Paper Group ANR 1035
Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair. A Focus on Neural Machine Translation for African Languages. MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging. Introducing languid particle dynamics to a selection of PSO variants. Explainabl …
Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair
| Title | Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair |
| Authors | Aidar Valeev, Ilshat Gibadullin, Albina Khusainova, Adil Khan |
| Abstract | Neural machine translation is the current state-of-the-art in machine translation. Although it is successful in a resource-rich setting, its applicability for low-resource language pairs is still debatable. In this paper, we explore the effect of different techniques to improve machine translation quality when a parallel corpus is as small as 324 000 sentences, taking as an example previously unexplored Russian-Tatar language pair. We apply such techniques as transfer learning and semi-supervised learning to the base Transformer model, and empirically show that the resulting models improve Russian to Tatar and Tatar to Russian translation quality by +2.57 and +3.66 BLEU, respectively. |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00368v1 |
| https://arxiv.org/pdf/1910.00368v1.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-low-resource-machine |
| Repo | |
| Framework | |
A Focus on Neural Machine Translation for African Languages
| Title | A Focus on Neural Machine Translation for African Languages |
| Authors | Laura Martinus, Jade Z. Abbott |
| Abstract | African languages are numerous, complex and low-resourced. The datasets required for machine translation are difficult to discover, and existing research is hard to reproduce. Minimal attention has been given to machine translation for African languages so there is scant research regarding the problems that arise when using machine translation techniques. To begin addressing these problems, we trained models to translate English to five of the official South African languages (Afrikaans, isiZulu, Northern Sotho, Setswana, Xitsonga), making use of modern neural machine translation techniques. The results obtained show the promise of using neural machine translation techniques for African languages. By providing reproducible publicly-available data, code and results, this research aims to provide a starting point for other researchers in African machine translation to compare to and build upon. |
| Tasks | Machine Translation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.05685v2 |
| https://arxiv.org/pdf/1906.05685v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-focus-on-neural-machine-translation-for |
| Repo | |
| Framework | |
MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging
| Title | MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging |
| Authors | Gabriel Marzinotto, Johannes Heinecke, Geraldine Damnati |
| Abstract | This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform semantic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these probabilities and builds the graph nodes. Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking feature that reflects the decisions made in previous steps. Process continues until the terminal nodes are reached. We choose a standard neural tagger and we focused on our recursive parsing strategy and on the cross lingual transfer problem to develop a robust model for the French language, using only few training samples. |
| Tasks | Cross-Lingual Transfer, Semantic Parsing |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02733v1 |
| https://arxiv.org/pdf/1910.02733v1.pdf | |
| PWC | https://paperswithcode.com/paper/maskparsedeskin-at-semeval-2019-task-1-cross-1 |
| Repo | |
| Framework | |
Introducing languid particle dynamics to a selection of PSO variants
| Title | Introducing languid particle dynamics to a selection of PSO variants |
| Authors | Siniša Družeta, Stefan Ivić, Luka Grbčić, Ivana Lučin |
| Abstract | Previous research showed that conditioning a PSO agent’s movement based on its personal fitness improvement enhances the standard PSO method. In this article, languid particle dynamics (LPD) technique is used on five adequate and widely used PSO variants. Five unmodified PSO variants were tested against their LPD-implemented counterparts on three search space dimensionalities (10, 20, and 50 dimensions) and 30 test functions of the CEC 2014 benchmark test. In the preliminary phase of the testing four of the five tested PSO variants showed improvement in accuracy. The worst and best-achieving variants from preliminary test went through detailed investigation on 220 and 770 combinations of method parameters, where both variants showed overall gains in accuracy when enhanced with LPD. Finally, the results obtained with best achieving PSO parameters were subject to statistical analysis which showed that the two variants give statistically significant improvements in accuracy for 13-50% of the test functions. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02474v1 |
| https://arxiv.org/pdf/1906.02474v1.pdf | |
| PWC | https://paperswithcode.com/paper/introducing-languid-particle-dynamics-to-a |
| Repo | |
| Framework | |
Explainable Fact Checking with Probabilistic Answer Set Programming
| Title | Explainable Fact Checking with Probabilistic Answer Set Programming |
| Authors | Naser Ahmadi, Joohyung Lee, Paolo Papotti, Mohammed Saeed |
| Abstract | One challenge in fact checking is the ability to improve the transparency of the decision. We present a fact checking method that uses reference information in knowledge graphs (KGs) to assess claims and explain its decisions. KGs contain a formal representation of knowledge with semantic descriptions of entities and their relationships. We exploit such rich semantics to produce interpretable explanations for the fact checking output. As information in a KG is inevitably incomplete, we rely on logical rule discovery and on Web text mining to gather the evidence to assess a given claim. Uncertain rules and facts are turned into logical programs and the checking task is modeled as an inference problem in a probabilistic extension of answer set programs. Experiments show that the probabilistic inference enables the efficient labeling of claims with interpretable explanations, and the quality of the results is higher than state of the art baselines. |
| Tasks | Knowledge Graphs |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09198v1 |
| https://arxiv.org/pdf/1906.09198v1.pdf | |
| PWC | https://paperswithcode.com/paper/explainable-fact-checking-with-probabilistic |
| Repo | |
| Framework | |
Analyzing privacy-aware mobility behavior using the evolution of spatio-temporal entropy
| Title | Analyzing privacy-aware mobility behavior using the evolution of spatio-temporal entropy |
| Authors | Arielle Moro, Benoît Garbinato, Valérie Chavez-Demoulin |
| Abstract | Analyzing mobility behavior of users is extremely useful to create or improve existing services. Several research works have been done in order to study mobility behavior of users that mainly use users’ significant locations. However, these existing analysis are extremely intrusive because they require the knowledge of the frequently visited places of users, which thus makes it fairly easy to identify them. Consequently, in this paper, we present a privacy-aware methodology to analyze mobility behavior of users. We firstly propose a new metric based on the well-known Shannon entropy, called spatio-temporal entropy, to quantify the mobility level of a user during a time window. Then, we compute a sequence of spatio-temporal entropy from the location history of the user that expresses user’s movements as rhythms. We secondly present how to study the effects of several groups of additional variables on the evolution of the spatio-temporal entropy of a user, such as spatio-temporal, demographic and mean of transportation variables. For this, we use Generalized Additive Models (GAMs). The results firstly show that the spatio-temporal entropy and GAMs are an ideal combination to understand mobility behavior of an individual user or a group of users. We also evaluate the prediction accuracy of a global GAM compared to individual GAMs and individual AutoRegressive Integrated Moving Average (ARIMA) models. These last results highlighted that the global GAM gives more accurate predictions of spatio-temporal entropy by checking the Mean Absolute Error (MAE). In addition, this research work opens various threads, such as the prediction of demographic data of users or the creation of personalized mobility prediction models by using movement rhythm characteristics of a user. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07537v2 |
| https://arxiv.org/pdf/1906.07537v2.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-privacy-aware-mobility-behavior |
| Repo | |
| Framework | |
Low rank tensor completion with sparse regularization in a transformed domain
| Title | Low rank tensor completion with sparse regularization in a transformed domain |
| Authors | Ping-Ping Wang, Liang Li, Guang-Hui Cheng |
| Abstract | Tensor completion is a challenging problem with various applications. Many related models based on the low-rank prior of the tensor have been proposed. However, the low-rank prior may not be enough to recover the original tensor from the observed incomplete tensor. In this paper, we prose a tensor completion method by exploiting both the low-rank and sparse prior of tensor. Specifically, the tensor completion task can be formulated as a low-rank minimization problem with a sparse regularizer. The low-rank property is depicted by the tensor truncated nuclear norm based on tensor singular value decomposition (T-SVD) which is a better approximation of tensor tubal rank than tensor nuclear norm. While the sparse regularizer is imposed by a $\ell_{1}$-norm in a discrete cosine transformation (DCT) domain, which can better employ the local sparse property of completed data. To solve the optimization problem, we employ an alternating direction method of multipliers (ADMM) in which we only need to solve several subproblems which have closed-form solutions. Substantial experiments on real world images and videos show that the proposed method has better performances than the existing state-of-the-art methods. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08082v1 |
| https://arxiv.org/pdf/1911.08082v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-tensor-completion-with-sparse |
| Repo | |
| Framework | |
Road Mapping In LiDAR Images Using A Joint-Task Dense Dilated Convolutions Merging Network
| Title | Road Mapping In LiDAR Images Using A Joint-Task Dense Dilated Convolutions Merging Network |
| Authors | Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg |
| Abstract | It is important, but challenging, for the forest industry to accurately map roads which are used for timber transport by trucks. In this work, we propose a Dense Dilated Convolutions Merging Network (DDCM-Net) to detect these roads in lidar images. The DDCM-Net can effectively recognize multi-scale and complex shaped roads with similar texture and colors, and also is shown to have superior performance over existing methods. To further improve its ability to accurately infer categories of roads, we propose the use of a joint-task learning strategy that utilizes two auxiliary output branches, i.e, multi-class classification and binary segmentation, joined with the main output of full-class segmentation. This pushes the network towards learning more robust representations that are expected to boost the ultimate performance of the main task. In addition, we introduce an iterative-random-weighting method to automatically weigh the joint losses for auxiliary tasks. This can avoid the difficult and expensive process of tuning the weights of each task’s loss by hand. The experiments demonstrate that our proposed joint-task DDCM-Net can achieve better performance with fewer parameters and higher computational efficiency than previous state-of-the-art approaches. |
| Tasks | |
| Published | 2019-09-07 |
| URL | https://arxiv.org/abs/1909.04588v1 |
| https://arxiv.org/pdf/1909.04588v1.pdf | |
| PWC | https://paperswithcode.com/paper/road-mapping-in-lidar-images-using-a-joint |
| Repo | |
| Framework | |
An Algorithm Unrolling Approach to Deep Image Deblurring
| Title | An Algorithm Unrolling Approach to Deep Image Deblurring |
| Authors | Yuelong Li, Mohammad Tofighi, Vishal Monga, Yonina C. Eldar |
| Abstract | While neural networks have achieved vastly enhanced performance over traditional iterative methods in many cases, they are generally empirically designed and the underlying structures are difficult to interpret. The algorithm unrolling approach has helped connect iterative algorithms to neural network architectures. However, such connections have not been made yet for blind image deblurring. In this paper, we propose a neural network architecture that advances this idea. We first present an iterative algorithm that may be considered a generalization of the traditional total-variation regularization method on the gradient domain, and subsequently unroll the half-quadratic splitting algorithm to construct a neural network. Our proposed deep network achieves significant practical performance gains while enjoying interpretability at the same time. Experimental results show that our approach outperforms many state-of-the-art methods. |
| Tasks | Blind Image Deblurring, Deblurring |
| Published | 2019-02-09 |
| URL | http://arxiv.org/abs/1902.05399v2 |
| http://arxiv.org/pdf/1902.05399v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-algorithm-unrolling-approach-to-deep-image |
| Repo | |
| Framework | |
DVOLVER: Efficient Pareto-Optimal Neural Network Architecture Search
| Title | DVOLVER: Efficient Pareto-Optimal Neural Network Architecture Search |
| Authors | Guillaume Michel, Mohammed Amine Alaoui, Alice Lebois, Amal Feriani, Mehdi Felhi |
| Abstract | Automatic search of neural network architectures is a standing research topic. In addition to the fact that it presents a faster alternative to hand-designed architectures, it can improve their efficiency and for instance generate Convolutional Neural Networks (CNN) adapted for mobile devices. In this paper, we present a multi-objective neural architecture search method to find a family of CNN models with the best accuracy and computational resources tradeoffs, in a search space inspired by the state-of-the-art findings in neural search. Our work, called Dvolver, evolves a population of architectures and iteratively improves an approximation of the optimal Pareto front. Applying Dvolver on the model accuracy and on the number of floating points operations as objective functions, we are able to find, in only 2.5 days, a set of competitive mobile models on ImageNet. Amongst these models one architecture has the same Top-1 accuracy on ImageNet as NASNet-A mobile with 8% less floating point operations and another one has a Top-1 accuracy of 75.28% on ImageNet exceeding by 0.28% the best MobileNetV2 model for the same computational resources. |
| Tasks | Neural Architecture Search |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01654v1 |
| http://arxiv.org/pdf/1902.01654v1.pdf | |
| PWC | https://paperswithcode.com/paper/dvolver-efficient-pareto-optimal-neural |
| Repo | |
| Framework | |
The Role of User Profile for Fake News Detection
| Title | The Role of User Profile for Fake News Detection |
| Authors | Kai Shu, Xinyi Zhou, Suhang Wang, Reza Zafarani, Huan Liu |
| Abstract | Consuming news from social media is becoming increasingly popular. Social media appeals to users due to its fast dissemination of information, low cost, and easy access. However, social media also enables the widespread of fake news. Because of the detrimental societal effects of fake news, detecting fake news has attracted increasing attention. However, the detection performance only using news contents is generally not satisfactory as fake news is written to mimic true news. Thus, there is a need for an in-depth understanding on the relationship between user profiles on social media and fake news. In this paper, we study the challenging problem of understanding and exploiting user profiles on social media for fake news detection. In an attempt to understand connections between user profiles and fake news, first, we measure users’ sharing behaviors on social media and group representative users who are more likely to share fake and real news; then, we perform a comparative analysis of explicit and implicit profile features between these user groups, which reveals their potential to help differentiate fake news from real news. To exploit user profile features, we demonstrate the usefulness of these user profile features in a fake news classification task. We further validate the effectiveness of these features through feature importance analysis. The findings of this work lay the foundation for deeper exploration of user profile features of social media and enhance the capabilities for fake news detection. |
| Tasks | Fake News Detection, Feature Importance |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13355v1 |
| http://arxiv.org/pdf/1904.13355v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-role-of-user-profile-for-fake-news |
| Repo | |
| Framework | |
Exploring Factors for Improving Low Resolution Face Recognition
| Title | Exploring Factors for Improving Low Resolution Face Recognition |
| Authors | Omid Abdollahi Aghdam, Behzad Bozorgtabar, Hazım Kemal Ekenel, Jean-Philippe Thiran |
| Abstract | State-of-the-art deep face recognition approaches report near perfect performance on popular benchmarks, e.g., Labeled Faces in the Wild. However, their performance deteriorates significantly when they are applied on low quality images, such as those acquired by surveillance cameras. A further challenge for low resolution face recognition for surveillance applications is the matching of recorded low resolution probe face images with high resolution reference images, which could be the case in watchlist scenarios. In this paper, we have addressed these problems and investigated the factors that would contribute to the identification performance of the state-of-the-art deep face recognition models when they are applied to low resolution face recognition under mismatched conditions. We have observed that the following factors affect performance in a positive way: appearance variety and resolution distribution of the training dataset, resolution matching between the gallery and probe images, and the amount of information included in the probe images. By leveraging this information, we have utilized deep face models trained on MS-Celeb-1M and fine-tuned on VGGFace2 dataset and achieved state-of-the-art accuracies on the SCFace and ICB-RW benchmarks, even without using any training data from the datasets of these benchmarks. |
| Tasks | Face Recognition |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10104v2 |
| https://arxiv.org/pdf/1907.10104v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-factors-for-improving-low |
| Repo | |
| Framework | |
On Constrained Open-World Probabilistic Databases
| Title | On Constrained Open-World Probabilistic Databases |
| Authors | Tal Friedman, Guy Van den Broeck |
| Abstract | Increasing amounts of available data have led to a heightened need for representing large-scale probabilistic knowledge bases. One approach is to use a probabilistic database, a model with strong assumptions that allow for efficiently answering many interesting queries. Recent work on open-world probabilistic databases strengthens the semantics of these probabilistic databases by discarding the assumption that any information not present in the data must be false. While intuitive, these semantics are not sufficiently precise to give reasonable answers to queries. We propose overcoming these issues by using constraints to restrict this open world. We provide an algorithm for one class of queries, and establish a basic hardness result for another. Finally, we propose an efficient and tight approximation for a large class of queries. |
| Tasks | |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10677v2 |
| http://arxiv.org/pdf/1902.10677v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-constrained-open-world-probabilistic |
| Repo | |
| Framework | |
Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks
| Title | Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks |
| Authors | Spencer Frei, Yuan Cao, Quanquan Gu |
| Abstract | The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited theoretical understanding for this improvement. In this work, we analyze overparameterized deep residual networks trained by gradient descent following random initialization, and demonstrate that (i) the class of networks learned by gradient descent constitutes a small subset of the entire neural network function class, and (ii) this subclass of networks is sufficiently large to guarantee small training error. By showing (i) we are able to demonstrate that deep residual networks trained with gradient descent have a small generalization gap between training and test error, and together with (ii) this guarantees that the test error will be small. Our optimization and generalization guarantees require overparameterization that is only logarithmic in the depth of the network, while all known generalization bounds for deep non-residual networks have overparameterization requirements that are at least polynomial in the depth. This provides an explanation for why residual networks are preferable to non-residual ones. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02934v1 |
| https://arxiv.org/pdf/1910.02934v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithm-dependent-generalization-bounds-for |
| Repo | |
| Framework | |
PolyTransform: Deep Polygon Transformer for Instance Segmentation
| Title | PolyTransform: Deep Polygon Transformer for Instance Segmentation |
| Authors | Justin Liang, Namdar Homayounfar, Wei-Chiu Ma, Yuwen Xiong, Rui Hu, Raquel Urtasun |
| Abstract | In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods. In particular, we first exploit a segmentation network to generate instance masks. We then convert the masks into a set of polygons that are then fed to a deforming network that transforms the polygons such that they better fit the object boundaries. Our experiments on the challenging Cityscapes dataset show that our PolyTransform significantly improves the performance of the backbone instance segmentation network and ranks 1st on the Cityscapes test-set leaderboard. We also show impressive gains in the interactive annotation setting. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02801v2 |
| https://arxiv.org/pdf/1912.02801v2.pdf | |
| PWC | https://paperswithcode.com/paper/polytransform-deep-polygon-transformer-for |
| Repo | |
| Framework | |
