October 20, 2019

3001 words 15 mins read

Paper Group AWR 215

SentiPers: A Sentiment Analysis Corpus for Persian. Spatially Localized Atlas Network Tiles Enables 3D Whole Brain Segmentation from Limited Data. MRI Super-Resolution using Multi-Channel Total Variation. A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation. Deep Component Analysis via Alterna …

SentiPers: A Sentiment Analysis Corpus for Persian


Title	SentiPers: A Sentiment Analysis Corpus for Persian
Authors	Pedram Hosseini, Ali Ahmadian Ramaki, Hassan Maleki, Mansoureh Anvari, Seyed Abolghasem Mirroshandel
Abstract	Sentiment Analysis (SA) is a major field of study in natural language processing, computational linguistics and information retrieval. Interest in SA has been constantly growing in both academia and industry over the recent years. Moreover, there is an increasing need for generating appropriate resources and datasets in particular for low resource languages including Persian. These datasets play an important role in designing and developing appropriate opinion mining platforms using supervised, semi-supervised or unsupervised methods. In this paper, we outline the entire process of developing a manually annotated sentiment corpus, SentiPers, which covers formal and informal written contemporary Persian. To the best of our knowledge, SentiPers is a unique sentiment corpus with such a rich annotation in three different levels including document-level, sentence-level, and entity/aspect-level for Persian. The corpus contains more than 26000 sentences of users opinions from digital product domain and benefits from special characteristics such as quantifying the positiveness or negativity of an opinion through assigning a number within a specific range to any given sentence. Furthermore, we present statistics on various components of our corpus as well as studying the inter-annotator agreement among the annotators. Finally, some of the challenges that we faced during the annotation process will be discussed as well.
Tasks	Information Retrieval, Opinion Mining, Sentiment Analysis
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07737v1
PDF	http://arxiv.org/pdf/1801.07737v1.pdf
PWC	https://paperswithcode.com/paper/sentipers-a-sentiment-analysis-corpus-for
Repo	https://github.com/phosseini/SentiPers
Framework	none

Spatially Localized Atlas Network Tiles Enables 3D Whole Brain Segmentation from Limited Data


Title	Spatially Localized Atlas Network Tiles Enables 3D Whole Brain Segmentation from Limited Data
Authors	Yuankai Huo, Zhoubing Xu, Katherine Aboud, Prasanna Parvathaneni, Shunxing Bao, Camilo Bermudez, Susan M. Resnick, Laurie E. Cutting, Bennett A. Landman
Abstract	Whole brain segmentation on a structural magnetic resonance imaging (MRI) is essential in non-invasive investigation for neuroanatomy. Historically, multi-atlas segmentation (MAS) has been regarded as the de facto standard method for whole brain segmentation. Recently, deep neural network approaches have been applied to whole brain segmentation by learning random patches or 2D slices. Yet, few previous efforts have been made on detailed whole brain segmentation using 3D networks due to the following challenges: (1) fitting entire whole brain volume into 3D networks is restricted by the current GPU memory, and (2) the large number of targeting labels (e.g., > 100 labels) with limited number of training 3D volumes (e.g., < 50 scans). In this paper, we propose the spatially localized atlas network tiles (SLANT) method to distribute multiple independent 3D fully convolutional networks to cover overlapped sub-spaces in a standard atlas space. This strategy simplifies the whole brain learning task to localized sub-tasks, which was enabled by combing canonical registration and label fusion techniques with deep learning. To address the second challenge, auxiliary labels on 5111 initially unlabeled scans were created by MAS for pre-training. From empirical validation, the state-of-the-art MAS method achieved mean Dice value of 0.76, 0.71, and 0.68, while the proposed method achieved 0.78, 0.73, and 0.71 on three validation cohorts. Moreover, the computational time reduced from > 30 hours using MAS to ~15 minutes using the proposed method. The source code is available online https://github.com/MASILab/SLANTbrainSeg
Tasks	Brain Segmentation
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00546v2
PDF	http://arxiv.org/pdf/1806.00546v2.pdf
PWC	https://paperswithcode.com/paper/spatially-localized-atlas-network-tiles
Repo	https://github.com/MASILab/SLANT_brain_seg
Framework	caffe2

MRI Super-Resolution using Multi-Channel Total Variation


Title	MRI Super-Resolution using Multi-Channel Total Variation
Authors	Mikael Brudfors, Yael Balbastre, Parashkev Nachev, John Ashburner
Abstract	This paper presents a generative model for super-resolution in routine clinical magnetic resonance images (MRI), of arbitrary orientation and contrast. The model recasts the recovery of high resolution images as an inverse problem, in which a forward model simulates the slice-select profile of the MR scanner. The paper introduces a prior based on multi-channel total variation for MRI super-resolution. Bias-variance trade-off is handled by estimating hyper-parameters from the low resolution input scans. The model was validated on a large database of brain images. The validation showed that the model can improve brain segmentation, that it can recover anatomical information between images of different MR contrasts, and that it generalises well to the large variability present in MR images of different subjects. The implementation is freely available at https://github.com/brudfors/spm_superres
Tasks	Brain Segmentation, Super-Resolution
Published	2018-10-08
URL	https://arxiv.org/abs/1810.03422v6
PDF	https://arxiv.org/pdf/1810.03422v6.pdf
PWC	https://paperswithcode.com/paper/mri-super-resolution-using-multi-channel
Repo	https://github.com/brudfors/spm_superres
Framework	none

A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation


Title	A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation
Authors	Mathias Müller, Annette Rios, Elena Voita, Rico Sennrich
Abstract	The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has seen only moderate improvements in terms of automatic evaluation metrics such as BLEU. However, metrics that quantify the overall translation quality are ill-equipped to measure gains from additional context. We argue that a different kind of evaluation is needed to assess how well models translate inter-sentential phenomena such as pronouns. This paper therefore presents a test suite of contrastive translations focused specifically on the translation of pronouns. Furthermore, we perform experiments with several context-aware models. We show that, while gains in BLEU are moderate for those systems, they outperform baselines by a large margin in terms of accuracy on our contrastive test set. Our experiments also show the effectiveness of parameter tying for multi-encoder architectures.
Tasks	Machine Translation
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02268v3
PDF	http://arxiv.org/pdf/1810.02268v3.pdf
PWC	https://paperswithcode.com/paper/a-large-scale-test-set-for-the-evaluation-of
Repo	https://github.com/ZurichNLP/ContraPro
Framework	none

Deep Component Analysis via Alternating Direction Neural Networks


Title	Deep Component Analysis via Alternating Direction Neural Networks
Authors	Calvin Murdock, Ming-Fang Chang, Simon Lucey
Abstract	Despite a lack of theoretical understanding, deep neural networks have achieved unparalleled performance in a wide range of applications. On the other hand, shallow representation learning with component analysis is associated with rich intuition and theory, but smaller capacity often limits its usefulness. To bridge this gap, we introduce Deep Component Analysis (DeepCA), an expressive multilayer model formulation that enforces hierarchical structure through constraints on latent variables in each layer. For inference, we propose a differentiable optimization algorithm implemented using recurrent Alternating Direction Neural Networks (ADNNs) that enable parameter learning using standard backpropagation. By interpreting feed-forward networks as single-iteration approximations of inference in our model, we provide both a novel theoretical perspective for understanding them and a practical technique for constraining predictions with prior knowledge. Experimentally, we demonstrate performance improvements on a variety of tasks, including single-image depth prediction with sparse output constraints.
Tasks	Depth Estimation, Representation Learning
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06407v1
PDF	http://arxiv.org/pdf/1803.06407v1.pdf
PWC	https://paperswithcode.com/paper/deep-component-analysis-via-alternating
Repo	https://github.com/DeadAt0m/DCA-PyTorch
Framework	pytorch

Generative adversarial network-based image super-resolution using perceptual content losses


Title	Generative adversarial network-based image super-resolution using perceptual content losses
Authors	Manri Cheon, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee
Abstract	In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion. Based on good performance of a recently developed model for super-resolution, i.e., deep residual network using enhanced upscale modules (EUSR), the proposed model is trained to improve perceptual performance with only slight increase of distortion. For this purpose, together with the conventional content loss, i.e., reconstruction loss such as L1 or L2, we consider additional losses in the training phase, which are the discrete cosine transform coefficients loss and differential content loss. These consider perceptual part in the content loss, i.e., consideration of proper high frequency components is helpful for the trade-off problem in super-resolution. The experimental results show that our proposed model has good performance for both perception and distortion, and is effective in perceptual super-resolution applications.
Tasks	Image Super-Resolution, Super-Resolution
Published	2018-09-13
URL	http://arxiv.org/abs/1809.04783v2
PDF	http://arxiv.org/pdf/1809.04783v2.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-network-based-image
Repo	https://github.com/manricheon/manricheon.github.io
Framework	tf

CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction


Title	CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
Authors	Chaojun Xiao, Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Zhiyuan Liu, Maosong Sun, Yansong Feng, Xianpei Han, Zhen Hu, Heng Wang, Jianfeng Xu
Abstract	In this paper, we introduce the \textbf{C}hinese \textbf{AI} and \textbf{L}aw challenge dataset (CAIL2018), the first large-scale Chinese legal dataset for judgment prediction. \dataset contains more than $2.6$ million criminal cases published by the Supreme People’s Court of China, which are several times larger than other datasets in existing works on judgment prediction. Moreover, the annotations of judgment results are more detailed and rich. It consists of applicable law articles, charges, and prison terms, which are expected to be inferred according to the fact descriptions of cases. For comparison, we implement several conventional text classification baselines for judgment prediction and experimental results show that it is still a challenge for current models to predict the judgment results of legal cases, especially on prison terms. To help the researchers make improvements on legal judgment prediction, both \dataset and baselines will be released after the CAIL competition\footnote{http://cail.cipsc.org.cn/}.
Tasks	Text Classification
Published	2018-07-04
URL	http://arxiv.org/abs/1807.02478v1
PDF	http://arxiv.org/pdf/1807.02478v1.pdf
PWC	https://paperswithcode.com/paper/cail2018-a-large-scale-legal-dataset-for
Repo	https://github.com/brightmart/ai_law
Framework	tf

DeepTriangle: A Deep Learning Approach to Loss Reserving


Title	DeepTriangle: A Deep Learning Approach to Loss Reserving
Authors	Kevin Kuo
Abstract	We propose a novel approach for loss reserving based on deep neural networks. The approach allows for joint modeling of paid losses and claims outstanding, and incorporation of heterogeneous inputs. We validate the models on loss reserving data across lines of business, and show that they improve on the predictive accuracy of existing stochastic methods. The models require minimal feature engineering and expert input, and can be automated to produce forecasts more frequently than manual workflows.
Tasks	Feature Engineering
Published	2018-04-24
URL	https://arxiv.org/abs/1804.09253v4
PDF	https://arxiv.org/pdf/1804.09253v4.pdf
PWC	https://paperswithcode.com/paper/deeptriangle-a-deep-learning-approach-to-loss
Repo	https://github.com/kevinykuo/deeptriangle
Framework	none

Extracting Universal Representations of Cognition across Brain-Imaging Studies


Title	Extracting Universal Representations of Cognition across Brain-Imaging Studies
Authors	Arthur Mensch, Julien Mairal, Bertrand Thirion, Gaël Varoquaux
Abstract	We show in this paper how to extract shared brain representations that predict mental processes across many cognitive neuroimaging studies. Focused cognitive-neuroimaging experiments study precise mental processes with carefully-designed cognitive paradigms; however the cost of imaging limits their statistical power. On the other hand, large-scale databasing efforts increase considerably the sample sizes, but cannot ask precise cognitive questions. To address this tension, we develop new methods that turn the heterogeneous cognitive information held in different task-fMRI studies into common-universal-cognitive models. Our approach does not assume any prior knowledge of the commonalities shared by the studies in the corpus; those are inferred during model training. The method uses deep-learning techniques to extract representations - task-optimized networks - that form a set of basis cognitive dimensions relevant to the psychological manipulations. In this sense, it forms a novel kind of functional atlas, optimized to capture mental state across many functional-imaging experiments. As it bridges information on the neural support of mental processes, this representation improves decoding performance for 80% of the 35 widely-different functional imaging studies that we consider. Our approach opens new ways of extracting information from brain maps, increasing statistical power even for focused cognitive neuroimaging studies, in particular for those with few subjects.
Tasks
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06035v2
PDF	http://arxiv.org/pdf/1809.06035v2.pdf
PWC	https://paperswithcode.com/paper/extracting-universal-representations-of
Repo	https://github.com/arthurmensch/cogspaces
Framework	none

Learning to Estimate Indoor Lighting from 3D Objects


Title	Learning to Estimate Indoor Lighting from 3D Objects
Authors	Henrique Weber, Donald Prévost, Jean-François Lalonde
Abstract	In this work, we propose a step towards a more accurate prediction of the environment light given a single picture of a known object. To achieve this, we developed a deep learning method that is able to encode the latent space of indoor lighting using few parameters and that is trained on a database of environment maps. This latent space is then used to generate predictions of the light that are both more realistic and accurate than previous methods. To achieve this, our first contribution is a deep autoencoder which is capable of learning the feature space that compactly models lighting. Our second contribution is a convolutional neural network that predicts the light from a single image of a known object. To train these networks, our third contribution is a novel dataset that contains 21,000 HDR indoor environment maps. The results indicate that the predictor can generate plausible lighting estimations even from diffuse objects.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03994v3
PDF	http://arxiv.org/pdf/1806.03994v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-estimate-indoor-lighting-from-3d
Repo	https://github.com/weberhen/learning_indoor_lighting
Framework	pytorch

Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees


Title	Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees
Authors	Viraj Shah, Chinmay Hegde
Abstract	In recent works, both sparsity-based methods as well as learning-based methods have proven to be successful in solving several challenging linear inverse problems. However, sparsity priors for natural signals and images suffer from poor discriminative capability, while learning-based methods seldom provide concrete theoretical guarantees. In this work, we advocate the idea of replacing hand-crafted priors, such as sparsity, with a Generative Adversarial Network (GAN) to solve linear inverse problems such as compressive sensing. In particular, we propose a projected gradient descent (PGD) algorithm for effective use of GAN priors for linear inverse problems, and also provide theoretical guarantees on the rate of convergence of this algorithm. Moreover, we show empirically that our algorithm demonstrates superior performance over an existing method of leveraging GANs for compressive sensing.
Tasks	Compressive Sensing
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08406v1
PDF	http://arxiv.org/pdf/1802.08406v1.pdf
PWC	https://paperswithcode.com/paper/solving-linear-inverse-problems-using-gan
Repo	https://github.com/shahviraj/pgdgan
Framework	tf

A fast algorithm with minimax optimal guarantees for topic models with an unknown number of topics


Title	A fast algorithm with minimax optimal guarantees for topic models with an unknown number of topics
Authors	Xin Bing, Florentina Bunea, Marten Wegkamp
Abstract	We propose a new method of estimation in topic models, that is not a variation on the existing simplex finding algorithms, and that estimates the number of topics K from the observed data. We derive new finite sample minimax lower bounds for the estimation of A, as well as new upper bounds for our proposed estimator. We describe the scenarios where our estimator is minimax adaptive. Our finite sample analysis is valid for any number of documents (n), individual document length (N_i), dictionary size (p) and number of topics (K), and both p and K are allowed to increase with n, a situation not handled well by previous analyses. We complement our theoretical results with a detailed simulation study. We illustrate that the new algorithm is faster and more accurate than the current ones, although we start out with a computational and theoretical disadvantage of not knowing the correct number of topics K, while we provide the competing methods with the correct value in our simulations.
Tasks	Topic Models
Published	2018-05-17
URL	https://arxiv.org/abs/1805.06837v3
PDF	https://arxiv.org/pdf/1805.06837v3.pdf
PWC	https://paperswithcode.com/paper/a-fast-algorithm-with-minimax-optimal
Repo	https://github.com/zihao12/Top_Experiments
Framework	none

Semantic Binary Segmentation using Convolutional Networks without Decoders


Title	Semantic Binary Segmentation using Convolutional Networks without Decoders
Authors	Shubhra Aich, William van der Kamp, Ian Stavness
Abstract	In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation. Our D2S model is comprised of a standard CNN encoder followed by a depth-to-space reordering of the final convolutional feature maps. Our approach eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half. As a participant of the DeepGlobe Road Extraction competition, we evaluate our models on the corresponding road segmentation dataset. Our highly efficient D2S models exhibit comparable performance to standard segmentation models with much lower computational cost.
Tasks	Semantic Segmentation
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00138v2
PDF	http://arxiv.org/pdf/1805.00138v2.pdf
PWC	https://paperswithcode.com/paper/semantic-binary-segmentation-using
Repo	https://github.com/littleaich/deepglobe2018
Framework	pytorch

NAM: Non-Adversarial Unsupervised Domain Mapping


Title	NAM: Non-Adversarial Unsupervised Domain Mapping
Authors	Yedid Hoshen, Lior Wolf
Abstract	Several methods were recently proposed for the task of translating images between domains without prior knowledge in the form of correspondences. The existing methods apply adversarial learning to ensure that the distribution of the mapped source domain is indistinguishable from the target domain, which suffers from known stability issues. In addition, most methods rely heavily on `cycle’ relationships between the domains, which enforce a one-to-one mapping. In this work, we introduce an alternative method: Non-Adversarial Mapping (NAM), which separates the task of target domain generative modeling from the cross-domain mapping task. NAM relies on a pre-trained generative model of the target domain, and aligns each source image with an image synthesized from the target domain, while jointly optimizing the domain mapping function. It has several key advantages: higher quality and resolution image translations, simpler and more stable training and reusable target models. Extensive experiments are presented validating the advantages of our method. \|
Tasks
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00804v2
PDF	http://arxiv.org/pdf/1806.00804v2.pdf
PWC	https://paperswithcode.com/paper/nam-non-adversarial-unsupervised-domain
Repo	https://github.com/facebookresearch/NAM
Framework	pytorch


Title	Sentence Embeddings in NLI with Iterative Refinement Encoders
Authors	Aarne Talman, Anssi Yli-Jyrä, Jörg Tiedemann
Abstract	Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We build on top of one such model and propose a hierarchy of BiLSTM and max pooling layers that implements an iterative refinement strategy and yields state of the art results on the SciTail dataset as well as strong results for SNLI and MultiNLI. We can show that the sentence embeddings learned in this way can be utilized in a wide variety of transfer learning tasks, outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval sentence embedding evaluation tasks. Furthermore, our model beats the InferSent model in 8 out of 10 recently published SentEval probing tasks designed to evaluate sentence embeddings’ ability to capture some of the important linguistic properties of sentences.
Tasks	Natural Language Inference, Sentence Embedding, Sentence Embeddings, Transfer Learning
Published	2018-08-27
URL	https://arxiv.org/abs/1808.08762v2
PDF	https://arxiv.org/pdf/1808.08762v2.pdf
PWC	https://paperswithcode.com/paper/natural-language-inference-with-hierarchical
Repo	https://github.com/Helsinki-NLP/HBMP
Framework	pytorch