January 28, 2020

3174 words 15 mins read

Paper Group ANR 883

Towards Unsupervised Grammatical Error Correction using Statistical Machine Translation with Synthetic Comparable Corpus. A Randomized Algorithm for Preconditioner Selection. DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare. Distributionally Robust Multi-instance Learning with Stable Instances. Kernel-Guided Training of Impl …

Towards Unsupervised Grammatical Error Correction using Statistical Machine Translation with Synthetic Comparable Corpus


Title	Towards Unsupervised Grammatical Error Correction using Statistical Machine Translation with Synthetic Comparable Corpus
Authors	Satoru Katsumata, Mamoru Komachi
Abstract	We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through experiments on various GEC dataset, includi ng a low resource track of the shared task at Building Educational Applications 2019 (BEA 2019). As a result, we achieved an F_0.5 score of 28.31 points with the test data of the low resource track.
Tasks	Grammatical Error Correction, Machine Translation
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09724v1
PDF	https://arxiv.org/pdf/1907.09724v1.pdf
PWC	https://paperswithcode.com/paper/towards-unsupervised-grammatical-error
Repo
Framework

A Randomized Algorithm for Preconditioner Selection


Title	A Randomized Algorithm for Preconditioner Selection
Authors	Conner DiPaolo, Weiqing Gu
Abstract	The task of choosing a preconditioner $\boldsymbol{M}$ to use when solving a linear system $\boldsymbol{Ax}=\boldsymbol{b}$ with iterative methods is difficult. For instance, even if one has access to a collection $\boldsymbol{M}_1,\boldsymbol{M}_2,\ldots,\boldsymbol{M}_n$ of candidate preconditioners, it is currently unclear how to practically choose the $\boldsymbol{M}_i$ which minimizes the number of iterations of an iterative algorithm to achieve a suitable approximation to $\boldsymbol{x}$. This paper makes progress on this sub-problem by showing that the preconditioner stability $\boldsymbol{I}-\boldsymbol{M}^{-1}\boldsymbol{A}_\mathsf{F}$, known to forecast preconditioner quality, can be computed in the time it takes to run a constant number of iterations of conjugate gradients through use of sketching methods. This is in spite of folklore which suggests the quantity is impractical to compute, and a proof we give that ensures the quantity could not possibly be approximated in a useful amount of time by a deterministic algorithm. Using our estimator, we provide a method which can provably select the minimal stability preconditioner among $n$ candidates using floating point operations commensurate with running on the order of $n\log n$ steps of the conjugate gradients algorithm. Our method can also advise the practitioner to use no preconditioner at all if none of the candidates appears useful. The algorithm is extremely easy to implement and trivially parallelizable. In one of our experiments, we use our preconditioner selection algorithm to create to the best of our knowledge the first preconditioned method for kernel regression reported to never use more iterations than the non-preconditioned analog in standard tests.
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00633v1
PDF	https://arxiv.org/pdf/1908.00633v1.pdf
PWC	https://paperswithcode.com/paper/a-randomized-algorithm-for-preconditioner
Repo
Framework

DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare


Title	DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
Authors	Yuanlu Xu, Song-Chun Zhu, Tony Tung
Abstract	We present DenseRaC, a novel end-to-end framework for jointly estimating 3D human pose and body shape from a monocular RGB image. Our two-step framework takes the body pixel-to-surface correspondence map (i.e., IUV map) as proxy representation and then performs estimation of parameterized human pose and shape. Specifically, given an estimated IUV map, we develop a deep neural network optimizing 3D body reconstruction losses and further integrating a render-and-compare scheme to minimize differences between the input and the rendered output, i.e., dense body landmarks, body part masks, and adversarial priors. To boost learning, we further construct a large-scale synthetic dataset (MOCA) utilizing web-crawled Mocap sequences, 3D scans and animations. The generated data covers diversified camera views, human actions and body shapes, and is paired with full ground truth. Our model jointly learns to represent the 3D human body from hybrid datasets, mitigating the problem of unpaired training data. Our experiments show that DenseRaC obtains superior performance against state of the art on public benchmarks of various humanrelated tasks.
Tasks	3D Human Pose Estimation
Published	2019-09-30
URL	https://arxiv.org/abs/1910.00116v2
PDF	https://arxiv.org/pdf/1910.00116v2.pdf
PWC	https://paperswithcode.com/paper/denserac-joint-3d-pose-and-shape-estimation
Repo
Framework

Distributionally Robust Multi-instance Learning with Stable Instances


Title	Distributionally Robust Multi-instance Learning with Stable Instances
Authors	Weijia Zhang, Jiuyong Li, Lin Liu
Abstract	Multi-instance learning (MIL) deals with tasks where data consist of set of bags and each bag is represented by a set of instances. Only the bag labels are observed but the label for each instance is not available. Previous MIL studies typically assume that the training and test samples follow the same distribution, which is often violated in real-world applications. Existing methods address distribution changes by re-weighting the training data with the density ratio between the training and test samples. However, models are often trained without prior knowledge of the test distribution which renders existing methods inapplicable. Inspired by a connection between MIL and causal inference, we propose a novel framework for addressing distribution change in MIL without relying on the test distribution. Experimental results validate the effectiveness of our approach.
Tasks	Causal Inference
Published	2019-02-13
URL	https://arxiv.org/abs/1902.05066v4
PDF	https://arxiv.org/pdf/1902.05066v4.pdf
PWC	https://paperswithcode.com/paper/distributionally-robust-multi-instance
Repo
Framework

Kernel-Guided Training of Implicit Generative Models with Stability Guarantees


Title	Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
Authors	Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet, Bernhard Schölkopf
Abstract	Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance. If we see these implicit models as dynamical systems, some of these issues are caused by being unable to control their behavior in a meaningful way during the course of training. In this work, we propose a theoretically grounded method to guide the training trajectories of GANs by augmenting the GAN loss function with a kernel-based regularization term that controls local and global discrepancies between the model and true distributions. This control signal allows us to inject prior knowledge into the model. We provide theoretical guarantees on the stability of the resulting dynamical system and demonstrate different aspects of it via a wide range of experiments.
Tasks
Published	2019-01-26
URL	https://arxiv.org/abs/1901.09206v2
PDF	https://arxiv.org/pdf/1901.09206v2.pdf
PWC	https://paperswithcode.com/paper/witnessing-adversarial-training-in
Repo
Framework

Learnability for the Information Bottleneck


Title	Learnability for the Information Bottleneck
Authors	Tailin Wu, Ian Fischer, Isaac L. Chuang, Max Tegmark
Abstract	The Information Bottleneck (IB) method (\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\beta I(Y;Z)$ employs a Lagrange multiplier $\beta$ to tune this trade-off. However, in practice, not only is $\beta$ chosen empirically without theoretical guidance, there is also a lack of theoretical understanding between $\beta$, learnability, the intrinsic nature of the dataset and model capacity. In this paper, we show that if $\beta$ is improperly chosen, learning cannot happen – the trivial representation $P(ZX)=P(Z)$ becomes the global minimum of the IB objective. We show how this can be avoided, by identifying a sharp phase transition between the unlearnable and the learnable which arises as $\beta$ is varied. This phase transition defines the concept of IB-Learnability. We prove several sufficient conditions for IB-Learnability, which provides theoretical guidance for choosing a good $\beta$. We further show that IB-learnability is determined by the largest confident, typical, and imbalanced subset of the examples (the conspicuous subset), and discuss its relation with model capacity. We give practical algorithms to estimate the minimum $\beta$ for a given dataset. We also empirically demonstrate our theoretical conditions with analyses of synthetic datasets, MNIST, and CIFAR10.
Tasks	Representation Learning
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07331v1
PDF	https://arxiv.org/pdf/1907.07331v1.pdf
PWC	https://paperswithcode.com/paper/learnability-for-the-information-bottleneck
Repo
Framework

Learning to combine Grammatical Error Corrections


Title	Learning to combine Grammatical Error Corrections
Authors	Yoav Kantor, Yoav Katz, Leshem Choshen, Edo Cohen-Karlik, Naftali Liberman, Assaf Toledo, Amir Menczel, Noam Slonim
Abstract	The field of Grammatical Error Correction (GEC) has produced various systems to deal with focused phenomena or general text editing. We propose an automatic way to combine black-box systems. Our method automatically detects the strength of a system or the combination of several systems per error type, improving precision and recall while optimizing $F$ score directly. We show consistent improvement over the best standalone system in all the configurations tested. This approach also outperforms average ensembling of different RNN models with random initializations. In addition, we analyze the use of BERT for GEC - reporting promising results on this end. We also present a spellchecker created for this task which outperforms standard spellcheckers tested on the task of spellchecking. This paper describes a system submission to Building Educational Applications 2019 Shared Task: Grammatical Error Correction. Combining the output of top BEA 2019 shared task systems using our approach, currently holds the highest reported score in the open phase of the BEA 2019 shared task, improving F0.5 by 3.7 points over the best result reported.
Tasks	Grammatical Error Correction
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03897v1
PDF	https://arxiv.org/pdf/1906.03897v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-combine-grammatical-error
Repo
Framework


Title	Keyphrase Extraction from Disaster-related Tweets
Authors	Jishnu Ray Chowdhury, Cornelia Caragea, Doina Caragea
Abstract	While keyphrase extraction has received considerable attention in recent years, relatively few studies exist on extracting keyphrases from social media platforms such as Twitter, and even fewer for extracting disaster-related keyphrases from such sources. During a disaster, keyphrases can be extremely useful for filtering relevant tweets that can enhance situational awareness. Previously, joint training of two different layers of a stacked Recurrent Neural Network for keyword discovery and keyphrase extraction had been shown to be effective in extracting keyphrases from general Twitter data. We improve the model’s performance on both general Twitter data and disaster-related Twitter data by incorporating contextual word embeddings, POS-tags, phonetics, and phonological features. Moreover, we discuss the shortcomings of the often used F1-measure for evaluating the quality of predicted keyphrases with respect to the ground truth annotations. Instead of the F1-measure, we propose the use of embedding-based metrics to better capture the correctness of the predicted keyphrases. In addition, we also present a novel extension of an embedding-based metric. The extension allows one to better control the penalty for the difference in the number of ground-truth and predicted keyphrases
Tasks	Word Embeddings
Published	2019-10-17
URL	https://arxiv.org/abs/1910.07897v1
PDF	https://arxiv.org/pdf/1910.07897v1.pdf
PWC	https://paperswithcode.com/paper/keyphrase-extraction-from-disaster-related
Repo
Framework

Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions


Title	Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
Authors	Upol Ehsan, Pradyumna Tambwekar, Larry Chan, Brent Harrison, Mark Riedl
Abstract	Automated rationale generation is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent’s internal state and action data representations into natural language. Training on human explanation data can enable agents to learn to generate human-like explanations for their behavior. In this paper, using the context of an agent that plays Frogger, we describe (a) how to collect a corpus of explanations, (b) how to train a neural rationale generator to produce different styles of rationales, and (c) how people perceive these rationales. We conducted two user studies. The first study establishes the plausibility of each type of generated rationale and situates their user perceptions along the dimensions of confidence, humanlike-ness, adequate justification, and understandability. The second study further explores user preferences between the generated rationales with regard to confidence in the autonomous agent, communicating failure and unexpected behavior. Overall, we find alignment between the intended differences in features of the generated rationales and the perceived differences by users. Moreover, context permitting, participants preferred detailed rationales to form a stable mental model of the agent’s behavior.
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03729v1
PDF	http://arxiv.org/pdf/1901.03729v1.pdf
PWC	https://paperswithcode.com/paper/automated-rationale-generation-a-technique
Repo
Framework

Joint Demosaicking and Denoising by Fine-Tuning of Bursts of Raw Images


Title	Joint Demosaicking and Denoising by Fine-Tuning of Bursts of Raw Images
Authors	Thibaud Ehret, Axel Davy, Pablo Arias, Gabriele Facciolo
Abstract	Demosaicking and denoising are the first steps of any camera image processing pipeline and are key for obtaining high quality RGB images. A promising current research trend aims at solving these two problems jointly using convolutional neural networks. Due to the unavailability of ground truth data these networks cannot be currently trained using real RAW images. Instead, they resort to simulated data. In this paper we present a method to learn demosaicking directly from mosaicked images, without requiring ground truth RGB data. We apply this to learn joint demosaicking and denoising only from RAW images, thus enabling the use of real data. In addition we show that for this application fine-tuning a network to a specific burst improves the quality of restoration for both demosaicking and denoising.
Tasks	Demosaicking, Denoising
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05092v2
PDF	https://arxiv.org/pdf/1905.05092v2.pdf
PWC	https://paperswithcode.com/paper/joint-demosaicing-and-denoising-by
Repo
Framework

A2: Extracting Cyclic Switchings from DOB-nets for Rejecting Excessive Disturbances


Title	A2: Extracting Cyclic Switchings from DOB-nets for Rejecting Excessive Disturbances
Authors	Wenjie Lu, Dikai Liu
Abstract	Reinforcement Learning (RL) is limited in practice by its gray-box nature, which is responsible for insufficient trustiness from users, unsatisfied interpretation for human intervention, inadequate analysis for future improvement, etc. This paper seeks to partially characterize the interplay between dynamical environments and the DOB-net. The DOB-net obtained from RL solves a set of Partially Observable Markovian Decision Processes (POMDPs). The transition function of each POMDP is largely determined by the environments, which are excessive external disturbances in this research. This paper proposes an Attention-based Abstraction (A${}^2$) approach to extract a finite-state automaton, referred to as a Key Moore Machine Network (KMMN), to capture the switching mechanisms exhibited by the DOB-net in dealing with multiple such POMDPs. This approach first quantizes the controlled platform by learning continuous-discrete interfaces. Then it extracts the KMMN by finding the key hidden states and transitions that attract sufficient attention from the DOB-net. Within the resultant KMMN, this study found three patterns of cyclic switchings (between key hidden states), showing controls near their saturation are synchronized with unknown disturbances. Interestingly, the found switching mechanism has appeared previously in the design of hybrid control for often-saturated systems. It is further interpreted via an analogy to the discrete-event subsystem in the hybrid control.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00165v1
PDF	https://arxiv.org/pdf/1911.00165v1.pdf
PWC	https://paperswithcode.com/paper/a2-extracting-cyclic-switchings-from-dob-nets
Repo
Framework

ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset


Title	ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset
Authors	Guiying Zhang, Yuxin Cui, Yong Zhao, Jianjun Hu
Abstract	State-of-the-art face recognition algorithms are able to achieve good performance when sufficient training images are provided. Unfortunately, the number of facial images is limited in some real face recognition applications. In this paper, we propose ComplexFace, a novel and effective algorithm for face recognition with limited samples using complex number based data augmentation. The algorithm first generates new representations from original samples and then fuse both into complex numbers, which avoids the difficulty of weight setting in other fusion approaches. A test sample can then be expressed by the linear combination of all the training samples, which mapped the sample to the new representation space for classification by the kernel function. The collaborative representation based classifier is then built to make predictions. Extensive experiments on the Georgia Tech (GT) face database and the ORL face database show that our algorithm significantly outperforms existing methods: the average errors of previous approaches ranging from 31.66% to 41.75% are reduced to 14.54% over the GT database; the average errors of previous approaches ranging from 5.21% to 10.99% are reduced to 1.67% over the ORL database. In other words, our algorithm has decreased the average errors by up to 84.80% on the ORL database.
Tasks	Data Augmentation, Face Recognition, Image Classification
Published	2019-02-21
URL	http://arxiv.org/abs/1902.07902v1
PDF	http://arxiv.org/pdf/1902.07902v1.pdf
PWC	https://paperswithcode.com/paper/complexface-a-multi-representation-approach
Repo
Framework

Joint Learning of Self-Representation and Indicator for Multi-View Image Clustering


Title	Joint Learning of Self-Representation and Indicator for Multi-View Image Clustering
Authors	Songsong Wu, Zhiqiang Lu, Hao Tang, Yan Yan, Songhao Zhu, Xiao-Yuan Jing, Zuoyong Li
Abstract	Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure. Although the spectral clustering based methods achieve promotion in multi-view clustering, their utility is limited by the separate learning manner in which affinity matrix construction and cluster indicator estimation are isolated. In this paper, we propose to jointly learn the self-representation, continue and discrete cluster indicators in an unified model. Our model can explore the subspace structure of each view and fusion them to facilitate clustering simultaneously. Experimental results on two benchmark datasets demonstrate that our method outperforms other existing competitive multi-view clustering methods.
Tasks	Image Clustering, Multi-view Subspace Clustering
Published	2019-05-11
URL	https://arxiv.org/abs/1905.04432v1
PDF	https://arxiv.org/pdf/1905.04432v1.pdf
PWC	https://paperswithcode.com/paper/joint-learning-of-self-representation-and
Repo
Framework

Universal Barcode Detector via Semantic Segmentation


Title	Universal Barcode Detector via Semantic Segmentation
Authors	Andrey Zharkov, Ivan Zagaynov
Abstract	Barcodes are used in many commercial applications, thus fast and robust reading is important. There are many different types of barcodes, some of them look similar while others are completely different. In this paper we introduce new fast and robust deep learning detector based on semantic segmentation approach. It is capable of detecting barcodes of any type simultaneously both in the document scans and in the wild by means of a single model. The detector achieves state-of-the-art results on the ArTe-Lab 1D Medium Barcode Dataset with detection rate 0.995. Moreover, developed detector can deal with more complicated object shapes like very long but narrow or very small barcodes. The proposed approach can also identify types of detected barcodes and performs at real-time speed on CPU environment being much faster than previous state-of-the-art approaches.
Tasks	Semantic Segmentation
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06281v2
PDF	https://arxiv.org/pdf/1906.06281v2.pdf
PWC	https://paperswithcode.com/paper/universal-barcode-detector-via-semantic
Repo
Framework

Learning Software Configuration Spaces: A Systematic Literature Review


Title	Learning Software Configuration Spaces: A Systematic Literature Review
Authors	Juliana Alves Pereira, Hugo Martin, Mathieu Acher, Jean-Marc Jézéquel, Goetz Botterweck, Anthony Ventresque
Abstract	Most modern software systems (operating systems like Linux or Android, Web browsers like Firefox or Chrome, video encoders like ffmpeg, x264 or VLC, mobile and cloud applications, etc.) are highly-configurable. Hundreds of configuration options, features, or plugins can be combined, each potentially with distinct functionality and effects on execution time, security, energy consumption, etc. Due to the combinatorial explosion and the cost of executing software, it is quickly impossible to exhaustively explore the whole configuration space. Hence, numerous works have investigated the idea of learning it from a small sample of configurations’ measurements. The pattern “sampling, measuring, learning” has emerged in the literature, with several practical interests for both software developers and end-users of configurable systems. In this survey, we report on the different application objectives (e.g., performance prediction, configuration optimization, constraint mining), use-cases, targeted software systems and application domains. We review the various strategies employed to gather a representative and cost-effective sample. We describe automated software techniques used to measure functional and non-functional properties of configurations. We classify machine learning algorithms and how they relate to the pursued application. Finally, we also describe how researchers evaluate the quality of the learning process. The findings from this systematic review show that the potential application objective is important; there are a vast number of case studies reported in the literature from the basis of several domains and software systems. Yet, the huge variant space of configurable systems is still challenging and calls to further investigate the synergies between artificial intelligence and software engineering.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03018v1
PDF	https://arxiv.org/pdf/1906.03018v1.pdf
PWC	https://paperswithcode.com/paper/learning-software-configuration-spaces-a
Repo
Framework