Paper Group ANR 860
Multi-Context Term Embeddings: the Use Case of Corpus-based Term Set Expansion. An End-to-End Framework to Identify Pathogenic Social Media Accounts on Twitter. Reinforced Imitation in Heterogeneous Action Space. Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of A …
Multi-Context Term Embeddings: the Use Case of Corpus-based Term Set Expansion
| Title | Multi-Context Term Embeddings: the Use Case of Corpus-based Term Set Expansion |
| Authors | Jonathan Mamou, Oren Pereg, Moshe Wasserblat, Ido Dagan |
| Abstract | In this paper, we present a novel algorithm that combines multi-context term embeddings using a neural classifier and we test this approach on the use case of corpus-based term set expansion. In addition, we present a novel and unique dataset for intrinsic evaluation of corpus-based term set expansion algorithms. We show that, over this dataset, our algorithm provides up to 5 mean average precision points over the best baseline. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02496v2 |
| http://arxiv.org/pdf/1904.02496v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-context-term-embeddings-the-use-case-of |
| Repo | |
| Framework | |
An End-to-End Framework to Identify Pathogenic Social Media Accounts on Twitter
| Title | An End-to-End Framework to Identify Pathogenic Social Media Accounts on Twitter |
| Authors | Elham Shaabani, Ashkan Sadeghi-Mobarakeh, Hamidreza Alvari, Paulo Shakarian |
| Abstract | Pathogenic Social Media (PSM) accounts such as terrorist supporter accounts and fake news writers have the capability of spreading disinformation to viral proportions. Early detection of PSM accounts is crucial as they are likely to be key users to make malicious information “viral”. In this paper, we adopt the causal inference framework along with graph-based metrics in order to distinguish PSMs from normal users within a short time of their activities. We propose both supervised and semi-supervised approaches without taking the network information and content into account. Results on a real-world dataset from Twitter accentuates the advantage of our proposed frameworks. We show our approach achieves 0.28 improvement in F1 score over existing approaches with the precision of 0.90 and F1 score of 0.63. |
| Tasks | Causal Inference |
| Published | 2019-05-04 |
| URL | https://arxiv.org/abs/1905.01553v1 |
| https://arxiv.org/pdf/1905.01553v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-end-to-end-framework-to-identify |
| Repo | |
| Framework | |
Reinforced Imitation in Heterogeneous Action Space
| Title | Reinforced Imitation in Heterogeneous Action Space |
| Authors | Konrad Zolna, Negar Rostamzadeh, Yoshua Bengio, Sungjin Ahn, Pedro O. Pinheiro |
| Abstract | Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume that the agent has access to a sparse reward function and state-only expert observations. We propose a method which gradually balances between the imitation learning cost and the reinforcement learning objective. In addition, this method adapts the agent’s policy based on either mimicking expert behavior or maximizing sparse reward. We show, through navigation scenarios, that (i) an agent is able to efficiently leverage sparse rewards to outperform standard state-only imitation learning, (ii) it can learn a policy even when its actions are different from the expert, and (iii) the performance of the agent is not bounded by that of the expert, due to the optimized usage of sparse rewards. |
| Tasks | Imitation Learning |
| Published | 2019-04-06 |
| URL | https://arxiv.org/abs/1904.03438v2 |
| https://arxiv.org/pdf/1904.03438v2.pdf | |
| PWC | https://paperswithcode.com/paper/reinforced-imitation-in-heterogeneous-action |
| Repo | |
| Framework | |
Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes
| Title | Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes |
| Authors | Paul Fergus, Carl Chalmers, Casimiro Curbelo Montanez, Denis Reilly, Paulo Lisboa, Beth Pineles |
| Abstract | Gynaecologists and obstetricians visually interpret cardiotocography (CTG) traces using the International Federation of Gynaecology and Obstetrics (FIGO) guidelines to assess the wellbeing of the foetus during antenatal care. This approach has raised concerns among professionals concerning inter- and intra-variability where clinical diagnosis only has a 30% positive predictive value when classifying pathological outcomes. Machine learning models, trained with FIGO and other user derived features extracted from CTG traces, have been shown to increase positive predictive capacity and minimise variability. This is only possible however when class distributions are equal which is rarely the case in clinical trials where case-control observations are heavily skewed. Classes can be balanced using either synthetic data derived from resampled case training data or by decreasing the number of control instances. However, this introduces bias and removes valuable information. Concerns have also been raised regarding machine learning studies and their reliance on manually handcrafted features. While this has led to some interesting results, deriving an optimal set of features is considered to be an art as well as a science and is often an empirical and time consuming process. In this paper, we address both of these issues and propose a novel CTG analysis methodology that a) splits CTG time series signals into n-size windows with equal class distributions, and b) automatically extracts features from time-series windows using a one dimensional convolutional neural network (1DCNN) and multilayer perceptron (MLP) ensemble. Our proposed method achieved good results using a window size of 200 with (Sens=0.7981, Spec=0.7881, F1=0.7830, Kappa=0.5849, AUC=0.8599, and Logloss=0.4791). |
| Tasks | Time Series |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02338v1 |
| https://arxiv.org/pdf/1908.02338v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-segmented-cardiotocography-time |
| Repo | |
| Framework | |
Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
| Title | Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches |
| Authors | Tian Li, Zaoxing Liu, Vyas Sekar, Virginia Smith |
| Abstract | Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and privacy preservation in the context of distributed machine learning. In particular, we prove that Count Sketch, a simple method for data stream summarization, has inherent differential privacy properties. Using these derived privacy guarantees, we propose a novel sketch-based framework (DiffSketch) for distributed learning, where we compress the transmitted messages via sketches to simultaneously achieve communication efficiency and provable privacy benefits. Our evaluation demonstrates that DiffSketch can provide strong differential privacy guarantees (e.g., $\varepsilon$= 1) and reduce communication by 20-50x with only marginal decreases in accuracy. Compared to baselines that treat privacy and communication separately, DiffSketch improves absolute test accuracy by 5%-50% while offering the same privacy guarantees and communication compression. |
| Tasks | |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00972v2 |
| https://arxiv.org/pdf/1911.00972v2.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-for-free-communication-efficient |
| Repo | |
| Framework | |
Arabic natural language processing: An overview
| Title | Arabic natural language processing: An overview |
| Authors | Imane Guellil, Houda Saâdane, Faical Azouaou, Billel Gueni, Damien Nouvel |
| Abstract | Arabic is recognised as the 4th most used language of the Internet. Arabic has three main varieties: (1) classical Arabic (CA), (2) Modern Standard Arabic (MSA), (3) Arabic Dialect (AD). MSA and AD could be written either in Arabic or in Roman script (Arabizi), which corresponds to Arabic written with Latin letters, numerals and punctuation. Due to the complexity of this language and the number of corresponding challenges for NLP, many surveys have been conducted, in order to synthesise the work done on Arabic. However these surveys principally focus on two varieties of Arabic (MSA and AD, written in Arabic letters only), they are slightly old (no such survey since 2015) and therefore do not cover recent resources and tools. To bridge the gap, we propose a survey focusing on 90 recent research papers (74% of which were published after 2015). Our study presents and classifies the work done on the three varieties of Arabic, by concentrating on both Arabic and Arabizi, and associates each work to its publicly available resources whenever available. |
| Tasks | |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.02784v1 |
| http://arxiv.org/pdf/1903.02784v1.pdf | |
| PWC | https://paperswithcode.com/paper/arabic-natural-language-processing-an |
| Repo | |
| Framework | |
Uncertainty about Uncertainty: Near-Optimal Adaptive Algorithms for Estimating Binary Mixtures of Unknown Coins
| Title | Uncertainty about Uncertainty: Near-Optimal Adaptive Algorithms for Estimating Binary Mixtures of Unknown Coins |
| Authors | Jasper C. H. Lee, Paul Valiant |
| Abstract | Given a mixture between two populations of coins, “positive” coins that have (unknown and potentially different) probabilities of heads $\geq\frac{1}{2}+\Delta$ and negative coins with probabilities $\leq\frac{1}{2}-\Delta$, we consider the task of estimating the fraction $\rho$ of coins of each type to within additive error $\epsilon$. We introduce new techniques to show a fully-adaptive lower bound of $\Omega(\frac{\rho}{\epsilon^2\Delta^2})$ samples (for constant probability of success). We achieve almost-matching algorithmic performance of $O(\frac{\rho}{\epsilon^2\Delta^2}(1+\rho\log\frac{1}{\epsilon}))$ samples, which matches the lower bound except in the regime where $\rho=\omega(\frac{1}{\log 1/\epsilon})$. The fine-grained adaptive flavor of both our algorithm and lower bound contrasts with much previous work in distributional testing and learning. |
| Tasks | |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09228v1 |
| http://arxiv.org/pdf/1904.09228v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-about-uncertainty-near-optimal |
| Repo | |
| Framework | |
SP-NET: One Shot Fingerprint Singular-Point Detector
| Title | SP-NET: One Shot Fingerprint Singular-Point Detector |
| Authors | Geetika Arora, Ranjeet Ranjan Jha, Akash Agrawal, Kamlesh Tiwari, Aditya Nigam |
| Abstract | Singular points of a fingerprint image are special locations having high curvature properties. They can play a pivotal role in fingerprint normalization and reliable feature extraction. Accurate and efficient extraction of a singular point plays a major role in successful fingerprint recognition and indexing. In this paper, a novel deep learning based architecture is proposed for one shot (end-to-end) singular point detection from an input fingerprint image. The model consists of a Macro-Localization Network and a Micro-Regression Network along with three stacked hourglass as a bottleneck. The proposed model has been tested on three databases viz. FVC2002 DB1_A, FVC2002 DB2_A and FPL30K and has been found to achieve true detection rate of 98.75%, 97.5% and 92.72% respectively, which is better than any other state-of-the-art technique. |
| Tasks | |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04842v1 |
| https://arxiv.org/pdf/1908.04842v1.pdf | |
| PWC | https://paperswithcode.com/paper/sp-net-one-shot-fingerprint-singular-point |
| Repo | |
| Framework | |
On Compositionality in Neural Machine Translation
| Title | On Compositionality in Neural Machine Translation |
| Authors | Vikas Raunak, Vaibhav Kumar, Florian Metze |
| Abstract | We investigate two specific manifestations of compositionality in Neural Machine Translation (NMT) : (1) Productivity - the ability of the model to extend its predictions beyond the observed length in training data and (2) Systematicity - the ability of the model to systematically recombine known parts and rules. We evaluate a standard Sequence to Sequence model on tests designed to assess these two properties in NMT. We quantitatively demonstrate that inadequate temporal processing, in the form of poor encoder representations is a bottleneck for both Productivity and Systematicity. We propose a simple pre-training mechanism which alleviates model performance on the two properties and leads to a significant improvement in BLEU scores. |
| Tasks | Machine Translation |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01497v3 |
| https://arxiv.org/pdf/1911.01497v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-compositionality-in-neural-machine |
| Repo | |
| Framework | |
Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs
| Title | Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs |
| Authors | Ryan A. Rossi, Anup Rao, Sungchul Kim, Eunyee Koh, Nesreen K. Ahmed, Gang Wu |
| Abstract | In this paper, we introduce the notion of motif closure and describe higher-order ranking and link prediction methods based on the notion of closing higher-order network motifs. The methods are fast and efficient for real-time ranking and link prediction-based applications such as web search, online advertising, and recommendation. In such applications, real-time performance is critical. The proposed methods do not require any explicit training data, nor do they derive an embedding from the graph data, or perform any explicit learning. Existing methods with the above desired properties are all based on closing triangles (common neighbors, Jaccard similarity, and the ilk). In this work, we investigate higher-order network motifs and develop techniques based on the notion of closing higher-order motifs that move beyond closing simple triangles. All methods described in this work are fast with a runtime that is sublinear in the number of nodes. The experimental results indicate the importance of closing higher-order motifs for ranking and link prediction applications. Finally, the proposed notion of higher-order motif closure can serve as a basis for studying and developing better ranking and link prediction methods. |
| Tasks | Link Prediction |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05059v1 |
| https://arxiv.org/pdf/1906.05059v1.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-ranking-and-link-prediction-from |
| Repo | |
| Framework | |
Deep learning for Aerosol Forecasting
| Title | Deep learning for Aerosol Forecasting |
| Authors | Caleb Hoyne, S. Karthik Mukkavilli, David Meger |
| Abstract | Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against ground truth. Biases identified with the NASA Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) aerosol optical depth (AOD) dataset, against the Aerosol Robotic Network (AERONET) ground measurements in previous studies, motivated the development of a deep learning based AOD prediction model globally. This study combines a convolutional neural network (CNN) with MERRA-2, tested against all AERONET sites. The new hybrid CNN-based model provides better estimates validated versus AERONET ground truth, than only using MERRA-2 reanalysis. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06789v1 |
| https://arxiv.org/pdf/1910.06789v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-aerosol-forecasting |
| Repo | |
| Framework | |
DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation
| Title | DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation |
| Authors | Rui Wang, Nan Yang, Joerg Stueckler, Daniel Cremers |
| Abstract | Scene understanding from images is a challenging problem encountered in autonomous driving. On the object level, while 2D methods have gradually evolved from computing simple bounding boxes to delivering finer grained results like instance segmentations, the 3D family is still dominated by estimating 3D bounding boxes. In this paper, we propose a novel approach to jointly infer the 3D rigid-body poses and shapes of vehicles from a stereo image pair using shape priors. Unlike previous works that geometrically align shapes to point clouds from dense stereo reconstruction, our approach works directly on images by combining a photometric and a silhouette alignment term in the energy function. An adaptive sparse point selection scheme is proposed to efficiently measure the consistency with both terms. In experiments, we show superior performance of our method on 3D pose and shape estimation over the previous geometric approach and demonstrate that our method can also be applied as a refinement step and significantly boost the performances of several state-of-the-art deep learning based 3D object detectors. All related materials and demonstration videos are available at the project page https://vision.in.tum.de/research/vslam/direct-shape. |
| Tasks | 3D Object Detection, Autonomous Driving, Object Detection, Pose Estimation, Scene Understanding |
| Published | 2019-04-22 |
| URL | https://arxiv.org/abs/1904.10097v2 |
| https://arxiv.org/pdf/1904.10097v2.pdf | |
| PWC | https://paperswithcode.com/paper/directshape-photometric-alignment-of-shape |
| Repo | |
| Framework | |
Background Hardly Matters: Understanding Personality Attribution in Deep Residual Networks
| Title | Background Hardly Matters: Understanding Personality Attribution in Deep Residual Networks |
| Authors | Gabriëlle Ras, Ron Dotsch, Luca Ambrogioni, Umut Güçlü, Marcel A. J. van Gerven |
| Abstract | Perceived personality traits attributed to an individual do not have to correspond to their actual personality traits and may be determined in part by the context in which one encounters a person. These apparent traits determine, to a large extent, how other people will behave towards them. Deep neural networks are increasingly being used to perform automated personality attribution (e.g., job interviews). It is important that we understand the driving factors behind the predictions, in humans and in deep neural networks. This paper explicitly studies the effect of the image background on apparent personality prediction while addressing two important confounds present in existing literature; overlapping data splits and including facial information in the background. Surprisingly, we found no evidence that background information improves model predictions for apparent personality traits. In fact, when background is explicitly added to the input, a decrease in performance was measured across all models. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09831v1 |
| https://arxiv.org/pdf/1912.09831v1.pdf | |
| PWC | https://paperswithcode.com/paper/background-hardly-matters-understanding |
| Repo | |
| Framework | |
Dual Supervised Learning for Natural Language Understanding and Generation
| Title | Dual Supervised Learning for Natural Language Understanding and Generation |
| Authors | Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen |
| Abstract | Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field. Natural language understanding is to extract the core semantic meaning from the given utterances, while natural language generation is opposite, of which the goal is to construct corresponding sentences based on the given semantics. However, such dual relationship has not been investigated in the literature. This paper proposes a new learning framework for language understanding and generation on top of dual supervised learning, providing a way to exploit the duality. The preliminary experiments show that the proposed approach boosts the performance for both tasks. |
| Tasks | Text Generation |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06196v3 |
| https://arxiv.org/pdf/1905.06196v3.pdf | |
| PWC | https://paperswithcode.com/paper/dual-supervised-learning-for-natural-language |
| Repo | |
| Framework | |
Learning from weakly dependent data under Dobrushin’s condition
| Title | Learning from weakly dependent data under Dobrushin’s condition |
| Authors | Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti |
| Abstract | Statistical learning theory has largely focused on learning and generalization given independent and identically distributed (i.i.d.) samples. Motivated by applications involving time-series data, there has been a growing literature on learning and generalization in settings where data is sampled from an ergodic process. This work has also developed complexity measures, which appropriately extend the notion of Rademacher complexity to bound the generalization error and learning rates of hypothesis classes in this setting. Rather than time-series data, our work is motivated by settings where data is sampled on a network or a spatial domain, and thus do not fit well within the framework of prior work. We provide learning and generalization bounds for data that are complexly dependent, yet their distribution satisfies the standard Dobrushin’s condition. Indeed, we show that the standard complexity measures of Gaussian and Rademacher complexities and VC dimension are sufficient measures of complexity for the purposes of bounding the generalization error and learning rates of hypothesis classes in our setting. Moreover, our generalization bounds only degrade by constant factors compared to their i.i.d. analogs, and our learnability bounds degrade by log factors in the size of the training set. |
| Tasks | Time Series |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09247v1 |
| https://arxiv.org/pdf/1906.09247v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-weakly-dependent-data-under |
| Repo | |
| Framework | |
