Paper Group ANR 370
Hybrid approach for transliteration of Algerian arabizi: a primary study. Flow From Motion: A Deep Learning Approach. Sparse and Smooth Signal Estimation: Convexification of L0 Formulations. Adversarial Learning for Chinese NER from Crowd Annotations. A comprehensive review of 3D point cloud descriptors. Customer Lifetime Value in Video Games Using …
Hybrid approach for transliteration of Algerian arabizi: a primary study
Title | Hybrid approach for transliteration of Algerian arabizi: a primary study |
Authors | Imane Guellil, Faical Azouaou, Fodil Benali, Ala-Eddine Hachani, Houda Saadane |
Abstract | A hybrid approach for the transliteration of Algerian Arabizi: A primary study In this paper, we present a hybrid approach for the transliteration of the Algerian Arabizi. We define a set of rules enable us the passage from Arabizi to Arabic. Through these rules, we generate a set of candidates for the transliteration of each Arabizi word into arabic. Then, we extract the best candidate. This approach was evaluated by using three test corpora, and the obtained results show an improvement of the precision score which is equal to 75.11% for the best result. These results allow us to verify that our approach is very competitive comparing to others works that treat Arabizi transliteration in general. Keywords: Arabizi, Dialecte Alg'erien, Arabizi Alg'erien, Translit'eration. |
Tasks | Transliteration |
Published | 2018-08-10 |
URL | http://arxiv.org/abs/1808.03437v1 |
http://arxiv.org/pdf/1808.03437v1.pdf | |
PWC | https://paperswithcode.com/paper/hybrid-approach-for-transliteration-of |
Repo | |
Framework | |
Flow From Motion: A Deep Learning Approach
Title | Flow From Motion: A Deep Learning Approach |
Authors | Cem Eteke, Hayati Havlucu, Nisa İrem Kırbaç, Mehmet Cengiz Onbaşlı, Aykut Coşkun, Terry Eskenazi, Oğuzhan Özcan, Barış Akgün |
Abstract | Wearable devices have the potential to enhance sports performance, yet they are not fulfilling this promise. Our previous studies with 6 professional tennis coaches and 20 players indicate that this could be due the lack of psychological or mental state feedback, which the coaches claim to provide. Towards this end, we propose to detect the flow state, mental state of optimal performance, using wearables data to be later used in training. We performed a study with a professional tennis coach and two players. The coach provided labels about the players’ flow state while each player had a wearable device on their racket holding wrist. We trained multiple models using the wearables data and the coach labels. Our deep neural network models achieved around 98% testing accuracy for a variety of conditions. This suggests that the flow state or what coaches recognize as flow, can be detected using wearables data in tennis which is a novel result. The implication for the HCI community is that having access to such information would allow for design of novel hardware and interaction paradigms that would be helpful in professional athlete training. |
Tasks | |
Published | 2018-03-26 |
URL | http://arxiv.org/abs/1803.09689v1 |
http://arxiv.org/pdf/1803.09689v1.pdf | |
PWC | https://paperswithcode.com/paper/flow-from-motion-a-deep-learning-approach |
Repo | |
Framework | |
Sparse and Smooth Signal Estimation: Convexification of L0 Formulations
Title | Sparse and Smooth Signal Estimation: Convexification of L0 Formulations |
Authors | Alper Atamturk, Andres Gomez, Shaoning Han |
Abstract | Signal estimation problems with smoothness and sparsity priors can be naturally modeled as quadratic optimization with L0-“norm” constraints. Since such problems are non-convex and hard-to-solve, the standard approach is, instead, to tackle their convex surrogates based on L1-norm relaxations. In this paper, we propose new iterative conic quadratic relaxations that exploit not only the L0-“norm” terms but also the fitness and smoothness functions. The iterative convexification approach substantially closes the gap between the L0-“norm” and its L1 surrogate. Experiments using an off-the-shelf conic quadratic solver on synthetic as well as real datasets indicate that the proposed iterative convex relaxations lead to significantly better estimators than L1-norm while preserving the computational efficiency. In addition, the parameters of the model and the resulting estimators are easily interpretable. |
Tasks | |
Published | 2018-11-06 |
URL | https://arxiv.org/abs/1811.02655v2 |
https://arxiv.org/pdf/1811.02655v2.pdf | |
PWC | https://paperswithcode.com/paper/sparse-and-smooth-signal-estimation |
Repo | |
Framework | |
Adversarial Learning for Chinese NER from Crowd Annotations
Title | Adversarial Learning for Chinese NER from Crowd Annotations |
Authors | YaoSheng Yang, Meishan Zhang, Wenliang Chen, Wei Zhang, Haofen Wang, Min Zhang |
Abstract | To quickly obtain new labeled data, we can choose crowdsourcing as an alternative way at lower cost in a short time. But as an exchange, crowd annotations from non-experts may be of lower quality than those from experts. In this paper, we propose an approach to performing crowd annotation learning for Chinese Named Entity Recognition (NER) to make full use of the noisy sequence labels from multiple annotators. Inspired by adversarial learning, our approach uses a common Bi-LSTM and a private Bi-LSTM for representing annotator-generic and -specific information. The annotator-generic information is the common knowledge for entities easily mastered by the crowd. Finally, we build our Chinese NE tagger based on the LSTM-CRF model. In our experiments, we create two data sets for Chinese NER tasks from two domains. The experimental results show that our system achieves better scores than strong baseline systems. |
Tasks | Chinese Named Entity Recognition, Named Entity Recognition |
Published | 2018-01-16 |
URL | http://arxiv.org/abs/1801.05147v1 |
http://arxiv.org/pdf/1801.05147v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-learning-for-chinese-ner-from |
Repo | |
Framework | |
A comprehensive review of 3D point cloud descriptors
Title | A comprehensive review of 3D point cloud descriptors |
Authors | Xian-Feng Hana, Jesse S. Jin, Juan Xie, Ming-Jie Wang, Wei Jiang |
Abstract | The introduction of inexpensive 3D data acquisition devices has promisingly facilitated the wide availability and popularity of 3D point cloud, which attracts more attention on the effective extraction of novel 3D point cloud descriptors for accurate and efficient of 3D computer vision tasks. However, how to de- velop discriminative and robust feature descriptors from various point clouds remains a challenging task. This paper comprehensively investigates the exist- ing approaches for extracting 3D point cloud descriptors which are categorized into three major classes: local-based descriptor, global-based descriptor and hybrid-based descriptor. Furthermore, experiments are carried out to present a thorough evaluation of performance of several state-of-the-art 3D point cloud descriptors used widely in practice in terms of descriptiveness, robustness and efficiency. |
Tasks | |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02297v1 |
http://arxiv.org/pdf/1802.02297v1.pdf | |
PWC | https://paperswithcode.com/paper/a-comprehensive-review-of-3d-point-cloud |
Repo | |
Framework | |
Customer Lifetime Value in Video Games Using Deep Learning and Parametric Models
Title | Customer Lifetime Value in Video Games Using Deep Learning and Parametric Models |
Authors | Pei Pei Chen, Anna Guitart, Ana Fernández del Río, África Periáñez |
Abstract | Nowadays, video game developers record every virtual action performed by their players. As each player can remain in the game for years, this results in an exceptionally rich dataset that can be used to understand and predict player behavior. In particular, this information may serve to identify the most valuable players and foresee the amount of money they will spend in in-app purchases during their lifetime. This is crucial in free-to-play games, where up to 50% of the revenue is generated by just around 2% of the players, the so-called whales. To address this challenge, we explore how deep neural networks can be used to predict customer lifetime value in video games, and compare their performance to parametric models such as Pareto/NBD. Our results suggest that convolutional neural network structures are the most efficient in predicting the economic value of individual players. They not only perform better in terms of accuracy, but also scale to big data and significantly reduce computational time, as they can work directly with raw sequential data and thus do not require any feature engineering process. This becomes important when datasets are very large, as is often the case with video game logs. Moreover, convolutional neural networks are particularly well suited to identify potential whales. Such an early identification is of paramount importance for business purposes, as it would allow developers to implement in-game actions aimed at retaining big spenders and maximizing their lifetime, which would ultimately translate into increased revenue. |
Tasks | Feature Engineering |
Published | 2018-11-28 |
URL | http://arxiv.org/abs/1811.12799v1 |
http://arxiv.org/pdf/1811.12799v1.pdf | |
PWC | https://paperswithcode.com/paper/customer-lifetime-value-in-video-games-using |
Repo | |
Framework | |
Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise
Title | Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise |
Authors | Vahid Behzadan, Arslan Munir |
Abstract | Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique for mitigation of such attacks based on addition of noise to the parameter space of deep reinforcement learners during training. We experimentally verify the effect of parameter-space noise in reducing the transferability of adversarial examples, and demonstrate the promising performance of this technique in mitigating the impact of whitebox and blackbox attacks at both test and training times. |
Tasks | |
Published | 2018-06-04 |
URL | http://arxiv.org/abs/1806.02190v1 |
http://arxiv.org/pdf/1806.02190v1.pdf | |
PWC | https://paperswithcode.com/paper/mitigation-of-policy-manipulation-attacks-on |
Repo | |
Framework | |
Adversarial Examples in Deep Learning: Characterization and Divergence
Title | Adversarial Examples in Deep Learning: Characterization and Divergence |
Authors | Wenqi Wei, Ling Liu, Margaret Loper, Stacey Truex, Lei Yu, Mehmet Emre Gursoy, Yanzhao Wu |
Abstract | The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a range of mission-critical deep learning systems and applications. This paper takes a holistic and principled approach to perform statistical characterization of adversarial examples in deep learning. We provide a general formulation of adversarial examples and elaborate on the basic principle for adversarial attack algorithm design. We introduce easy and hard categorization of adversarial attacks to analyze the effectiveness of adversarial examples in terms of attack success rate, degree of change in adversarial perturbation, average entropy of prediction qualities, and fraction of adversarial examples that lead to successful attacks. We conduct extensive experimental study on adversarial behavior in easy and hard attacks under deep learning models with different hyperparameters and different deep learning frameworks. We show that the same adversarial attack behaves differently under different hyperparameters and across different frameworks due to the different features learned under different deep learning model training process. Our statistical characterization with strong empirical evidence provides a transformative enlightenment on mitigation strategies towards effective countermeasures against present and future adversarial attacks. |
Tasks | Adversarial Attack |
Published | 2018-06-29 |
URL | http://arxiv.org/abs/1807.00051v3 |
http://arxiv.org/pdf/1807.00051v3.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-examples-in-deep-learning |
Repo | |
Framework | |
Natural Language to Structured Query Generation via Meta-Learning
Title | Natural Language to Structured Query Generation via Meta-Learning |
Authors | Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, Xiaodong He |
Abstract | In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could vary widely. In this work, we explore a different learning protocol that treats each example as a unique pseudo-task, by reducing the original learning problem to a few-shot meta-learning scenario with the help of a domain-dependent relevance function. When evaluated on the WikiSQL dataset, our approach leads to faster convergence and achieves 1.1%-5.4% absolute accuracy gains over the non-meta-learning counterparts. |
Tasks | Meta-Learning |
Published | 2018-03-02 |
URL | http://arxiv.org/abs/1803.02400v4 |
http://arxiv.org/pdf/1803.02400v4.pdf | |
PWC | https://paperswithcode.com/paper/natural-language-to-structured-query |
Repo | |
Framework | |
Logic Programming Applications: What Are the Abstractions and Implementations?
Title | Logic Programming Applications: What Are the Abstractions and Implementations? |
Authors | Yanhong A. Liu |
Abstract | This article presents an overview of applications of logic programming, classifying them based on the abstractions and implementations of logic languages that support the applications. The three key abstractions are join, recursion, and constraint. Their essential implementations are for-loops, fixed points, and backtracking, respectively. The corresponding kinds of applications are database queries, inductive analysis, and combinatorial search, respectively. We also discuss language extensions and programming paradigms, summarize example application problems by application areas, and touch on example systems that support variants of the abstractions with different implementations. |
Tasks | |
Published | 2018-02-20 |
URL | http://arxiv.org/abs/1802.07284v1 |
http://arxiv.org/pdf/1802.07284v1.pdf | |
PWC | https://paperswithcode.com/paper/logic-programming-applications-what-are-the |
Repo | |
Framework | |
Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
Title | Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder |
Authors | Jingkuan Song, Hanwang Zhang, Xiangpeng Li, Lianli Gao, Meng Wang, Richang Hong |
Abstract | Existing video hash functions are built on three isolated stages: frame pooling, relaxed learning, and binarization, which have not adequately explored the temporal order of video frames in a joint binary optimization model, resulting in severe information loss. In this paper, we propose a novel unsupervised video hashing framework dubbed Self-Supervised Video Hashing (SSVH), that is able to capture the temporal nature of videos in an end-to-end learning-to-hash fashion. We specifically address two central problems: 1) how to design an encoder-decoder architecture to generate binary codes for videos; and 2) how to equip the binary codes with the ability of accurate video retrieval. We design a hierarchical binary autoencoder to model the temporal dependencies in videos with multiple granularities, and embed the videos into binary codes with less computations than the stacked architecture. Then, we encourage the binary codes to simultaneously reconstruct the visual content and neighborhood structure of the videos. Experiments on two real-world datasets (FCVID and YFCC) show that our SSVH method can significantly outperform the state-of-the-art methods and achieve the currently best performance on the task of unsupervised video retrieval. |
Tasks | Video Retrieval |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02305v1 |
http://arxiv.org/pdf/1802.02305v1.pdf | |
PWC | https://paperswithcode.com/paper/self-supervised-video-hashing-with |
Repo | |
Framework | |
BandNet: A Neural Network-based, Multi-Instrument Beatles-Style MIDI Music Composition Machine
Title | BandNet: A Neural Network-based, Multi-Instrument Beatles-Style MIDI Music Composition Machine |
Authors | Yichao Zhou, Wei Chu, Sam Young, Xin Chen |
Abstract | In this paper, we propose a recurrent neural network (RNN)-based MIDI music composition machine that is able to learn musical knowledge from existing Beatles’ songs and generate music in the style of the Beatles with little human intervention. In the learning stage, a sequence of stylistically uniform, multiple-channel music samples was modeled by a RNN. In the composition stage, a short clip of randomly-generated music was used as a seed for the RNN to start music score prediction. To form structured music, segments of generated music from different seeds were concatenated together. To improve the quality and structure of the generated music, we integrated music theory knowledge into the model, such as controlling the spacing of gaps in the vocal melody, normalizing the timing of chord changes, and requiring notes to be related to the song’s key (C major, for example). This integration improved the quality of the generated music as verified by a professional composer. We also conducted a subjective listening test that showed our generated music was close to original music by the Beatles in terms of style similarity, professional quality, and interestingness. Generated music samples are at https://goo.gl/uaLXoB. |
Tasks | |
Published | 2018-12-18 |
URL | http://arxiv.org/abs/1812.07126v1 |
http://arxiv.org/pdf/1812.07126v1.pdf | |
PWC | https://paperswithcode.com/paper/bandnet-a-neural-network-based-multi |
Repo | |
Framework | |
Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks
Title | Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks |
Authors | Shibo Zhou, Wei Wang |
Abstract | Neural networks has been successfully used in the processing of Lidar data, especially in the scenario of autonomous driving. However, existing methods heavily rely on pre-processing of the pulse signals derived from Lidar sensors and therefore result in high computational overhead and considerable latency. In this paper, we proposed an approach utilizing Spiking Neural Network (SNN) to address the object recognition problem directly with raw temporal pulses. To help with the evaluation and benchmarking, a comprehensive temporal pulses data-set was created to simulate Lidar reflection in different road scenarios. Being tested with regard to recognition accuracy and time efficiency under different noise conditions, our proposed method shows remarkable performance with the inference accuracy up to 99.83% (with 10% noise) and the average recognition delay as low as 265 ns. It highlights the potential of SNN in autonomous driving and some related applications. In particular, to our best knowledge, this is the first attempt to use SNN to directly perform object recognition on raw Lidar temporal pulses. |
Tasks | Autonomous Driving, Object Detection, Object Recognition |
Published | 2018-10-29 |
URL | http://arxiv.org/abs/1810.12436v1 |
http://arxiv.org/pdf/1810.12436v1.pdf | |
PWC | https://paperswithcode.com/paper/object-detection-based-on-lidar-temporal |
Repo | |
Framework | |
TIFTI: A Framework for Extracting Drug Intervals from Longitudinal Clinic Notes
Title | TIFTI: A Framework for Extracting Drug Intervals from Longitudinal Clinic Notes |
Authors | Monica Agrawal, Griffin Adams, Nathan Nussbaum, Benjamin Birnbaum |
Abstract | Oral drugs are becoming increasingly common in oncology care. In contrast to intravenous chemotherapy, which is administered in the clinic and carefully tracked via structure electronic health records (EHRs), oral drug treatment is self-administered and therefore not tracked as well. Often, the details of oral cancer treatment occur only in unstructured clinic notes. Extracting this information is critical to understanding a patient’s treatment history. Yet, this a challenging task because treatment intervals must be inferred longitudinally from both explicit mentions in the text as well as from document timestamps. In this work, we present TIFTI (Temporally Integrated Framework for Treatment Intervals), a robust framework for extracting oral drug treatment intervals from a patient’s unstructured notes. TIFTI leverages distinct sources of temporal information by breaking the problem down into two separate subtasks: document-level sequence labeling and date extraction. On a labeled dataset of metastatic renal-cell carcinoma (RCC) patients, it exactly matched the labeled start date in 46% of the examples (86% of the examples within 30 days), and it exactly matched the labeled end date in 52% of the examples (78% of the examples within 30 days). Without retraining, the model achieved a similar level of performance on a labeled dataset of advanced non-small-cell lung cancer (NSCLC) patients. |
Tasks | |
Published | 2018-11-30 |
URL | http://arxiv.org/abs/1811.12793v2 |
http://arxiv.org/pdf/1811.12793v2.pdf | |
PWC | https://paperswithcode.com/paper/tifti-a-framework-for-extracting-drug |
Repo | |
Framework | |
Bayesian posterior approximation via greedy particle optimization
Title | Bayesian posterior approximation via greedy particle optimization |
Authors | Futoshi Futami, Zhenghang Cui, Issei Sato, Masashi Sugiyama |
Abstract | In Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric distribution for approximation, from which we can easily draw samples. Recently discrete approximation by particles has attracted attention because of its high expression ability. An example is Stein variational gradient descent (SVGD), which iteratively optimizes particles. Although SVGD has been shown to be computationally efficient empirically, its theoretical properties have not been clarified yet and no finite sample bound of the convergence rate is known. Another example is the Stein points (SP) method, which minimizes kernelized Stein discrepancy directly. Although a finite sample bound is assured theoretically, SP is computationally inefficient empirically, especially in high-dimensional problems. In this paper, we propose a novel method named maximum mean discrepancy minimization by the Frank-Wolfe algorithm (MMD-FW), which minimizes MMD in a greedy way by the FW algorithm. Our method is computationally efficient empirically and we show that its finite sample convergence bound is in a linear order in finite dimensions. |
Tasks | Bayesian Inference |
Published | 2018-05-21 |
URL | http://arxiv.org/abs/1805.07912v3 |
http://arxiv.org/pdf/1805.07912v3.pdf | |
PWC | https://paperswithcode.com/paper/bayesian-posterior-approximation-via-greedy |
Repo | |
Framework | |