October 20, 2019

3269 words 16 mins read

Paper Group ANR 16

All You Need is “Love”: Evading Hate-speech Detection. Collective behavior recognition using compact descriptors. Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples. Two “correlation games” for a nonlinear network with Hebbian excitatory neurons and anti-Hebbian inhibitory neurons. Examining a hate speech corpus for hate s …

All You Need is “Love”: Evading Hate-speech Detection


Title	All You Need is “Love”: Evading Hate-speech Detection
Authors	Tommi Gröndahl, Luca Pajola, Mika Juuti, Mauro Conti, N. Asokan
Abstract	With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem. In this paper, we reproduce seven state-of-the-art hate speech detection models from prior work, and show that they perform well only when tested on the same type of data they were trained on. Based on these results, we argue that for successful hate speech detection, model architecture is less important than the type of data and labeling criteria. We further show that all proposed detection techniques are brittle against adversaries who can (automatically) insert typos, change word boundaries or add innocuous words to the original hate speech. A combination of these methods is also effective against Google Perspective – a cutting-edge solution from industry. Our experiments demonstrate that adversarial training does not completely mitigate the attacks, and using character-level features makes the models systematically more attack-resistant than using word-level features.
Tasks	Hate Speech Detection
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09115v3
PDF	http://arxiv.org/pdf/1808.09115v3.pdf
PWC	https://paperswithcode.com/paper/all-you-need-is-love-evading-hate-speech
Repo
Framework

Collective behavior recognition using compact descriptors


Title	Collective behavior recognition using compact descriptors
Authors	Gustavo Fuhr, Claudio Rosito Jung
Abstract	This paper presents a novel hierarchical approach for collective behavior recognition based solely on ground-plane trajectories. In the first layer of our classifier, we introduce a novel feature called Personal Interaction Descriptor (PID), which combines the spatial distribution of a pair of pedestrians within a temporal window with a pyramidal representation of the relative speed to detect pairwise interactions. These interactions are then combined with higher level features related to the mean speed and shape formed by the pedestrians in the scene, generating a Collective Behavior Descriptor (CBD) that is used to identify collective behaviors in a second stage. In both layers, Random Forests were used as classifiers, since they allow features of different natures to be combined seamlessly. Our experimental results indicate that the proposed method achieves results on par with state of the art techniques with a better balance of class errors. Moreover, we show that our method can generalize well across different camera setups through cross-dataset experiments.
Tasks
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10499v1
PDF	http://arxiv.org/pdf/1809.10499v1.pdf
PWC	https://paperswithcode.com/paper/collective-behavior-recognition-using-compact
Repo
Framework

Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples


Title	Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
Authors	Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani
Abstract	Synthesizing user-intended programs from a small number of input-output examples is a challenging problem with several important applications like spreadsheet manipulation, data wrangling and code refactoring. Existing synthesis systems either completely rely on deductive logic techniques that are extensively hand-engineered or on purely statistical models that need massive amounts of data, and in general fail to provide real-time synthesis on challenging benchmarks. In this work, we propose Neural Guided Deductive Search (NGDS), a hybrid synthesis technique that combines the best of both symbolic logic techniques and statistical models. Thus, it produces programs that satisfy the provided specifications by construction and generalize well on unseen examples, similar to data-driven systems. Our technique effectively utilizes the deductive search framework to reduce the learning problem of the neural component to a simple supervised learning setup. Further, this allows us to both train on sparingly available real-world data and still leverage powerful recurrent neural network encoders. We demonstrate the effectiveness of our method by evaluating on real-world customer scenarios by synthesizing accurate programs with up to 12x speed-up compared to state-of-the-art systems.
Tasks	Program Synthesis
Published	2018-04-03
URL	http://arxiv.org/abs/1804.01186v2
PDF	http://arxiv.org/pdf/1804.01186v2.pdf
PWC	https://paperswithcode.com/paper/neural-guided-deductive-search-for-real-time
Repo
Framework

Two “correlation games” for a nonlinear network with Hebbian excitatory neurons and anti-Hebbian inhibitory neurons


Title	Two “correlation games” for a nonlinear network with Hebbian excitatory neurons and anti-Hebbian inhibitory neurons
Authors	H. Sebastian Seung
Abstract	A companion paper introduces a nonlinear network with Hebbian excitatory (E) neurons that are reciprocally coupled with anti-Hebbian inhibitory (I) neurons and also receive Hebbian feedforward excitation from sensory (S) afferents. The present paper derives the network from two normative principles that are mathematically equivalent but conceptually different. The first principle formulates unsupervised learning as a constrained optimization problem: maximization of S-E correlations subject to a copositivity constraint on E-E correlations. A combination of Legendre and Lagrangian duality yields a zero-sum continuous game between excitatory and inhibitory connections that is solved by the neural network. The second principle defines a zero-sum game between E and I cells. E cells want to maximize S-E correlations and minimize E-I correlations, while I cells want to maximize I-E correlations and minimize power. The conflict between I and E objectives effectively forces the E cells to decorrelate from each other, although only incompletely. Legendre duality yields the neural network.
Tasks
Published	2018-12-31
URL	http://arxiv.org/abs/1812.11937v1
PDF	http://arxiv.org/pdf/1812.11937v1.pdf
PWC	https://paperswithcode.com/paper/two-correlation-games-for-a-nonlinear-network
Repo
Framework

Examining a hate speech corpus for hate speech detection and popularity prediction


Title	Examining a hate speech corpus for hate speech detection and popularity prediction
Authors	Filip Klubička, Raquel Fernández
Abstract	As research on hate speech becomes more and more relevant every day, most of it is still focused on hate speech detection. By attempting to replicate a hate speech detection experiment performed on an existing Twitter corpus annotated for hate speech, we highlight some issues that arise from doing research in the field of hate speech, which is essentially still in its infancy. We take a critical look at the training corpus in order to understand its biases, while also using it to venture beyond hate speech detection and investigate whether it can be used to shed light on other facets of research, such as popularity of hate tweets.
Tasks	Hate Speech Detection
Published	2018-05-12
URL	http://arxiv.org/abs/1805.04661v1
PDF	http://arxiv.org/pdf/1805.04661v1.pdf
PWC	https://paperswithcode.com/paper/examining-a-hate-speech-corpus-for-hate
Repo
Framework

Stay On-Topic: Generating Context-specific Fake Restaurant Reviews


Title	Stay On-Topic: Generating Context-specific Fake Restaurant Reviews
Authors	Mika Juuti, Bo Sun, Tatsuya Mori, N. Asokan
Abstract	Automatically generated fake restaurant reviews are a threat to online review systems. Recent research has shown that users have difficulties in detecting machine-generated fake reviews hiding among real restaurant reviews. The method used in this work (char-LSTM ) has one drawback: it has difficulties staying in context, i.e. when it generates a review for specific target entity, the resulting review may contain phrases that are unrelated to the target, thus increasing its detectability. In this work, we present and evaluate a more sophisticated technique based on neural machine translation (NMT) with which we can generate reviews that stay on-topic. We test multiple variants of our technique using native English speakers on Amazon Mechanical Turk. We demonstrate that reviews generated by the best variant have almost optimal undetectability (class-averaged F-score 47%). We conduct a user study with skeptical users and show that our method evades detection more frequently compared to the state-of-the-art (average evasion 3.2/4 vs 1.5/4) with statistical significance, at level {\alpha} = 1% (Section 4.3). We develop very effective detection tools and reach average F-score of 97% in classifying these. Although fake reviews are very effective in fooling people, effective automatic detection is still feasible.
Tasks	Machine Translation
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02400v4
PDF	http://arxiv.org/pdf/1805.02400v4.pdf
PWC	https://paperswithcode.com/paper/stay-on-topic-generating-context-specific
Repo
Framework

Deep Nearest Class Mean Model for Incremental Odor Classification


Title	Deep Nearest Class Mean Model for Incremental Odor Classification
Authors	Yu Cheng, Angus Wong, Kevin Hung, Zhizhong Li, Weitong Li, Jun Zhang
Abstract	In recent years, more machine learning algorithms have been applied to odor classification. These odor classification algorithms usually assume that the training datasets are static. However, for some odor recognition tasks, new odor classes continually emerge. That is, the odor datasets are dynamically growing while both training samples and number of classes are increasing over time. Motivated by this concern, this paper proposes a Deep Nearest Class Mean (DNCM) model based on the deep learning framework and nearest class mean method. The proposed model not only leverages deep neural network to extract deep features, but is also able to dynamically integrate new classes over time. In our experiments, the DNCM model was initially trained with 10 classes, then 25 new classes are integrated. Experiment results demonstrate that the proposed model is very efficient for incremental odor classification, especially for new classes with only a small number of training examples.
Tasks
Published	2018-01-08
URL	http://arxiv.org/abs/1801.02328v2
PDF	http://arxiv.org/pdf/1801.02328v2.pdf
PWC	https://paperswithcode.com/paper/deep-nearest-class-mean-model-for-incremental
Repo
Framework

Efficient Recurrent Neural Networks using Structured Matrices in FPGAs


Title	Efficient Recurrent Neural Networks using Structured Matrices in FPGAs
Authors	Zhe Li, Shuo Wang, Caiwen Ding, Qinru Qiu, Yanzhi Wang, Yun Liang
Abstract	Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose block-circulant matrices for weight matrix representation in RNNs, thereby achieving simultaneous model compression and acceleration. We aim to implement RNNs in FPGA with highest performance and energy efficiency, with certain accuracy requirement (negligible accuracy degradation). Experimental results on actual FPGA deployments shows that the proposed framework achieves a maximum energy efficiency improvement of 35.7$\times$ compared with ESE.
Tasks	Model Compression, Time Series
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07661v2
PDF	http://arxiv.org/pdf/1803.07661v2.pdf
PWC	https://paperswithcode.com/paper/efficient-recurrent-neural-networks-using
Repo
Framework

Investigating Object Compositionality in Generative Adversarial Networks


Title	Investigating Object Compositionality in Generative Adversarial Networks
Authors	Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly
Abstract	Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several core inductive biases. However, a bias to account for the compositional way in which humans structure a visual scene in terms of objects has frequently been overlooked. In this work we investigate object compositionality as an inductive bias for Generative Adversarial Networks (GANs). We present a minimal modification of a standard generator to incorporate this inductive bias and find that it reliably learns to generate images as compositions of objects. Using this general design as a backbone, we then propose two useful extensions to incorporate dependencies among objects and background. We extensively evaluate our approach on several multi-object image datasets and highlight the merits of incorporating structure for representation learning purposes. In particular, we find that our structured GANs are better at generating multi-object images that are more faithful to the reference distribution. More so, we demonstrate how, by leveraging the structure of the learned generative process, it can be `inverted’ to perform unsupervised instance segmentation. Compared to prior work on purely unsupervised object-centric image generation our results on CLEVR are state of the art. \|
Tasks	Image Generation, Instance Segmentation, Representation Learning, Semantic Segmentation
Published	2018-10-17
URL	https://arxiv.org/abs/1810.10340v2
PDF	https://arxiv.org/pdf/1810.10340v2.pdf
PWC	https://paperswithcode.com/paper/a-case-for-object-compositionality-in-deep
Repo
Framework

Scalable Label Propagation for Multi-relational Learning on Tensor Product Graph


Title	Scalable Label Propagation for Multi-relational Learning on Tensor Product Graph
Authors	Zhuliu Li, Raphael Petegrosso, Shaden Smith, David Sterling, George Karypis, Rui Kuang
Abstract	Label propagation on the tensor product of multiple graphs can infer multi-relations among the entities across the graphs by learning labels in a tensor. However, the tensor formulation is only empirically scalable up to three graphs due to the exponential complexity of computing tensors. In this paper, we propose an optimization formulation and a scalable Lowrank Tensor-based Label Propagation algorithm (LowrankTLP). The optimization formulation minimizes the rank-k approximation error for computing the closed-form solution of label propagation on a tensor product graph with efficient tensor computations used in LowrankTLP. LowrankTLP takes either a sparse tensor of known multi-relations or pairwise relations between each pair of graphs as the input to infer unknown multi-relations by semi-supervised learning on the tensor product graph. We also accelerate LowrankTLP with parallel tensor computation which enabled label propagation on a tensor product of 100 graphs of size 1000 within 150 seconds in simulation. LowrankTLP was also successfully applied to multi-relational learning for predicting author-paper-venue in publication records, alignment of several protein-protein interaction networks across species and alignment of segmented regions across up to 7 CT scan images. The experiments prove that LowrankTLP indeed well approximates the original label propagation with high scalability. Source code: https://github.com/kuanglab/LowrankTLP
Tasks	Relational Reasoning
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07379v1
PDF	http://arxiv.org/pdf/1802.07379v1.pdf
PWC	https://paperswithcode.com/paper/scalable-label-propagation-for-multi
Repo
Framework

Sentence-wise Smooth Regularization for Sequence to Sequence Learning


Title	Sentence-wise Smooth Regularization for Sequence to Sequence Learning
Authors	Chengyue Gong, Xu Tan, Di He, Tao Qin
Abstract	Maximum-likelihood estimation (MLE) is widely used in sequence to sequence tasks for model training. It uniformly treats the generation/prediction of each target token as multi-class classification, and yields non-smooth prediction probabilities: in a target sequence, some tokens are predicted with small probabilities while other tokens are with large probabilities. According to our empirical study, we find that the non-smoothness of the probabilities results in low quality of generated sequences. In this paper, we propose a sentence-wise regularization method which aims to output smooth prediction probabilities for all the tokens in the target sequence. Our proposed method can automatically adjust the weights and gradients of each token in one sentence to ensure the predictions in a sequence uniformly well. Experiments on three neural machine translation tasks and one text summarization task show that our method outperforms conventional MLE loss on all these tasks and achieves promising BLEU scores on WMT14 English-German and WMT17 Chinese-English translation task.
Tasks	Machine Translation, Text Summarization
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04784v1
PDF	http://arxiv.org/pdf/1812.04784v1.pdf
PWC	https://paperswithcode.com/paper/sentence-wise-smooth-regularization-for
Repo
Framework

Deep Robust Framework for Protein Function Prediction using Variable-Length Protein Sequences


Title	Deep Robust Framework for Protein Function Prediction using Variable-Length Protein Sequences
Authors	Ashish Ranjan, Md Shah Fahad, David Fernandez-Baca, Akshay Deepak, Sudhakar Tripathi
Abstract	Amino acid sequence portrays most intrinsic form of a protein and expresses primary structure of protein. The order of amino acids in a sequence enables a protein to acquire a particular stable conformation that is responsible for the functions of the protein. This relationship between a sequence and its function motivates the need to analyse the sequences for predicting protein functions. Early generation computational methods using BLAST, FASTA, etc. perform function transfer based on sequence similarity with existing databases and are computationally slow. Although machine learning based approaches are fast, they fail to perform well for long protein sequences (i.e., protein sequences with more than 300 amino acid residues). In this paper, we introduce a novel method for construction of two separate feature sets for protein sequences based on analysis of 1) single fixed-sized segments and 2) multi-sized segments, using bi-directional long short-term memory network. Further, model based on proposed feature set is combined with the state of the art Multi-lable Linear Discriminant Analysis (MLDA) features based model to improve the accuracy. Extensive evaluations using separate datasets for biological processes and molecular functions demonstrate promising results for both single-sized and multi-sized segments based feature sets. While former showed an improvement of +3.37% and +5.48%, the latter produces an improvement of +5.38% and +8.00% respectively for two datasets over the state of the art MLDA based classifier. After combining two models, there is a significant improvement of +7.41% and +9.21% respectively for two datasets compared to MLDA based classifier. Specifically, the proposed approach performed well for the long protein sequences and superior overall performance.
Tasks	Protein Function Prediction
Published	2018-11-04
URL	https://arxiv.org/abs/1811.01338v2
PDF	https://arxiv.org/pdf/1811.01338v2.pdf
PWC	https://paperswithcode.com/paper/deep-robust-framework-for-protein-function
Repo
Framework

An Enhanced Latent Semantic Analysis Approach for Arabic Document Summarization


Title	An Enhanced Latent Semantic Analysis Approach for Arabic Document Summarization
Authors	Kamal Al-Sabahi, Zuping Zhang, Jun Long, Khaled Alwesabi
Abstract	The fast-growing amount of information on the Internet makes the research in automatic document summarization very urgent. It is an effective solution for information overload. Many approaches have been proposed based on different strategies, such as latent semantic analysis (LSA). However, LSA, when applied to document summarization, has some limitations which diminish its performance. In this work, we try to overcome these limitations by applying statistic and linear algebraic approaches combined with syntactic and semantic processing of text. First, the part of speech tagger is utilized to reduce the dimension of LSA. Then, the weight of the term in four adjacent sentences is added to the weighting schemes while calculating the input matrix to take into account the word order and the syntactic relations. In addition, a new LSA-based sentence selection algorithm is proposed, in which the term description is combined with sentence description for each topic which in turn makes the generated summary more informative and diverse. To ensure the effectiveness of the proposed LSA-based sentence selection algorithm, extensive experiment on Arabic and English are done. Four datasets are used to evaluate the new model, Linguistic Data Consortium (LDC) Arabic Newswire-a corpus, Essex Arabic Summaries Corpus (EASC), DUC2002, and Multilingual MSS 2015 dataset. Experimental results on the four datasets show the effectiveness of the proposed model on Arabic and English datasets. It performs comprehensively better compared to the state-of-the-art methods.
Tasks	Document Summarization
Published	2018-07-31
URL	http://arxiv.org/abs/1807.11618v1
PDF	http://arxiv.org/pdf/1807.11618v1.pdf
PWC	https://paperswithcode.com/paper/an-enhanced-latent-semantic-analysis-approach
Repo
Framework

Visual Tracking Using Sparse Coding and Earth Mover’s Distance


Title	Visual Tracking Using Sparse Coding and Earth Mover’s Distance
Authors	Gang Yao, Ashwin Dani
Abstract	An efficient iterative Earth Mover’s Distance (iEMD) algorithm for visual tracking is proposed in this paper. The Earth Mover’s Distance (EMD) is used as the similarity measure to search for the optimal template candidates in feature-spatial space in a video sequence. The computation of the EMD is formulated as the transportation problem from linear programming. The efficiency of the EMD optimization problem limits its use for visual tracking. To alleviate this problem, a transportation-simplex method is used for EMD optimization and a monotonically convergent iterative optimization algorithm is developed. The local sparse representation is used as the appearance models for the iEMD tracker. The maximum-alignment-pooling method is used for constructing a sparse coding histogram which reduces the computational complexity of the EMD optimization. The template update algorithm based on the EMD is also presented. The iEMD tracking algorithm assumes small inter-frame movement in order to guarantee convergence. When the camera is mounted on a moving robot, e.g., a flying quadcopter, the camera could experience a sudden and rapid motion leading to large inter-frame movements. To ensure that the tracking algorithm converges, a gyro-aided extension of the iEMD tracker is presented, where synchronized gyroscope information is utilized to compensate for the rotation of the camera. The iEMD algorithm’s performance is evaluated using eight publicly available datasets. The performance of the iEMD algorithm is compared with seven state-of-the-art tracking algorithms based on relative percentage overlap. The robustness of this algorithm for large inter-frame displacements is also illustrated.
Tasks	Visual Tracking
Published	2018-04-06
URL	http://arxiv.org/abs/1804.02470v1
PDF	http://arxiv.org/pdf/1804.02470v1.pdf
PWC	https://paperswithcode.com/paper/visual-tracking-using-sparse-coding-and-earth
Repo
Framework

Event Representation through Semantic Roles: Evaluation of Coverage


Title	Event Representation through Semantic Roles: Evaluation of Coverage
Authors	Aliaksandr Huminski, Hao Zhang
Abstract	Semantic role theory is a widely used approach for event representation. Yet, there are multiple indications that semantic role paradigm is necessary but not sufficient to cover all elements of event structure. We conducted an analysis of semantic role representation for events to provide an empirical evidence of insufficiency. The consequence of that is a hybrid role-scalar approach. The results are considered as preliminary in investigation of semantic roles coverage for event representation.
Tasks
Published	2018-10-09
URL	http://arxiv.org/abs/1810.03879v1
PDF	http://arxiv.org/pdf/1810.03879v1.pdf
PWC	https://paperswithcode.com/paper/event-representation-through-semantic-roles
Repo
Framework