efficient feature extractors for a variety of machine learning tasks. Generative models based on deep neural networks introduce constraints on the feature space to learn transferable and disentangled rep- resentations. Transferable feature representations help in training machine learning models that are robust across different distributions of data. For example, with the application of transferable features in domain adaptation, models trained on a source distribution can be applied to a data from a target distribution even though the dis- tributions may be different. In style transfer and image-to-image translation, disen- tangled representations allow for the separation of style and content when translating images. This thesis examines learning transferable data representations in novel deep gen- erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar- ial methods and cross-domain weight sharing in a neural network to extract trans- ferable representations. These transferable interpretations can then be decoded into the original image or a similar image in another domain. The Explicit Disentangling Network (EDN) utilizes generative methods to disentangle images into their core at- tributes and then segments sets of related attributes. The EDN can separate these attributes by controlling the ow of information using a novel combination of losses and network architecture. This separation of attributes allows precise modi_cations to speci_c components of the data representation, boosting the performance of ma- chine learning tasks. The effectiveness of these models is evaluated across domain adaptation, style transfer, and image-to-image translation tasks. / Dissertation/Thesis / Masters Thesis Computer Science 2018

Deep understanding of urban mobility is of great significance for many real-world applications, such as urban traffic management and autonomous driving. This thesis develops deep learning methodologies to extract vehicle counts from streaming realtime video captured by multiple low resolution web cameras and construct maps of traffic density in a city environment; in particular, we focus on cameras installed in the Manhattan borough of NYC. The large-scale videos from these web cameras have low spatial and temporal resolution, high occlusion, large perspective, and variable environment conditions, making most existing methods to lose their efficacy. To overcome these challenges, the thesis develops several techniques: 1. a block-level regression model with a rank constraint to map the dense image feature into vehicle densities; 2. a deep multi-task learning framework based on fully convolutional neural networks to jointly learn vehicle density and vehicle count; 3. deep spatio-temporal networks for vehicle counting to incorporate temporal information of the traffic flow; and 4. multi-source domain adaptation mechanisms with adversarial learning to adapt the deep counting model to multiple cameras. To train and validate the proposed system, we have collected a largescale webcam traffic dataset CityCam that contains 60 million frames from 212 webcams installed in key intersections of NYC. Of there, 60; 000 frames have been annotated with rich information, leading to about 900; 000 annotated objects. To the best of our knowledge, it is the first and largest webcam traffic dataset with such large number of elaborate annotations. The proposed methods are integrated into the CityScapeEye system that has been extensively evaluated and compared to existing techniques on different counting tasks and datasets, with experimental results demonstrating the effectiveness and robustness of CityScapeEye.

O treinamento de sistemas de Tradução de Máquina baseada em Estatística (TME) é bastante dependente da disponibilidade de corpora paralelos. Entretanto, este tipo de recurso costuma ser difícil de ser encontrado, especialmente quando lida com idiomas com poucos recursos ou com tópicos muito específicos, como, por exemplo, dermatologia. Para contornar esta situação, uma possibilidade é utilizar corpora comparáveis, que são recursos muito mais abundantes. Um modo de adquirir corpora comparáveis é a aplicação de algoritmos de Coleta Focada (CF). Neste trabalho, são propostas novas abordagens para CF, algumas baseadas em n-gramas e outras no poder expressivo das expressões multipalavra. Também são avaliadas a viabilidade do uso de CF para realização de adaptação de domínio para sistemas genéricos de TME e se há alguma correlação entre a qualidade dos algoritmos de CF e dos sistemas de TME que podem ser construídos a partir dos respectivos dados coletados. Os resultados indicam que algoritmos de CF podem ser bons meios para adquirir corpora comparáveis para realizar adaptação de domínio para TME e que há uma correlação entre a qualidade dos dois processos. / Statistical Machine Translation (SMT) is highly dependent on the availability of parallel corpora for training. However, these kinds of resource may be hard to be found, especially when dealing with under-resourced languages or very specific domains, like the dermatology. For working this situation around, one possibility is the use of comparable corpora, which are much more abundant resources. One way of acquiring comparable corpora is to apply Focused Crawling (FC) algorithms. In this work we propose novel approach for FC algorithms, some based on n-grams and other on the expressive power of multiword expressions. We also assess the viability of using FC for performing domain adaptations for generic SMT systems and whether there is a correlation between the quality of the FC algorithms and of the SMT systems that can be built with its collected data. Results indicate that the use of FCs is, indeed, a good way for acquiring comparable corpora for SMT domain adaptation and that there is a correlation between the qualities of both processes.