Paper Group NANR 114
JPEG Artifacts Reduction via Deep Convolutional Sparse Coding. OSIAN: Open Source International Arabic News Corpus - Preparation and Integration into the CLARIN-infrastructure. An Automated Framework for Fast Cognate Detection and Bayesian Phylogenetic Inference in Computational Historical Linguistics. A NON-LINEAR THEORY FOR SENTENCE EMBEDDING. Te …
JPEG Artifacts Reduction via Deep Convolutional Sparse Coding
| Title | JPEG Artifacts Reduction via Deep Convolutional Sparse Coding |
| Authors | Xueyang Fu, Zheng-Jun Zha, Feng Wu, Xinghao Ding, John Paisley |
| Abstract | To effectively reduce JPEG compression artifacts, we propose a deep convolutional sparse coding (DCSC) network architecture. We design our DCSC in the framework of classic learned iterative shrinkage-threshold algorithm. To focus on recognizing and separating artifacts only, we sparsely code the feature maps instead of the raw image. The final de-blocked image is directly reconstructed from the coded features. We use dilated convolution to extract multi-scale image features, which allows our single model to simultaneously handle multiple JPEG compression levels. Since our method integrates model-based convolutional sparse coding with a learning-based deep neural network, the entire network structure is compact and more explainable. The resulting lightweight model generates comparable or better de-blocking results when compared with state-of-the-art methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Fu_JPEG_Artifacts_Reduction_via_Deep_Convolutional_Sparse_Coding_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Fu_JPEG_Artifacts_Reduction_via_Deep_Convolutional_Sparse_Coding_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/jpeg-artifacts-reduction-via-deep |
| Repo | |
| Framework | |
OSIAN: Open Source International Arabic News Corpus - Preparation and Integration into the CLARIN-infrastructure
| Title | OSIAN: Open Source International Arabic News Corpus - Preparation and Integration into the CLARIN-infrastructure |
| Authors | Imad Zeroual, Dirk Goldhahn, Thomas Eckart, Abdelhak Lakhouaja |
| Abstract | The World Wide Web has become a fundamental resource for building large text corpora. Broadcasting platforms such as news websites are rich sources of data regarding diverse topics and form a valuable foundation for research. The Arabic language is extensively utilized on the Web. Still, Arabic is relatively an under-resourced language in terms of availability of freely annotated corpora. This paper presents the first version of the Open Source International Arabic News (OSIAN) corpus. The corpus data was collected from international Arabic news websites, all being freely available on the Web. The corpus consists of about 3.5 million articles comprising more than 37 million sentences and roughly 1 billion tokens. It is encoded in XML; each article is annotated with metadata information. Moreover, each word is annotated with lemma and part-of-speech. the described corpus is processed, archived and published into the CLARIN infrastructure. This publication includes descriptive metadata via OAI-PMH, direct access to the plain text material (available under Creative Commons Attribution-Non-Commercial 4.0 International License - CC BY-NC 4.0), and integration into the WebLicht annotation platform and CLARIN{'}s Federated Content Search FCS. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4619/ |
| https://www.aclweb.org/anthology/W19-4619 | |
| PWC | https://paperswithcode.com/paper/osian-open-source-international-arabic-news |
| Repo | |
| Framework | |
An Automated Framework for Fast Cognate Detection and Bayesian Phylogenetic Inference in Computational Historical Linguistics
| Title | An Automated Framework for Fast Cognate Detection and Bayesian Phylogenetic Inference in Computational Historical Linguistics |
| Authors | Taraka Rama, Johann-Mattis List |
| Abstract | We present a fully automated workflow for phylogenetic reconstruction on large datasets, consisting of two novel methods, one for fast detection of cognates and one for fast Bayesian phylogenetic inference. Our results show that the methods take less than a few minutes to process language families that have so far required large amounts of time and computational power. Moreover, the cognates and the trees inferred from the method are quite close, both to gold standard cognate judgments and to expert language family trees. Given its speed and ease of application, our framework is specifically useful for the exploration of very large datasets in historical linguistics. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1627/ |
| https://www.aclweb.org/anthology/P19-1627 | |
| PWC | https://paperswithcode.com/paper/an-automated-framework-for-fast-cognate |
| Repo | |
| Framework | |
A NON-LINEAR THEORY FOR SENTENCE EMBEDDING
| Title | A NON-LINEAR THEORY FOR SENTENCE EMBEDDING |
| Authors | Hichem Mezaoui, Isar Nejadgholi |
| Abstract | This paper revisits the Random Walk model for sentence embedding in the context of non-extensive statistics. We propose a non-extensive algebra to compute the discourse vector. We argue that by doing so we are taking into account high non-linearity in the semantic space. Furthermore, we show that by considering a non-extensive algebra, the compounding effect of the vector length is mitigated. Overall, we show that the proposed model leads to good sentence embedding. We evaluate the embedding method on textual similarity tasks. |
| Tasks | Sentence Embedding |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJMZRsC9Y7 |
| https://openreview.net/pdf?id=SJMZRsC9Y7 | |
| PWC | https://paperswithcode.com/paper/a-non-linear-theory-for-sentence-embedding |
| Repo | |
| Framework | |
Team Taurus at SemEval-2019 Task 9: Expert-informed pattern recognition for suggestion mining
| Title | Team Taurus at SemEval-2019 Task 9: Expert-informed pattern recognition for suggestion mining |
| Authors | Nelleke Oostdijk, Hans van Halteren |
| Abstract | This paper presents our submissions to SemEval-2019 Task9, Suggestion Mining. Our system is one in a series of systems in which we compare an approach using expert-defined rules with a comparable one using machine learning. We target tasks with a syntactic or semantic component that might be better described by a human understanding the task than by a machine learner only able to count features. For Semeval-2019 Task 9, the expert rules clearly outperformed our machine learning model when training and testing on equally balanced testsets. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2219/ |
| https://www.aclweb.org/anthology/S19-2219 | |
| PWC | https://paperswithcode.com/paper/team-taurus-at-semeval-2019-task-9-expert |
| Repo | |
| Framework | |
Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text
| Title | Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text |
| Authors | Prasadith Kirinde Gamaarachchige, Diana Inkpen |
| Abstract | We investigate the impact of using emotional patterns identified by the clinical practitioners and computational linguists to enhance the prediction capabilities of a mental illness detection (in our case depression and post-traumatic stress disorder) model built using a deep neural network architecture. Over the years, deep learning methods have been successfully used in natural language processing tasks, including a few in the domain of mental illness and suicide ideation detection. We illustrate the effectiveness of using multi-task learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability. Given the limited amount of unstructured data available for training, we managed to obtain a task-specific AUC higher than 0.90. In comparison to methods such as multi-class classification, we identified multi-task learning with multi-channel convolution neural network and multiple-inputs to be effective in detecting mental disorders. |
| Tasks | Multi-Task Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6208/ |
| https://www.aclweb.org/anthology/D19-6208 | |
| PWC | https://paperswithcode.com/paper/multi-task-multi-channel-multi-input-learning |
| Repo | |
| Framework | |
Neural Multi-Task Learning for Stance Prediction
| Title | Neural Multi-Task Learning for Stance Prediction |
| Authors | Wei Fang, Moin Nadeem, Mitra Mohtarami, James Glass |
| Abstract | We present a multi-task learning model that leverages large amount of textual information from existing datasets to improve stance prediction. In particular, we utilize multiple NLP tasks under both unsupervised and supervised settings for the target stance prediction task. Our model obtains state-of-the-art performance on a public benchmark dataset, Fake News Challenge, outperforming current approaches by a wide margin. |
| Tasks | Multi-Task Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6603/ |
| https://www.aclweb.org/anthology/D19-6603 | |
| PWC | https://paperswithcode.com/paper/neural-multi-task-learning-for-stance |
| Repo | |
| Framework | |
ChiMed: A Chinese Medical Corpus for Question Answering
| Title | ChiMed: A Chinese Medical Corpus for Question Answering |
| Authors | Yuanhe Tian, Weicheng Ma, Fei Xia, Yan Song |
| Abstract | Question answering (QA) is a challenging task in natural language processing (NLP), especially when it is applied to specific domains. While models trained in the general domain can be adapted to a new target domain, their performance often degrades significantly due to domain mismatch. Alternatively, one can require a large amount of domain-specific QA data, but such data are rare, especially for the medical domain. In this study, we first collect a large-scale Chinese medical QA corpus called ChiMed; second we annotate a small fraction of the corpus to check the quality of the answers; third, we extract two datasets from the corpus and use them for the relevancy prediction task and the adoption prediction task. Several benchmark models are applied to the datasets, producing good results for both tasks. |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5027/ |
| https://www.aclweb.org/anthology/W19-5027 | |
| PWC | https://paperswithcode.com/paper/chimed-a-chinese-medical-corpus-for-question |
| Repo | |
| Framework | |
Event Causality Recognition Exploiting Multiple Annotators’ Judgments and Background Knowledge
| Title | Event Causality Recognition Exploiting Multiple Annotators’ Judgments and Background Knowledge |
| Authors | Kazuma Kadowaki, Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh, Julien Kloetzer |
| Abstract | We propose new BERT-based methods for recognizing event causality such as {}smoke cigarettes{''} {--}{\textgreater} {}die of lung cancer{''} written in web texts. In our methods, we grasp each annotator{'}s policy by training multiple classifiers, each of which predicts the labels given by a single annotator, and combine the resulting classifiers{'} outputs to predict the final labels determined by majority vote. Furthermore, we investigate the effect of supplying background knowledge to our classifiers. Since BERT models are pre-trained with a large corpus, some sort of background knowledge for event causality may be learned during pre-training. Our experiments with a Japanese dataset suggest that this is actually the case: Performance improved when we pre-trained the BERT models with web texts containing a large number of event causalities instead of Wikipedia articles or randomly sampled web texts. However, this effect was limited. Therefore, we further improved performance by simply adding texts related to an input causality candidate as background knowledge to the input of the BERT models. We believe these findings indicate a promising future research direction. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1590/ |
| https://www.aclweb.org/anthology/D19-1590 | |
| PWC | https://paperswithcode.com/paper/event-causality-recognition-exploiting |
| Repo | |
| Framework | |
Probabilistic Planning with Sequential Monte Carlo methods
| Title | Probabilistic Planning with Sequential Monte Carlo methods |
| Authors | Alexandre Piche, Valentin Thomas, Cyril Ibrahim, Yoshua Bengio, Chris Pal |
| Abstract | In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal trajectories. This enables us to use sampling methods, and thus, tackle planning in continuous domains using a fixed computational budget. We design a new algorithm, Sequential Monte Carlo Planning, by leveraging classical methods in Sequential Monte Carlo and Bayesian smoothing in the context of control as inference. Furthermore, we show that Sequential Monte Carlo Planning can capture multimodal policies and can quickly learn continuous control tasks. |
| Tasks | Continuous Control |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ByetGn0cYX |
| https://openreview.net/pdf?id=ByetGn0cYX | |
| PWC | https://paperswithcode.com/paper/probabilistic-planning-with-sequential-monte |
| Repo | |
| Framework | |
Whitening and Coloring transform for GANs
| Title | Whitening and Coloring transform for GANs |
| Authors | Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe |
| Abstract | Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is important in a general GAN scenario in which the training process is known to be highly unstable. We test our approach on different datasets and using different GAN networks and training protocols, showing a consistent improvement in all the tested frameworks. Our CIFAR-10 supervised results are higher than all previous works on this dataset. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1x2Fj0qKQ |
| https://openreview.net/pdf?id=S1x2Fj0qKQ | |
| PWC | https://paperswithcode.com/paper/whitening-and-coloring-transform-for-gans |
| Repo | |
| Framework | |
The LAIX Systems in the BEA-2019 GEC Shared Task
| Title | The LAIX Systems in the BEA-2019 GEC Shared Task |
| Authors | Ruobing Li, Chuan Wang, Yefei Zha, Yonghong Yu, Shiman Guo, Qiang Wang, Yang Liu, Hui Lin |
| Abstract | In this paper, we describe two systems we developed for the three tracks we have participated in the BEA-2019 GEC Shared Task. We investigate competitive classification models with bi-directional recurrent neural networks (Bi-RNN) and neural machine translation (NMT) models. For different tracks, we use ensemble systems to selectively combine the NMT models, the classification models, and some rules, and demonstrate that an ensemble solution can effectively improve GEC performance over single systems. Our GEC systems ranked the first in the Unrestricted Track, and the third in both the Restricted Track and the Low Resource Track. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4416/ |
| https://www.aclweb.org/anthology/W19-4416 | |
| PWC | https://paperswithcode.com/paper/the-laix-systems-in-the-bea-2019-gec-shared |
| Repo | |
| Framework | |
Tinkering with black boxes: counterfactuals uncover modularity in generative models
| Title | Tinkering with black boxes: counterfactuals uncover modularity in generative models |
| Authors | Michel Besserve, Remy Sun, Bernhard Schoelkopf |
| Abstract | Deep generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are important tools to capture and investigate the properties of complex empirical data. However, the complexity of their inner elements makes their functionment challenging to assess and modify. In this respect, these architectures behave as black box models. In order to better understand the function of such networks, we analyze their modularity based on the counterfactual manipulation of their internal variables. Our experiments on the generation of human faces with VAEs and GANs support that modularity between activation maps distributed over channels of generator architectures is achieved to some degree, can be used to better understand how these systems operate and allow meaningful transformations of the generated images without further training. erate and edit the content of generated images. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Byldr3RqKX |
| https://openreview.net/pdf?id=Byldr3RqKX | |
| PWC | https://paperswithcode.com/paper/tinkering-with-black-boxes-counterfactuals |
| Repo | |
| Framework | |
IM-Net for High Resolution Video Frame Interpolation
| Title | IM-Net for High Resolution Video Frame Interpolation |
| Authors | Tomer Peleg, Pablo Szekely, Doron Sabo, Omry Sendik |
| Abstract | Video frame interpolation is a long-studied problem in the video processing field. Recently, deep learning approaches have been applied to this problem, showing impressive results on low-resolution benchmarks. However, these methods do not scale-up favorably to high resolutions. Specifically, when the motion exceeds a typical number of pixels, their interpolation quality is degraded. Moreover, their run time renders them impractical for real-time applications. In this paper we propose IM-Net: an interpolated motion neural network. We use an economic structured architecture and end-to-end training with multi-scale tailored losses. In particular, we formulate interpolated motion estimation as classification rather than regression. IM-Net outperforms previous methods by more than 1.3dB (PSNR) on a high resolution version of the recently introduced Vimeo triplet dataset. Moreover, the network runs in less than 33msec on a single GPU for HD resolution. |
| Tasks | Motion Estimation, Video Frame Interpolation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Peleg_IM-Net_for_High_Resolution_Video_Frame_Interpolation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Peleg_IM-Net_for_High_Resolution_Video_Frame_Interpolation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/im-net-for-high-resolution-video-frame |
| Repo | |
| Framework | |
Neural Network Regression with Beta, Dirichlet, and Dirichlet-Multinomial Outputs
| Title | Neural Network Regression with Beta, Dirichlet, and Dirichlet-Multinomial Outputs |
| Authors | Peter Sadowski, Pierre Baldi |
| Abstract | We propose a method for quantifying uncertainty in neural network regression models when the targets are real values on a $d$-dimensional simplex, such as probabilities. We show that each target can be modeled as a sample from a Dirichlet distribution, where the parameters of the Dirichlet are provided by the output of a neural network, and that the combined model can be trained using the gradient of the data likelihood. This approach provides interpretable predictions in the form of multidimensional distributions, rather than point estimates, from which one can obtain confidence intervals or quantify risk in decision making. Furthermore, we show that the same approach can be used to model targets in the form of empirical counts as samples from the Dirichlet-multinomial compound distribution. In experiments, we verify that our approach provides these benefits without harming the performance of the point estimate predictions on two diverse applications: (1) distilling deep convolutional networks trained on CIFAR-100, and (2) predicting the location of particle collisions in the XENON1T Dark Matter detector. |
| Tasks | Decision Making |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJeRg205Fm |
| https://openreview.net/pdf?id=BJeRg205Fm | |
| PWC | https://paperswithcode.com/paper/neural-network-regression-with-beta-dirichlet |
| Repo | |
| Framework | |
