October 15, 2019

2292 words 11 mins read

Paper Group NANR 86

Paper Group NANR 86

Denoising Time Series Data Using Asymmetric Generative Adversarial Networks. Differentially Private Robust Low-Rank Approximation. Understanding the Effect of Gender and Stance in Opinion Expression in Debates on ``Abortion’'. AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos. Universal Dependencies and Quantitative Typolo …

Denoising Time Series Data Using Asymmetric Generative Adversarial Networks

Title Denoising Time Series Data Using Asymmetric Generative Adversarial Networks
Authors Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, David Hairston
Abstract Denoising data is a preprocessing step for several time series mining algorithms. This step is especially important if the noise in data originates from diverse sources. Consequently, it is commonly used in biomedical applications that use Electroencephalography (EEG) data. In EEG data noise can occur due to ocular, muscular and cardiac activities. In this paper, we explicitly learn to remove noise from time series data without assuming a prior distribution of noise. We propose an online, fully automated, end-to-end system for denoising time series data. Our model for denoising time series is trained using unpaired training corpora and does not need information about the source of the noise or how it is manifested in the time series. We propose a new architecture called AsymmetricGAN that uses a generative adversarial network for denoising time series data. To analyze our approach, we create a synthetic dataset that is easy to visualize and interpret. We also evaluate and show the effectiveness of our approach on an existing EEG dataset.
Tasks Denoising, EEG, EEG Denoising, Time Series
Published 2018-06-17
URL https://doi.org/10.1007/978-3-319-93040-4_23
PDF https://www.researchgate.net/publication/325808737_Denoising_Time_Series_Data_Using_Asymmetric_Generative_Adversarial_Networks
PWC https://paperswithcode.com/paper/denoising-time-series-data-using-asymmetric
Repo
Framework

Differentially Private Robust Low-Rank Approximation

Title Differentially Private Robust Low-Rank Approximation
Authors Raman Arora, Vladimir Braverman, Jalaj Upadhyay
Abstract In this paper, we study the following robust low-rank matrix approximation problem: given a matrix $A \in \R^{n \times d}$, find a rank-$k$ matrix $B$, while satisfying differential privacy, such that $ \norm{ A - B }_p \leq \alpha \mathsf{OPT}_k(A) + \tau,$ where $\norm{ M }_p$ is the entry-wise $\ell_p$-norm and $\mathsf{OPT}k(A):=\min{\mathsf{rank}(X) \leq k} \norm{ A - X}_p$. It is well known that low-rank approximation w.r.t. entrywise $\ell_p$-norm, for $p \in [1,2)$, yields robustness to gross outliers in the data. We propose an algorithm that guarantees $\alpha=\widetilde{O}(k^2), \tau=\widetilde{O}(k^2(n+kd)/\varepsilon)$, runs in $\widetilde O((n+d)\poly~k)$ time and uses $O(k(n+d)\log k)$ space. We study extensions to the streaming setting where entries of the matrix arrive in an arbitrary order and output is produced at the very end or continually. We also study the related problem of differentially private robust principal component analysis (PCA), wherein we return a rank-$k$ projection matrix $\Pi$ such that $\norm{ A - A \Pi }_p \leq \alpha \mathsf{OPT}_k(A) + \tau.$
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7668-differentially-private-robust-low-rank-approximation
PDF http://papers.nips.cc/paper/7668-differentially-private-robust-low-rank-approximation.pdf
PWC https://paperswithcode.com/paper/differentially-private-robust-low-rank
Repo
Framework

Understanding the Effect of Gender and Stance in Opinion Expression in Debates on ``Abortion’’

Title Understanding the Effect of Gender and Stance in Opinion Expression in Debates on ``Abortion’’ |
Authors Esin Durmus, Claire Cardie
Abstract In this paper, we focus on understanding linguistic differences across groups with different self-identified gender and stance in expressing opinions about ABORTION. We provide a new dataset consisting of users{'} gender, stance on ABORTION as well as the debates in ABORTION drawn from debate.org. We use the gender and stance information to identify significant linguistic differences across individuals with different gender and stance. We show the importance of considering the stance information along with the gender since we observe significant linguistic differences across individuals with different stance even within the same gender group.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1110/
PDF https://www.aclweb.org/anthology/W18-1110
PWC https://paperswithcode.com/paper/understanding-the-effect-of-gender-and-stance
Repo
Framework

AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos

Title AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos
Authors Zheng Shou, Hang Gao, Lei Zhang, Kazuyuki Miyazawa, Shih-Fu Chang
Abstract Temporal Action Localization (TAL) in untrimmed video is important for many applications. But it is very expensive to annotate the segment-level ground truth (action class and temporal boundary). This raises the interest of addressing TAL with weak supervision, namely only video-level annotations are available during training). However, the state-of-the-art weakly-supervised TAL methods only focus on generating good Class Activation Sequence (CAS) over time but conduct simple thresholding on CAS to localize actions. In this paper, we first develop a novel weakly-supervised TAL framework called AutoLoc to directly predict the temporal boundary of each action instance. We propose a novel Outer-Inner-Contrastive (OIC) loss to automatically discover the needed segment-level supervision for training such a boundary predictor. Our method achieves dramatically improved performance: under the IoU threshold 0.5, our method improves mAP on THUMOS’14 from 13.7% to 21.2% and mAP on ActivityNet from 7.4% to 27.3%. It is also very encouraging to see that our weakly-supervised method achieves comparable results with some fully-supervised methods.
Tasks Action Localization, Temporal Action Localization, Weakly Supervised Action Localization, Weakly-supervised Temporal Action Localization
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Zheng_Shou_AutoLoc_Weakly-supervised_Temporal_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Zheng_Shou_AutoLoc_Weakly-supervised_Temporal_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/autoloc-weakly-supervised-temporal-action-1
Repo
Framework
Title Universal Dependencies and Quantitative Typological Trends. A Case Study on Word Order
Authors Chiara Alzetta, Felice Dell{'}Orletta, Simonetta Montemagni, Giulia Venturi
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1719/
PDF https://www.aclweb.org/anthology/L18-1719
PWC https://paperswithcode.com/paper/universal-dependencies-and-quantitative
Repo
Framework

Limited Memory Kelley’s Method Converges for Composite Convex and Submodular Objectives

Title Limited Memory Kelley’s Method Converges for Composite Convex and Submodular Objectives
Authors Song Zhou, Swati Gupta, Madeleine Udell
Abstract The original simplicial method (OSM), a variant of the classic Kelley’s cutting plane method, has been shown to converge to the minimizer of a composite convex and submodular objective, though no rate of convergence for this method was known. Moreover, OSM is required to solve subproblems in each iteration whose size grows linearly in the number of iterations. We propose a limited memory version of Kelley’s method (L-KM) and of OSM that requires limited memory (at most n+ 1 constraints for an n-dimensional problem) independent of the iteration. We prove convergence for L-KM when the convex part of the objective g is strongly convex and show it converges linearly when g is also smooth. Our analysis relies on duality between minimization of the composite convex and submodular objective and minimization of a convex function over the submodular base polytope. We introduce a limited memory version, L-FCFW, of the Fully-Corrective Frank-Wolfe (FCFW) method with approximate correction, to solve the dual problem. We show that L-FCFW and L-KM are dual algorithms that produce the same sequence of iterates; hence both converge linearly (when g is smooth and strongly convex) and with limited memory. We propose L-KM to minimize composite convex and submodular objectives; however, our results on L-FCFW hold for general polytopes and may be of independent interest.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7694-limited-memory-kelleys-method-converges-for-composite-convex-and-submodular-objectives
PDF http://papers.nips.cc/paper/7694-limited-memory-kelleys-method-converges-for-composite-convex-and-submodular-objectives.pdf
PWC https://paperswithcode.com/paper/limited-memory-kelleys-method-converges-for
Repo
Framework

Simple Neologism Based Domain Independent Models to Predict Year of Authorship

Title Simple Neologism Based Domain Independent Models to Predict Year of Authorship
Authors Vivek Kulkarni, Yingtao Tian, D, Parth iwala, Steve Skiena
Abstract We present domain independent models to date documents based only on neologism usage patterns. Our models capture patterns of neologism usage over time to date texts, provide insights into temporal locality of word usage over a span of 150 years, and generalize to various domains like News, Fiction, and Non-Fiction with competitive performance. Quite intriguingly, we show that by modeling only the distribution of usage counts over neologisms (the model being agnostic of the particular words themselves), we achieve competitive performance using several orders of magnitude fewer features (only 200 input features) compared to state of the art models some of which use 200K features.
Tasks Domain Adaptation, Information Retrieval
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1017/
PDF https://www.aclweb.org/anthology/C18-1017
PWC https://paperswithcode.com/paper/simple-neologism-based-domain-independent
Repo
Framework

Inverse Composition Discriminative Optimization for Point Cloud Registration

Title Inverse Composition Discriminative Optimization for Point Cloud Registration
Authors Jayakorn Vongkulbhisal, Beñat Irastorza Ugalde, Fernando De la Torre, João P. Costeira
Abstract Rigid Point Cloud Registration (PCReg) refers to the problem of finding the rigid transformation between two sets of point clouds. This problem is particularly important due to the advances in new 3D sensing hardware, and it is challenging because neither the correspondence nor the transformation parameters are known. Traditional local PCReg methods (e.g., ICP) rely on local optimization algorithms, which can get trapped in bad local minima in the presence of noise, outliers, bad initializations, etc. To alleviate these issues, this paper proposes Inverse Composition Discriminative Optimization (ICDO), an extension of Discriminative Optimization (DO), which learns a sequence of update steps from synthetic training data that search the parameter space for an improved solution. Unlike DO, ICDO is object-independent and generalizes even to unseen shapes. We evaluated ICDO on both synthetic and real data, and show that ICDO can match the speed and outperform the accuracy of state-of-the-art PCReg algorithms.
Tasks Point Cloud Registration
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Vongkulbhisal_Inverse_Composition_Discriminative_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Vongkulbhisal_Inverse_Composition_Discriminative_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/inverse-composition-discriminative
Repo
Framework

The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task

Title The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task
Authors Noe Casas, Carlos Escolano, Marta R. Costa-juss{`a}, Jos{'e} A. R. Fonollosa
Abstract In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for Finnish-English and Estonian-English within the multi-lingual subtrack. All of our primary submissions implement an attention-based Neural Machine Translation architecture. Given that Finnish and Estonian belong to the same language family and are similar, we use as training data the combination of the datasets of both language pairs to paliate the data scarceness of each individual pair. We also report the translation quality of systems trained on individual language pair data to serve as baseline and comparison reference.
Tasks Machine Translation
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6406/
PDF https://www.aclweb.org/anthology/W18-6406
PWC https://paperswithcode.com/paper/the-talp-upc-machine-translation-systems-for
Repo
Framework

Interpretable Emoji Prediction via Label-Wise Attention LSTMs

Title Interpretable Emoji Prediction via Label-Wise Attention LSTMs
Authors Francesco Barbieri, Luis Espinosa-Anke, Jose Camacho-Collados, Steven Schockaert, Horacio Saggion
Abstract Human language has evolved towards newer forms of communication such as social media, where emojis (i.e., ideograms bearing a visual meaning) play a key role. While there is an increasing body of work aimed at the computational modeling of emoji semantics, there is currently little understanding about what makes a computational model represent or predict a given emoji in a certain way. In this paper we propose a label-wise attention mechanism with which we attempt to better understand the nuances underlying emoji prediction. In addition to advantages in terms of interpretability, we show that our proposed architecture improves over standard baselines in emoji prediction, and does particularly well when predicting infrequent emojis.
Tasks Emotion Recognition, Information Retrieval, Language Modelling, Machine Translation, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1508/
PDF https://www.aclweb.org/anthology/D18-1508
PWC https://paperswithcode.com/paper/interpretable-emoji-prediction-via-label-wise
Repo
Framework

Overview of NLPTEA-2018 Share Task Chinese Grammatical Error Diagnosis

Title Overview of NLPTEA-2018 Share Task Chinese Grammatical Error Diagnosis
Authors Gaoqi Rao, Qi Gong, Baolin Zhang, Endong Xun
Abstract This paper presents the NLPTEA 2018 shared task for Chinese Grammatical Error Diagnosis (CGED) which seeks to identify grammatical error types, their range of occurrence and recommended corrections within sentences written by learners of Chinese as foreign language. We describe the task definition, data preparation, performance metrics, and evaluation results. Of the 20 teams registered for this shared task, 13 teams developed the system and submitted a total of 32 runs. Progress in system performances was obviously, reaching F1 of 36.12{%} in position level and 25.27{%} in correction level. All data sets with gold standards and scoring scripts are made publicly available to researchers.
Tasks Grammatical Error Correction
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3706/
PDF https://www.aclweb.org/anthology/W18-3706
PWC https://paperswithcode.com/paper/overview-of-nlptea-2018-share-task-chinese
Repo
Framework

The AFRL WMT18 Systems: Ensembling, Continuation and Combination

Title The AFRL WMT18 Systems: Ensembling, Continuation and Combination
Authors Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young
Abstract This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT18 evaluation campaign. This year, we examined the developments and additions to popular neural machine translation toolkits and measure improvements in performance on the Russian{–}English language pair.
Tasks Machine Translation
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6411/
PDF https://www.aclweb.org/anthology/W18-6411
PWC https://paperswithcode.com/paper/the-afrl-wmt18-systems-ensembling
Repo
Framework

#MeToo Alexa: How Conversational Systems Respond to Sexual Harassment

Title #MeToo Alexa: How Conversational Systems Respond to Sexual Harassment
Authors Amanda Cercas Curry, Verena Rieser
Abstract
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/papers/W18-0802/w18-0802
PDF https://www.aclweb.org/anthology/W18-0802v2
PWC https://paperswithcode.com/paper/metoo-alexa-how-conversational-systems
Repo
Framework

A hybrid pipeline of rules and machine learning to filter web-crawled parallel corpora

Title A hybrid pipeline of rules and machine learning to filter web-crawled parallel corpora
Authors Eduard Barbu, Verginica Barbu Mititelu
Abstract A hybrid pipeline comprising rules and machine learning is used to filter a noisy web English-German parallel corpus for the Parallel Corpus Filtering task. The core of the pipeline is a module based on the logistic regression algorithm that returns the probability that a translation unit is accepted. The training set for the logistic regression is created by automatic annotation. The quality of the automatic annotation is estimated by manually labeling the training set.
Tasks Machine Translation, Word Alignment
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6474/
PDF https://www.aclweb.org/anthology/W18-6474
PWC https://paperswithcode.com/paper/a-hybrid-pipeline-of-rules-and-machine
Repo
Framework

Neural Clustering By Predicting And Copying Noise

Title Neural Clustering By Predicting And Copying Noise
Authors Sam Coope, Andrej Zukov-Gregoric, Yoram Bachrach
Abstract We propose a neural clustering model that jointly learns both latent features and how they cluster. Unlike similar methods our model does not require a predefined number of clusters. Using a supervised approach, we agglomerate latent features towards randomly sampled targets within the same space whilst progressively removing the targets until we are left with only targets which represent cluster centroids. To show the behavior of our model across different modalities we apply our model on both text and image data and very competitive results on MNIST. Finally, we also provide results against baseline models for fashion-MNIST, the 20 newsgroups dataset, and a Twitter dataset we ourselves create.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=BJvVbCJCb
PDF https://openreview.net/pdf?id=BJvVbCJCb
PWC https://paperswithcode.com/paper/neural-clustering-by-predicting-and-copying
Repo
Framework
comments powered by Disqus