Paper Group ANR 930
Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System. Re-ID done right: towards good practices for person re-identification. Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening. Vision-Based Preharvest Yield Mapping for Apple Orchards. Middle-Out Decoding. Harvesting Para …
Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System
Title | Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System |
Authors | Ankush Khandelwal, Sahil Swami, Syed S. Akhtar, Manish Shrivastava |
Abstract | The tremendous amount of user generated data through social networking sites led to the gaining popularity of automatic text classification in the field of computational linguistics over the past decade. Within this domain, one problem that has drawn the attention of many researchers is automatic humor detection in texts. In depth semantic understanding of the text is required to detect humor which makes the problem difficult to automate. With increase in the number of social media users, many multilingual speakers often interchange between languages while posting on social media which is called code-mixing. It introduces some challenges in the field of linguistic analysis of social media content (Barman et al., 2014), like spelling variations and non-grammatical structures in a sentence. Past researches include detecting puns in texts (Kao et al., 2016) and humor in one-lines (Mihalcea et al., 2010) in a single language, but with the tremendous amount of code-mixed data available online, there is a need to develop techniques which detects humor in code-mixed tweets. In this paper, we analyze the task of humor detection in texts and describe a freely available corpus containing English-Hindi code-mixed tweets annotated with humorous(H) or non-humorous(N) tags. We also tagged the words in the tweets with Language tags (English/Hindi/Others). Moreover, we describe the experiments carried out on the corpus and provide a baseline classification system which distinguishes between humorous and non-humorous texts. |
Tasks | Humor Detection, Text Classification |
Published | 2018-06-14 |
URL | http://arxiv.org/abs/1806.05513v1 |
http://arxiv.org/pdf/1806.05513v1.pdf | |
PWC | https://paperswithcode.com/paper/humor-detection-in-english-hindi-code-mixed |
Repo | |
Framework | |
Re-ID done right: towards good practices for person re-identification
Title | Re-ID done right: towards good practices for person re-identification |
Authors | Jon Almazan, Bojana Gajic, Naila Murray, Diane Larlus |
Abstract | Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism. |
Tasks | Person Re-Identification |
Published | 2018-01-16 |
URL | http://arxiv.org/abs/1801.05339v1 |
http://arxiv.org/pdf/1801.05339v1.pdf | |
PWC | https://paperswithcode.com/paper/re-id-done-right-towards-good-practices-for |
Repo | |
Framework | |
Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening
Title | Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening |
Authors | Merlin Schüler, Hlynur Davíð Hlynsson, Laurenz Wiskott |
Abstract | We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction. We provide experimental evidence that PowerSFA is able to extract meaningful and informative low-dimensional features in the case of (a) synthetic low-dimensional data, (b) ego-visual data, and also for (c) a general dataset for which symmetric non-temporal similarities between points can be defined. |
Tasks | |
Published | 2018-08-27 |
URL | https://arxiv.org/abs/1808.08833v3 |
https://arxiv.org/pdf/1808.08833v3.pdf | |
PWC | https://paperswithcode.com/paper/gradient-based-training-of-slow-feature |
Repo | |
Framework | |
Vision-Based Preharvest Yield Mapping for Apple Orchards
Title | Vision-Based Preharvest Yield Mapping for Apple Orchards |
Authors | Pravakar Roy, Abhijeet Kislay, Patrick A. Plonski, James Luby, Volkan Isler |
Abstract | We present an end-to-end computer vision system for mapping yield in an apple orchard using images captured from a single camera. Our proposed system is platform independent and does not require any specific lighting conditions. Our main technical contributions are 1)~a semi-supervised clustering algorithm that utilizes colors to identify apples and 2)~an unsupervised clustering method that utilizes spatial properties to estimate fruit counts from apple clusters having arbitrarily complex geometry. Additionally, we utilize camera motion to merge the counts across multiple views. We verified the performance of our algorithms by conducting multiple field trials on three tree rows consisting of $252$ trees at the University of Minnesota Horticultural Research Center. Results indicate that the detection method achieves $F_1$-measure $.95 -.97$ for multiple color varieties and lighting conditions. The counting method achieves an accuracy of $89%-98%$. Additionally, we report merged fruit counts from both sides of the tree rows. Our yield estimation method achieves an overall accuracy of $91.98% - 94.81%$ across different datasets. |
Tasks | |
Published | 2018-08-13 |
URL | http://arxiv.org/abs/1808.04336v1 |
http://arxiv.org/pdf/1808.04336v1.pdf | |
PWC | https://paperswithcode.com/paper/vision-based-preharvest-yield-mapping-for |
Repo | |
Framework | |
Middle-Out Decoding
Title | Middle-Out Decoding |
Authors | Shikib Mehri, Leonid Sigal |
Abstract | Despite being virtually ubiquitous, sequence-to-sequence models are challenged by their lack of diversity and inability to be externally controlled. In this paper, we speculate that a fundamental shortcoming of sequence generation models is that the decoding is done strictly from left-to-right, meaning that outputs values generated earlier have a profound effect on those generated later. To address this issue, we propose a novel middle-out decoder architecture that begins from an initial middle-word and simultaneously expands the sequence in both directions. To facilitate information flow and maintain consistent decoding, we introduce a dual self-attention mechanism that allows us to model complex dependencies between the outputs. We illustrate the performance of our model on the task of video captioning, as well as a synthetic sequence de-noising task. Our middle-out decoder achieves significant improvements on de-noising and competitive performance in the task of video captioning, while quantifiably improving the caption diversity. Furthermore, we perform a qualitative analysis that demonstrates our ability to effectively control the generation process of our decoder. |
Tasks | Video Captioning |
Published | 2018-10-28 |
URL | http://arxiv.org/abs/1810.11735v1 |
http://arxiv.org/pdf/1810.11735v1.pdf | |
PWC | https://paperswithcode.com/paper/middle-out-decoding |
Repo | |
Framework | |
Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia
Title | Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia |
Authors | Xinya Du, Claire Cardie |
Abstract | We study the task of generating from Wikipedia articles question-answer pairs that cover content beyond a single sentence. We propose a neural network approach that incorporates coreference knowledge via a novel gating mechanism. Compared to models that only take into account sentence-level information (Heilman and Smith, 2010; Du et al., 2017; Zhou et al., 2017), we find that the linguistic knowledge introduced by the coreference representation aids question generation significantly, producing models that outperform the current state-of-the-art. We apply our system (composed of an answer span extraction system and the passage-level QG system) to the 10,000 top-ranking Wikipedia articles and create a corpus of over one million question-answer pairs. We also provide a qualitative analysis for this large-scale generated corpus from Wikipedia. |
Tasks | Question Generation |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.05942v1 |
http://arxiv.org/pdf/1805.05942v1.pdf | |
PWC | https://paperswithcode.com/paper/harvesting-paragraph-level-question-answer |
Repo | |
Framework | |
Spectral clustering algorithms for the detection of clusters in block-cyclic and block-acyclic graphs
Title | Spectral clustering algorithms for the detection of clusters in block-cyclic and block-acyclic graphs |
Authors | H. Van Lierde, T. W. S. Chow, J. -C. Delvenne |
Abstract | We propose two spectral algorithms for partitioning nodes in directed graphs respectively with a cyclic and an acyclic pattern of connection between groups of nodes. Our methods are based on the computation of extremal eigenvalues of the transition matrix associated to the directed graph. The two algorithms outperform state-of-the art methods for directed graph clustering on synthetic datasets, including methods based on blockmodels, bibliometric symmetrization and random walks. Our algorithms have the same space complexity as classical spectral clustering algorithms for undirected graphs and their time complexity is also linear in the number of edges in the graph. One of our methods is applied to a trophic network based on predator-prey relationships. It successfully extracts common categories of preys and predators encountered in food chains. The same method is also applied to highlight the hierarchical structure of a worldwide network of Autonomous Systems depicting business agreements between Internet Service Providers. |
Tasks | Graph Clustering |
Published | 2018-05-02 |
URL | http://arxiv.org/abs/1805.00862v1 |
http://arxiv.org/pdf/1805.00862v1.pdf | |
PWC | https://paperswithcode.com/paper/spectral-clustering-algorithms-for-the |
Repo | |
Framework | |
State Space Gaussian Processes with Non-Gaussian Likelihood
Title | State Space Gaussian Processes with Non-Gaussian Likelihood |
Authors | Hannes Nickisch, Arno Solin, Alexander Grigorievskiy |
Abstract | We provide a comprehensive overview and tooling for GP modeling with non-Gaussian likelihoods using state space methods. The state space formulation allows for solving one-dimensional GP models in $\mathcal{O}(n)$ time and memory complexity. While existing literature has focused on the connection between GP regression and state space methods, the computational primitives allowing for inference using general likelihoods in combination with the Laplace approximation (LA), variational Bayes (VB), and assumed density filtering (ADF, a.k.a. single-sweep expectation propagation, EP) schemes has been largely overlooked. We present means of combining the efficient $\mathcal{O}(n)$ state space methodology with existing inference methods. We extend existing methods, and provide unifying code implementing all approaches. |
Tasks | Gaussian Processes |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04846v5 |
http://arxiv.org/pdf/1802.04846v5.pdf | |
PWC | https://paperswithcode.com/paper/state-space-gaussian-processes-with-non |
Repo | |
Framework | |
Toward Intelligent Vehicular Networks: A Machine Learning Framework
Title | Toward Intelligent Vehicular Networks: A Machine Learning Framework |
Authors | Le Liang, Hao Ye, Geoffrey Ye Li |
Abstract | As wireless networks evolve towards high mobility and providing better support for connected vehicles, a number of new challenges arise due to the resulting high dynamics in vehicular environments and thus motive rethinking of traditional wireless design methodologies. Future intelligent vehicles, which are at the heart of high mobility networks, are increasingly equipped with multiple advanced onboard sensors and keep generating large volumes of data. Machine learning, as an effective approach to artificial intelligence, can provide a rich set of tools to exploit such data for the benefit of the networks. In this article, we first identify the distinctive characteristics of high mobility vehicular networks and motivate the use of machine learning to address the resulting challenges. After a brief introduction of the major concepts of machine learning, we discuss its applications to learn the dynamics of vehicular networks and make informed decisions to optimize network performance. In particular, we discuss in greater detail the application of reinforcement learning in managing network resources as an alternative to the prevalent optimization approach. Finally, some open issues worth further investigation are highlighted. |
Tasks | |
Published | 2018-04-01 |
URL | https://arxiv.org/abs/1804.00338v3 |
https://arxiv.org/pdf/1804.00338v3.pdf | |
PWC | https://paperswithcode.com/paper/towards-intelligent-vehicular-networks-a |
Repo | |
Framework | |
Synthesizing Skeletons for Reactive Systems
Title | Synthesizing Skeletons for Reactive Systems |
Authors | Bernd Finkbeiner, Hazem Torfah |
Abstract | We present an analysis technique for temporal specifications of reactive systems that identifies, on the level of individual system outputs over time, which parts of the implementation are determined by the specification, and which parts are still open. This information is represented in the form of a labeled transition system, which we call skeleton. Each state of the skeleton is labeled with a three-valued assignment to the output variables: each output can be true, false, or open, where true or false means that the value must be true or false, respectively, and open means that either value is still possible. We present algorithms for the verification of skeletons and for the learning-based synthesis of skeletons from specifications in linear-time temporal logic (LTL). The algorithm returns a skeleton that satisfies the given LTL specification in time polynomial in the size of the minimal skeleton. Our new analysis technique can be used to recognize and repair specifications that underspecify critical situations. The technique thus complements existing methods for the recognition and repair of overspecifications via the identification of unrealizable cores. |
Tasks | |
Published | 2018-03-25 |
URL | http://arxiv.org/abs/1803.09285v1 |
http://arxiv.org/pdf/1803.09285v1.pdf | |
PWC | https://paperswithcode.com/paper/synthesizing-skeletons-for-reactive-systems |
Repo | |
Framework | |
Drive2Vec: Multiscale State-Space Embedding of Vehicular Sensor Data
Title | Drive2Vec: Multiscale State-Space Embedding of Vehicular Sensor Data |
Authors | David Hallac, Suvrat Bhooshan, Michael Chen, Kacem Abida, Rok Sosic, Jure Leskovec |
Abstract | With automobiles becoming increasingly reliant on sensors to perform various driving tasks, it is important to encode the relevant CAN bus sensor data in a way that captures the general state of the vehicle in a compact form. In this paper, we develop a deep learning-based method, called Drive2Vec, for embedding such sensor data in a low-dimensional yet actionable form. Our method is based on stacked gated recurrent units (GRUs). It accepts a short interval of automobile sensor data as input and computes a low-dimensional representation of that data, which can then be used to accurately solve a range of tasks. With this representation, we (1) predict the exact values of the sensors in the short term (up to three seconds in the future), (2) forecast the long-term average values of these same sensors, (3) infer additional contextual information that is not encoded in the data, including the identity of the driver behind the wheel, and (4) build a knowledge base that can be used to auto-label data and identify risky states. We evaluate our approach on a dataset collected by Audi, which equipped a fleet of test vehicles with data loggers to store all sensor readings on 2,098 hours of driving on real roads. We show in several experiments that our method outperforms other baselines by up to 90%, and we further demonstrate how these embeddings of sensor data can be used to solve a variety of real-world automotive applications. |
Tasks | |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.04795v1 |
http://arxiv.org/pdf/1806.04795v1.pdf | |
PWC | https://paperswithcode.com/paper/drive2vec-multiscale-state-space-embedding-of |
Repo | |
Framework | |
Hypergraph p-Laplacian Regularization for Remote Sensing Image Recognition
Title | Hypergraph p-Laplacian Regularization for Remote Sensing Image Recognition |
Authors | Xueqi Ma, Weifeng Liu, Shuying Li, Yicong Zhou |
Abstract | It is of great importance to preserve locality and similarity information in semi-supervised learning (SSL) based applications. Graph based SSL and manifold regularization based SSL including Laplacian regularization (LapR) and Hypergraph Laplacian regularization (HLapR) are representative SSL methods and have achieved prominent performance by exploiting the relationship of sample distribution. However, it is still a great challenge to exactly explore and exploit the local structure of the data distribution. In this paper, we present an effect and effective approximation algorithm of Hypergraph p-Laplacian and then propose Hypergraph p-Laplacian regularization (HpLapR) to preserve the geometry of the probability distribution. In particular, p-Laplacian is a nonlinear generalization of the standard graph Laplacian and Hypergraph is a generalization of a standard graph. Therefore, the proposed HpLapR provides more potential to exploiting the local structure preserving. We apply HpLapR to logistic regression and conduct the implementations for remote sensing image recognition. We compare the proposed HpLapR to several popular manifold regularization based SSL methods including LapR, HLapR and HpLapR on UC-Merced dataset. The experimental results demonstrate the superiority of the proposed HpLapR. |
Tasks | |
Published | 2018-06-21 |
URL | http://arxiv.org/abs/1806.08104v1 |
http://arxiv.org/pdf/1806.08104v1.pdf | |
PWC | https://paperswithcode.com/paper/hypergraph-p-laplacian-regularization-for |
Repo | |
Framework | |
Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
Title | Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection |
Authors | Heng Fan, Peng Chu, Longin Jan Latecki, Haibin Ling |
Abstract | Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic dependencies among image units. Different from existing RNN based approaches, our dense RNNs are able to capture richer contextual dependencies for each image unit by enabling immediate connections between each pair of image units, which significantly enhances their discriminative power. Besides, to select relevant dependencies and meanwhile to restrain irrelevant ones for each unit from dense connections, we introduce an attention model into dense RNNs. The attention model allows automatically assigning more importance to helpful dependencies while less weight to unconcerned dependencies. Integrating with convolutional neural networks (CNNs), we develop an end-to-end scene labeling system. Extensive experiments on three large-scale benchmarks demonstrate that the proposed approach can improve the baselines by large margins and outperform other state-of-the-art algorithms. |
Tasks | Scene Labeling, Scene Parsing |
Published | 2018-11-09 |
URL | http://arxiv.org/abs/1811.04778v1 |
http://arxiv.org/pdf/1811.04778v1.pdf | |
PWC | https://paperswithcode.com/paper/scene-parsing-via-dense-recurrent-neural |
Repo | |
Framework | |
Path Consistency Learning in Tsallis Entropy Regularized MDPs
Title | Path Consistency Learning in Tsallis Entropy Regularized MDPs |
Authors | Ofir Nachum, Yinlam Chow, Mohammad Ghavamzadeh |
Abstract | We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero probability for only a small number of actions. This addresses the main drawback of the standard Shannon entropy-regularized RL (soft ERL) formulation, in which the optimal policy is softmax, and thus, may assign a non-negligible probability mass to non-optimal actions. This problem is aggravated as the number of actions is increased. In this paper, we follow the work of Nachum et al. (2017) in the soft ERL setting, and propose a class of novel path consistency learning (PCL) algorithms, called {\em sparse PCL}, for the sparse ERL problem that can work with both on-policy and off-policy data. We first derive a {\em sparse consistency} equation that specifies a relationship between the optimal value function and policy of the sparse ERL along any system trajectory. Crucially, a weak form of the converse is also true, and we quantify the sub-optimality of a policy which satisfies sparse consistency, and show that as we increase the number of actions, this sub-optimality is better than that of the soft ERL optimal policy. We then use this result to derive the sparse PCL algorithms. We empirically compare sparse PCL with its soft counterpart, and show its advantage, especially in problems with a large number of actions. |
Tasks | |
Published | 2018-02-10 |
URL | http://arxiv.org/abs/1802.03501v1 |
http://arxiv.org/pdf/1802.03501v1.pdf | |
PWC | https://paperswithcode.com/paper/path-consistency-learning-in-tsallis-entropy |
Repo | |
Framework | |
Superposition-Assisted Stochastic Optimization for Hawkes Processes
Title | Superposition-Assisted Stochastic Optimization for Hawkes Processes |
Authors | Hongteng Xu, Xu Chen, Lawrence Carin |
Abstract | We consider the learning of multi-agent Hawkes processes, a model containing multiple Hawkes processes with shared endogenous impact functions and different exogenous intensities. In the framework of stochastic maximum likelihood estimation, we explore the associated risk bound. Further, we consider the superposition of Hawkes processes within the model, and demonstrate that under certain conditions such an operation is beneficial for tightening the risk bound. Accordingly, we propose a stochastic optimization algorithm assisted with a diversity-driven superposition strategy, achieving better learning results with improved convergence properties. The effectiveness of the proposed method is verified on synthetic data, and its potential to solve the cold-start problem of sequential recommendation systems is demonstrated on real-world data. |
Tasks | Recommendation Systems, Stochastic Optimization |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.04725v2 |
http://arxiv.org/pdf/1802.04725v2.pdf | |
PWC | https://paperswithcode.com/paper/superposition-assisted-stochastic |
Repo | |
Framework | |