Paper Group ANR 884
Inferring Political Alignments of Twitter Users: A case study on 2017 Turkish constitutional referendum. Polarity and Intensity: the Two Aspects of Sentiment Analysis. META-DES.Oracle: Meta-learning and feature selection for ensemble selection. Sparse Blind Deconvolution for Distributed Radar Autofocus Imaging. Hierarchy-based Image Embeddings for …
Inferring Political Alignments of Twitter Users: A case study on 2017 Turkish constitutional referendum
Title | Inferring Political Alignments of Twitter Users: A case study on 2017 Turkish constitutional referendum |
Authors | Kutlu Emre Yilmaz, Osman Abul |
Abstract | Increasing popularity of Twitter in politics is subject to commercial and academic interest. To fully exploit the merits of this platform, reaching the target audience with desired political leanings is critical. This paper extends the research on inferring political orientations of Twitter users to the case of 2017 Turkish constitutional referendum. After constructing a targeted dataset of tweets, we explore several types of potential features to build accurate machine learning based predictive models. In our experiments, a three-class support vector machine (SVM) classifier trained on semantic features achieves the best accuracy score of 89.9%. Moreover, an SVM classifier trained on full-text features performs better than an SVM classifier trained on hashtags, with respective accuracy scores of 89.05% and 85.9%. Relatively high accuracy scores obtained by full-text features may point to differences in language use, which deserves further research. |
Tasks | |
Published | 2018-09-15 |
URL | http://arxiv.org/abs/1809.05699v1 |
http://arxiv.org/pdf/1809.05699v1.pdf | |
PWC | https://paperswithcode.com/paper/inferring-political-alignments-of-twitter |
Repo | |
Framework | |
Polarity and Intensity: the Two Aspects of Sentiment Analysis
Title | Polarity and Intensity: the Two Aspects of Sentiment Analysis |
Authors | Leimin Tian, Catherine Lai, Johanna D. Moore |
Abstract | Current multimodal sentiment analysis frames sentiment score prediction as a general Machine Learning task. However, what the sentiment score actually represents has often been overlooked. As a measurement of opinions and affective states, a sentiment score generally consists of two aspects: polarity and intensity. We decompose sentiment scores into these two aspects and study how they are conveyed through individual modalities and combined multimodal models in a naturalistic monologue setting. In particular, we build unimodal and multimodal multi-task learning models with sentiment score prediction as the main task and polarity and/or intensity classification as the auxiliary tasks. Our experiments show that sentiment analysis benefits from multi-task learning, and individual modalities differ when conveying the polarity and intensity aspects of sentiment. |
Tasks | Multimodal Sentiment Analysis, Multi-Task Learning, Sentiment Analysis |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01466v1 |
http://arxiv.org/pdf/1807.01466v1.pdf | |
PWC | https://paperswithcode.com/paper/polarity-and-intensity-the-two-aspects-of |
Repo | |
Framework | |
META-DES.Oracle: Meta-learning and feature selection for ensemble selection
Title | META-DES.Oracle: Meta-learning and feature selection for ensemble selection |
Authors | Rafael M. O Cruz, Robert Sabourin, George D. C. Cavalcanti |
Abstract | The key issue in Dynamic Ensemble Selection (DES) is defining a suitable criterion for calculating the classifiers’ competence. There are several criteria available to measure the level of competence of base classifiers, such as local accuracy estimates and ranking. However, using only one criterion may lead to a poor estimation of the classifier’s competence. In order to deal with this issue, we have proposed a novel dynamic ensemble selection framework using meta-learning, called META-DES. An important aspect of the META-DES framework is that multiple criteria can be embedded in the system encoded as different sets of meta-features. However, some DES criteria are not suitable for every classification problem. For instance, local accuracy estimates may produce poor results when there is a high degree of overlap between the classes. Moreover, a higher classification accuracy can be obtained if the performance of the meta-classifier is optimized for the corresponding data. In this paper, we propose a novel version of the META-DES framework based on the formal definition of the Oracle, called META-DES.Oracle. The Oracle is an abstract method that represents an ideal classifier selection scheme. A meta-feature selection scheme using an overfitting cautious Binary Particle Swarm Optimization (BPSO) is proposed for improving the performance of the meta-classifier. The difference between the outputs obtained by the meta-classifier and those presented by the Oracle is minimized. Thus, the meta-classifier is expected to obtain results that are similar to the Oracle. Experiments carried out using 30 classification problems demonstrate that the optimization procedure based on the Oracle definition leads to a significant improvement in classification accuracy when compared to previous versions of the META-DES framework and other state-of-the-art DES techniques. |
Tasks | Feature Selection, Meta-Learning |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00217v1 |
http://arxiv.org/pdf/1811.00217v1.pdf | |
PWC | https://paperswithcode.com/paper/meta-desoracle-meta-learning-and-feature |
Repo | |
Framework | |
Sparse Blind Deconvolution for Distributed Radar Autofocus Imaging
Title | Sparse Blind Deconvolution for Distributed Radar Autofocus Imaging |
Authors | Hassan Mansour, Dehong Liu, Ulugbek S. Kamilov, Petros T. Boufounos |
Abstract | A common problem that arises in radar imaging systems, especially those mounted on mobile platforms, is antenna position ambiguity. Approaches to resolve this ambiguity and correct position errors are generally known as radar autofocus. Common techniques that attempt to resolve the antenna ambiguity generally assume an unknown gain and phase error afflicting the radar measurements. However, ensuring identifiability and tractability of the unknown error imposes strict restrictions on the allowable antenna perturbations. Furthermore, these techniques are often not applicable in near-field imaging, where mapping the position ambiguity to phase errors breaks down. In this paper, we propose an alternate formulation where the position error of each antenna is mapped to a spatial shift operator in the image-domain. Thus, the radar autofocus problem becomes a multichannel blind deconvolution problem, in which the radar measurements correspond to observations of a static radar image that is convolved with the spatial shift kernel associated with each antenna. To solve the reformulated problem, we also develop a block coordinate descent framework that leverages the sparsity and piece-wise smoothness of the radar scene, as well as the one-sparse property of the two dimensional shift kernels. We evaluate the performance of our approach using both simulated and experimental radar measurements, and demonstrate its superior performance compared to state-of-the-art methods. |
Tasks | |
Published | 2018-05-08 |
URL | http://arxiv.org/abs/1805.03269v1 |
http://arxiv.org/pdf/1805.03269v1.pdf | |
PWC | https://paperswithcode.com/paper/sparse-blind-deconvolution-for-distributed |
Repo | |
Framework | |
Hierarchy-based Image Embeddings for Semantic Image Retrieval
Title | Hierarchy-based Image Embeddings for Semantic Image Retrieval |
Authors | Björn Barz, Joachim Denzler |
Abstract | Deep neural networks trained for classification have been found to learn powerful image representations, which are also often used for other tasks such as comparing images w.r.t. their visual similarity. However, visual similarity does not imply semantic similarity. In order to learn semantically discriminative features, we propose to map images onto class embeddings whose pair-wise dot products correspond to a measure of semantic similarity between classes. Such an embedding does not only improve image retrieval results, but could also facilitate integrating semantics for other tasks, e.g., novelty detection or few-shot learning. We introduce a deterministic algorithm for computing the class centroids directly based on prior world-knowledge encoded in a hierarchy of classes such as WordNet. Experiments on CIFAR-100, NABirds, and ImageNet show that our learned semantic image embeddings improve the semantic consistency of image retrieval results by a large margin. |
Tasks | Few-Shot Learning, Image Retrieval, Semantic Similarity, Semantic Textual Similarity |
Published | 2018-09-26 |
URL | http://arxiv.org/abs/1809.09924v4 |
http://arxiv.org/pdf/1809.09924v4.pdf | |
PWC | https://paperswithcode.com/paper/hierarchy-based-image-embeddings-for-semantic |
Repo | |
Framework | |
Practical Obstacles to Deploying Active Learning
Title | Practical Obstacles to Deploying Active Learning |
Authors | David Lowell, Zachary C. Lipton, Byron C. Wallace |
Abstract | Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is most uncertain (by some measure). The hope is that active sampling leads to better performance than would be achieved under independent and identically distributed (i.i.d.) random samples. While AL has shown promise in retrospective evaluations, these studies often ignore practical obstacles to its use. In this paper we show that while AL may provide benefits when used with specific models and for particular domains, the benefits of current approaches do not generalize reliably across models and tasks. This is problematic because in practice one does not have the opportunity to explore and compare alternative AL strategies. Moreover, AL couples the training dataset with the model used to guide its acquisition. We find that subsequently training a successor model with an actively-acquired dataset does not consistently outperform training on i.i.d. sampled data. Our findings raise the question of whether the downsides inherent to AL are worth the modest and inconsistent performance gains it tends to afford. |
Tasks | Active Learning, Text Classification |
Published | 2018-07-12 |
URL | https://arxiv.org/abs/1807.04801v3 |
https://arxiv.org/pdf/1807.04801v3.pdf | |
PWC | https://paperswithcode.com/paper/how-transferable-are-the-datasets-collected |
Repo | |
Framework | |
Semantic Parsing with Syntax- and Table-Aware SQL Generation
Title | Semantic Parsing with Syntax- and Table-Aware SQL Generation |
Authors | Yibo Sun, Duyu Tang, Nan Duan, Jianshu Ji, Guihong Cao, Xiaocheng Feng, Bing Qin, Ting Liu, Ming Zhou |
Abstract | We present a generative model to map natural language questions into SQL queries. Existing neural network based approaches typically generate a SQL query word-by-word, however, a large portion of the generated results are incorrect or not executable due to the mismatch between question words and table contents. Our approach addresses this problem by considering the structure of table and the syntax of SQL language. The quality of the generated SQL query is significantly improved through (1) learning to replicate content from column names, cells or SQL keywords; and (2) improving the generation of WHERE clause by leveraging the column-cell relation. Experiments are conducted on WikiSQL, a recently released dataset with the largest question-SQL pairs. Our approach significantly improves the state-of-the-art execution accuracy from 69.0% to 74.4%. |
Tasks | Semantic Parsing |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08338v1 |
http://arxiv.org/pdf/1804.08338v1.pdf | |
PWC | https://paperswithcode.com/paper/semantic-parsing-with-syntax-and-table-aware |
Repo | |
Framework | |
Non-Gaussian Component Analysis using Entropy Methods
Title | Non-Gaussian Component Analysis using Entropy Methods |
Authors | Navin Goyal, Abhishek Shetty |
Abstract | Non-Gaussian component analysis (NGCA) is a problem in multidimensional data analysis which, since its formulation in 2006, has attracted considerable attention in statistics and machine learning. In this problem, we have a random variable $X$ in $n$-dimensional Euclidean space. There is an unknown subspace $\Gamma$ of the $n$-dimensional Euclidean space such that the orthogonal projection of $X$ onto $\Gamma$ is standard multidimensional Gaussian and the orthogonal projection of $X$ onto $\Gamma^{\perp}$, the orthogonal complement of $\Gamma$, is non-Gaussian, in the sense that all its one-dimensional marginals are different from the Gaussian in a certain metric defined in terms of moments. The NGCA problem is to approximate the non-Gaussian subspace $\Gamma^{\perp}$ given samples of $X$. Vectors in $\Gamma^{\perp}$ correspond to `interesting’ directions, whereas vectors in $\Gamma$ correspond to the directions where data is very noisy. The most interesting applications of the NGCA model is for the case when the magnitude of the noise is comparable to that of the true signal, a setting in which traditional noise reduction techniques such as PCA don’t apply directly. NGCA is also related to dimension reduction and to other data analysis problems such as ICA. NGCA-like problems have been studied in statistics for a long time using techniques such as projection pursuit. We give an algorithm that takes polynomial time in the dimension $n$ and has an inverse polynomial dependence on the error parameter measuring the angle distance between the non-Gaussian subspace and the subspace output by the algorithm. Our algorithm is based on relative entropy as the contrast function and fits under the projection pursuit framework. The techniques we develop for analyzing our algorithm maybe of use for other related problems. | |
Tasks | Dimensionality Reduction |
Published | 2018-07-13 |
URL | http://arxiv.org/abs/1807.04936v3 |
http://arxiv.org/pdf/1807.04936v3.pdf | |
PWC | https://paperswithcode.com/paper/non-gaussian-component-analysis-using-entropy |
Repo | |
Framework | |
Triply Supervised Decoder Networks for Joint Detection and Segmentation
Title | Triply Supervised Decoder Networks for Joint Detection and Segmentation |
Authors | Jiale Cao, Yanwei Pang, Xuelong Li |
Abstract | Joint object detection and semantic segmentation can be applied to many fields, such as self-driving cars and unmanned surface vessels. An initial and important progress towards this goal has been achieved by simply sharing the deep convolutional features for the two tasks. However, this simple scheme is unable to make full use of the fact that detection and segmentation are mutually beneficial. To overcome this drawback, we propose a framework called TripleNet where triple supervisions including detection-oriented supervision, class-aware segmentation supervision, and class-agnostic segmentation supervision are imposed on each layer of the decoder network. Class-agnostic segmentation supervision provides an objectness prior knowledge for both semantic segmentation and object detection. Besides the three types of supervisions, two light-weight modules (i.e., inner-connected module and attention skip-layer fusion) are also incorporated into each layer of the decoder. In the proposed framework, detection and segmentation can sufficiently boost each other. Moreover, class-agnostic and class-aware segmentation on each decoder layer are not performed at the test stage. Therefore, no extra computational costs are introduced at the test stage. Experimental results on the VOC2007 and VOC2012 datasets demonstrate that the proposed TripleNet is able to improve both the detection and segmentation accuracies without adding extra computational costs. |
Tasks | Object Detection, Self-Driving Cars, Semantic Segmentation |
Published | 2018-09-25 |
URL | http://arxiv.org/abs/1809.09299v1 |
http://arxiv.org/pdf/1809.09299v1.pdf | |
PWC | https://paperswithcode.com/paper/triply-supervised-decoder-networks-for-joint |
Repo | |
Framework | |
A Highly Parallel FPGA Implementation of Sparse Neural Network Training
Title | A Highly Parallel FPGA Implementation of Sparse Neural Network Training |
Authors | Sourya Dey, Diandian Chen, Zongyang Li, Souvik Kundu, Kuan-Wen Huang, Keith M. Chugg, Peter A. Beerel |
Abstract | We demonstrate an FPGA implementation of a parallel and reconfigurable architecture for sparse neural networks, capable of on-chip training and inference. The network connectivity uses pre-determined, structured sparsity to significantly reduce complexity by lowering memory and computational requirements. The architecture uses a notion of edge-processing, leading to efficient pipelining and parallelization. Moreover, the device can be reconfigured to trade off resource utilization with training time to fit networks and datasets of varying sizes. The combined effects of complexity reduction and easy reconfigurability enable significantly greater exploration of network hyperparameters and structures on-chip. As proof of concept, we show implementation results on an Artix-7 FPGA. |
Tasks | |
Published | 2018-05-31 |
URL | http://arxiv.org/abs/1806.01087v2 |
http://arxiv.org/pdf/1806.01087v2.pdf | |
PWC | https://paperswithcode.com/paper/a-highly-parallel-fpga-implementation-of |
Repo | |
Framework | |
Exploiting Treewidth for Projected Model Counting and its Limits
Title | Exploiting Treewidth for Projected Model Counting and its Limits |
Authors | Johannes K. Fichte, Michael Morak, Markus Hecher, Stefan Woltran |
Abstract | In this paper, we introduce a novel algorithm to solve projected model counting (PMC). PMC asks to count solutions of a Boolean formula with respect to a given set of projected variables, where multiple solutions that are identical when restricted to the projected variables count as only one solution. Our algorithm exploits small treewidth of the primal graph of the input instance. It runs in time $O({2^{2^{k+4}} n^2})$ where k is the treewidth and n is the input size of the instance. In other words, we obtain that the problem PMC is fixed-parameter tractable when parameterized by treewidth. Further, we take the exponential time hypothesis (ETH) into consideration and establish lower bounds of bounded treewidth algorithms for PMC, yielding asymptotically tight runtime bounds of our algorithm. |
Tasks | |
Published | 2018-05-14 |
URL | http://arxiv.org/abs/1805.05445v1 |
http://arxiv.org/pdf/1805.05445v1.pdf | |
PWC | https://paperswithcode.com/paper/exploiting-treewidth-for-projected-model |
Repo | |
Framework | |
Machine learning in resting-state fMRI analysis
Title | Machine learning in resting-state fMRI analysis |
Authors | Meenakshi Khosla, Keith Jamison, Gia H. Ngo, Amy Kuceyeski, Mert R. Sabuncu |
Abstract | Machine learning techniques have gained prominence for the analysis of resting-state functional Magnetic Resonance Imaging (rs-fMRI) data. Here, we present an overview of various unsupervised and supervised machine learning applications to rs-fMRI. We present a methodical taxonomy of machine learning methods in resting-state fMRI. We identify three major divisions of unsupervised learning methods with regard to their applications to rs-fMRI, based on whether they discover principal modes of variation across space, time or population. Next, we survey the algorithms and rs-fMRI feature representations that have driven the success of supervised subject-level predictions. The goal is to provide a high-level overview of the burgeoning field of rs-fMRI from the perspective of machine learning applications. |
Tasks | |
Published | 2018-12-30 |
URL | http://arxiv.org/abs/1812.11477v1 |
http://arxiv.org/pdf/1812.11477v1.pdf | |
PWC | https://paperswithcode.com/paper/machine-learning-in-resting-state-fmri |
Repo | |
Framework | |
Bilingual Embeddings with Random Walks over Multilingual Wordnets
Title | Bilingual Embeddings with Random Walks over Multilingual Wordnets |
Authors | J. Goikoetxea, A. Soroa, E. Agirre |
Abstract | Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then map them using bilingual dictionaries. In this work, we present a novel method to learn bilingual embeddings based on multilingual knowledge bases (KB) such as WordNet. Our method extracts bilingual information from multilingual wordnets via random walks and learns a joint embedding space in one go. We further reinforce cross-lingual equivalence adding bilingual con- straints in the loss function of the popular skipgram model. Our experiments involve twelve cross-lingual word similarity and relatedness datasets in six lan- guage pairs covering four languages, and show that: 1) random walks over mul- tilingual wordnets improve results over just using dictionaries; 2) multilingual wordnets on their own improve over text-based systems in similarity datasets; 3) the good results are consistent for large wordnets (e.g. English, Spanish), smaller wordnets (e.g. Basque) or loosely aligned wordnets (e.g. Italian); 4) the combination of wordnets and text yields the best results, above mapping-based approaches. Our method can be applied to richer KBs like DBpedia or Babel- Net, and can be easily extended to multilingual embeddings. All software and resources are open source. |
Tasks | Machine Translation, Word Embeddings |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08316v1 |
http://arxiv.org/pdf/1804.08316v1.pdf | |
PWC | https://paperswithcode.com/paper/bilingual-embeddings-with-random-walks-over |
Repo | |
Framework | |
Wayeb: a Tool for Complex Event Forecasting
Title | Wayeb: a Tool for Complex Event Forecasting |
Authors | Elias Alevizos, Alexander Artikis, Georgios Paliouras |
Abstract | Complex Event Processing (CEP) systems have appeared in abundance during the last two decades. Their purpose is to detect in real-time interesting patterns upon a stream of events and to inform an analyst for the occurrence of such patterns in a timely manner. However, there is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CEP engine. We present Wayeb, a tool that attempts to address the issue of Complex Event Forecasting. Wayeb employs symbolic automata as a computational model for pattern detection and Markov chains for deriving a probabilistic description of a symbolic automaton. |
Tasks | |
Published | 2018-12-16 |
URL | http://arxiv.org/abs/1901.01826v1 |
http://arxiv.org/pdf/1901.01826v1.pdf | |
PWC | https://paperswithcode.com/paper/wayeb-a-tool-for-complex-event-forecasting |
Repo | |
Framework | |
Convolutional Neural Networks over Control Flow Graphs for Software Defect Prediction
Title | Convolutional Neural Networks over Control Flow Graphs for Software Defect Prediction |
Authors | Anh Viet Phan, Minh Le Nguyen, Lam Thu Bui |
Abstract | Existing defects in software components is unavoidable and leads to not only a waste of time and money but also many serious consequences. To build predictive models, previous studies focus on manually extracting features or using tree representations of programs, and exploiting different machine learning algorithms. However, the performance of the models is not high since the existing features and tree structures often fail to capture the semantics of programs. To explore deeply programs’ semantics, this paper proposes to leverage precise graphs representing program execution flows, and deep neural networks for automatically learning defect features. Firstly, control flow graphs are constructed from the assembly instructions obtained by compiling source code; we thereafter apply multi-view multi-layer directed graph-based convolutional neural networks (DGCNNs) to learn semantic features. The experiments on four real-world datasets show that our method significantly outperforms the baselines including several other deep learning approaches. |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.04986v1 |
http://arxiv.org/pdf/1802.04986v1.pdf | |
PWC | https://paperswithcode.com/paper/convolutional-neural-networks-over-control |
Repo | |
Framework | |