Paper Group ANR 991
Expert Finding in Community Question Answering: A Review. An Acceleration Scheme to The Local Directional Pattern. CT-image Super Resolution Using 3D Convolutional Neural Network. Background Subtraction using Compressed Low-resolution Images. Topic Modelling of Empirical Text Corpora: Validity, Reliability, and Reproducibility in Comparison to Sema …
Expert Finding in Community Question Answering: A Review
| Title | Expert Finding in Community Question Answering: A Review |
| Authors | Sha Yuan, Yu Zhang, Jie Tang, Juan Bautista Cabotà |
| Abstract | The rapid development recently of Community Question Answering (CQA) satisfies users quest for professional and personal knowledge about anything. In CQA, one central issue is to find users with expertise and willingness to answer the given questions. Expert finding in CQA often exhibits very different challenges compared to traditional methods. Sparse data and new features violate fundamental assumptions of traditional recommendation systems. This paper focuses on reviewing and categorizing the current progress on expert finding in CQA. We classify all the existing solutions into four different categories: matrix factorization based models (MF-based models), gradient boosting tree based models (GBT-based models), deep learning based models (DL-based models) and ranking based models (R-based models). We find that MF-based models outperform other categories of models in the field of expert finding in CQA. Moreover, we use innovative diagrams to clarify several important concepts of ensemble learning, and find that ensemble models with several specific single models can further boosting the performance. Further, we compare the performance of different models on different types of matching tasks, including text vs. text, graph vs. text, audio vs. text and video vs. text. The results can help the model selection of expert finding in practice. Finally, we explore some potential future issues in expert finding research in CQA. |
| Tasks | Community Question Answering, Model Selection, Question Answering, Recommendation Systems |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1804.07958v1 |
| http://arxiv.org/pdf/1804.07958v1.pdf | |
| PWC | https://paperswithcode.com/paper/expert-finding-in-community-question |
| Repo | |
| Framework | |
An Acceleration Scheme to The Local Directional Pattern
| Title | An Acceleration Scheme to The Local Directional Pattern |
| Authors | Yasin Musa Ayami, Aboubayda Shabat |
| Abstract | This study seeks to improve the running time of the Local Directional Pattern (LDP) during feature extraction using a newly proposed acceleration scheme to LDP. LDP is considered to be computationally expensive. To confirm this, the running time of the LDP to gray level co-occurrence matrix (GLCM) were it was established that the running time for LDP was two orders of magnitude higher than that of the GLCM. In this study, the performance of the newly proposed acceleration scheme was evaluated against LDP and Local Binary patter (LBP) using images from the publicly available extended Cohn-Kanade (CK+) dataset. Based on our findings, the proposed acceleration scheme significantly improves the running time of the LDP by almost 3 times during feature extraction |
| Tasks | |
| Published | 2018-10-26 |
| URL | http://arxiv.org/abs/1810.11518v1 |
| http://arxiv.org/pdf/1810.11518v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-acceleration-scheme-to-the-local |
| Repo | |
| Framework | |
CT-image Super Resolution Using 3D Convolutional Neural Network
| Title | CT-image Super Resolution Using 3D Convolutional Neural Network |
| Authors | Yukai Wang, Qizhi Teng, Xiaohai He, Junxi Feng, Tingrong Zhang |
| Abstract | Computed Tomography (CT) imaging technique is widely used in geological exploration, medical diagnosis and other fields. In practice, however, the resolution of CT image is usually limited by scanning devices and great expense. Super resolution (SR) methods based on deep learning have achieved surprising performance in two-dimensional (2D) images. Unfortunately, there are few effective SR algorithms for three-dimensional (3D) images. In this paper, we proposed a novel network named as three-dimensional super resolution convolutional neural network (3DSRCNN) to realize voxel super resolution for CT images. To solve the practical problems in training process such as slow convergence of network training, insufficient memory, etc., we utilized adjustable learning rate, residual-learning, gradient clipping, momentum stochastic gradient descent (SGD) strategies to optimize training procedure. In addition, we have explored the empirical guidelines to set appropriate number of layers of network and how to use residual learning strategy. Additionally, previous learning-based algorithms need to separately train for different scale factors for reconstruction, yet our single model can complete the multi-scale SR. At last, our method has better performance in terms of PSNR, SSIM and efficiency compared with conventional methods. |
| Tasks | Computed Tomography (CT), Image Super-Resolution, Medical Diagnosis, Super-Resolution |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09074v1 |
| http://arxiv.org/pdf/1806.09074v1.pdf | |
| PWC | https://paperswithcode.com/paper/ct-image-super-resolution-using-3d |
| Repo | |
| Framework | |
Background Subtraction using Compressed Low-resolution Images
| Title | Background Subtraction using Compressed Low-resolution Images |
| Authors | Min Chen, Andy Song, Shivanthan A. C. Yhanandan, Jing Zhang |
| Abstract | Image processing and recognition are an important part of the modern society, with applications in fields such as advanced artificial intelligence, smart assistants, and security surveillance. The essential first step involved in almost all the visual tasks is background subtraction with a static camera. Ensuring that this critical step is performed in the most efficient manner would therefore improve all aspects related to objects recognition and tracking, behavior comprehension, etc.. Although background subtraction method has been applied for many years, its application suffers from real-time requirement. In this letter, we present a novel approach in implementing the background subtraction. The proposed method uses compressed, low-resolution grayscale image for the background subtraction. These low-resolution grayscale images were found to preserve the salient information very well. To verify the feasibility of our methodology, two prevalent methods, ViBe and GMM, are used in the experiment. The results of the proposed methodology confirm the effectiveness of our approach. |
| Tasks | |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10155v1 |
| http://arxiv.org/pdf/1810.10155v1.pdf | |
| PWC | https://paperswithcode.com/paper/background-subtraction-using-compressed-low |
| Repo | |
| Framework | |
Topic Modelling of Empirical Text Corpora: Validity, Reliability, and Reproducibility in Comparison to Semantic Maps
| Title | Topic Modelling of Empirical Text Corpora: Validity, Reliability, and Reproducibility in Comparison to Semantic Maps |
| Authors | Tobias Hecking, Loet Leydesdorff |
| Abstract | Using the 6,638 case descriptions of societal impact submitted for evaluation in the Research Excellence Framework (REF 2014), we replicate the topic model (Latent Dirichlet Allocation or LDA) made in this context and compare the results with factor-analytic results using a traditional word-document matrix (Principal Component Analysis or PCA). Removing a small fraction of documents from the sample, for example, has on average a much larger impact on LDA than on PCA-based models to the extent that the largest distortion in the case of PCA has less effect than the smallest distortion of LDA-based models. In terms of semantic coherence, however, LDA models outperform PCA-based models. The topic models inform us about the statistical properties of the document sets under study, but the results are statistical and should not be used for a semantic interpretation - for example, in grant selections and micro-decision making, or scholarly work-without follow-up using domain-specific semantic maps. |
| Tasks | Decision Making, Topic Models |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01045v1 |
| http://arxiv.org/pdf/1806.01045v1.pdf | |
| PWC | https://paperswithcode.com/paper/topic-modelling-of-empirical-text-corpora |
| Repo | |
| Framework | |
Cross-Domain Labeled LDA for Cross-Domain Text Classification
| Title | Cross-Domain Labeled LDA for Cross-Domain Text Classification |
| Authors | Baoyu Jing, Chenwei Lu, Deqing Wang, Fuzhen Zhuang, Cheng Niu |
| Abstract | Cross-domain text classification aims at building a classifier for a target domain which leverages data from both source and target domain. One promising idea is to minimize the feature distribution differences of the two domains. Most existing studies explicitly minimize such differences by an exact alignment mechanism (aligning features by one-to-one feature alignment, projection matrix etc.). Such exact alignment, however, will restrict models’ learning ability and will further impair models’ performance on classification tasks when the semantic distributions of different domains are very different. To address this problem, we propose a novel group alignment which aligns the semantics at group level. In addition, to help the model learn better semantic groups and semantics within these groups, we also propose a partial supervision for model’s learning in source domain. To this end, we embed the group alignment and a partial supervision into a cross-domain topic model, and propose a Cross-Domain Labeled LDA (CDL-LDA). On the standard 20Newsgroup and Reuters dataset, extensive quantitative (classification, perplexity etc.) and qualitative (topic detection) experiments are conducted to show the effectiveness of the proposed group alignment and partial supervision. |
| Tasks | Cross-Domain Text Classification, Text Classification |
| Published | 2018-09-16 |
| URL | http://arxiv.org/abs/1809.05820v1 |
| http://arxiv.org/pdf/1809.05820v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-domain-labeled-lda-for-cross-domain |
| Repo | |
| Framework | |
Hierarchical Recurrent Filtering for Fully Convolutional DenseNets
| Title | Hierarchical Recurrent Filtering for Fully Convolutional DenseNets |
| Authors | Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke |
| Abstract | Generating a robust representation of the environment is a crucial ability of learning agents. Deep learning based methods have greatly improved perception systems but still fail in challenging situations. These failures are often not solvable on the basis of a single image. In this work, we present a parameter-efficient temporal filtering concept which extends an existing single-frame segmentation model to work with multiple frames. The resulting recurrent architecture temporally filters representations on all abstraction levels in a hierarchical manner, while decoupling temporal dependencies from scene representation. Using a synthetic dataset, we show the ability of our model to cope with data perturbations and highlight the importance of recurrent and hierarchical filtering. |
| Tasks | |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02766v2 |
| http://arxiv.org/pdf/1810.02766v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-recurrent-filtering-for-fully |
| Repo | |
| Framework | |
Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning
| Title | Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning |
| Authors | Dengxin Dai, Wen Li, Till Kroeger, Luc Van Gool |
| Abstract | Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the CNNs. In this paper we present ManifoldNet, a novel method to encourage learning of manifold-aware representations. Our approach segments the input manifold into a set of fragments. By assigning the corresponding segmentation id as a pseudo label to every sample, we convert the problem of preserving the local manifold structure into a point-wise classification task. Due to its unsupervised nature, the segmentation tends to be noisy. We mitigate this by introducing ensemble manifold segmentation (EMS). EMS accounts for the manifold structure by dividing the training data into an ensemble of classification training sets that contain samples of local proximity. CNNs are trained on these ensembles under a multi-task learning framework to conform to the manifold. ManifoldNet can be trained with only the pseudo labels or together with task-specific labels. We evaluate ManifoldNet on two different tasks: network imitation (distillation) and semi-supervised learning. Our experiments show that the manifold structures are effectively utilized for both unsupervised and semi-supervised learning. |
| Tasks | Multi-Task Learning |
| Published | 2018-04-06 |
| URL | http://arxiv.org/abs/1804.02201v1 |
| http://arxiv.org/pdf/1804.02201v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-manifold-segmentation-for-model |
| Repo | |
| Framework | |
Morphologic for knowledge dynamics: revision, fusion, abduction
| Title | Morphologic for knowledge dynamics: revision, fusion, abduction |
| Authors | Isabelle Bloch, Jérôme Lang, Ramón Pino Pérez, Carlos Uzcátegui |
| Abstract | Several tasks in artificial intelligence require to be able to find models about knowledge dynamics. They include belief revision, fusion and belief merging, and abduction. In this paper we exploit the algebraic framework of mathematical morphology in the context of propositional logic, and define operations such as dilation or erosion of a set of formulas. We derive concrete operators, based on a semantic approach, that have an intuitive interpretation and that are formally well behaved, to perform revision, fusion and abduction. Computation and tractability are addressed, and simple examples illustrate the typical results that can be obtained. |
| Tasks | |
| Published | 2018-02-14 |
| URL | http://arxiv.org/abs/1802.05142v1 |
| http://arxiv.org/pdf/1802.05142v1.pdf | |
| PWC | https://paperswithcode.com/paper/morphologic-for-knowledge-dynamics-revision |
| Repo | |
| Framework | |
Hidden Integrality of SDP Relaxation for Sub-Gaussian Mixture Models
| Title | Hidden Integrality of SDP Relaxation for Sub-Gaussian Mixture Models |
| Authors | Yingjie Fei, Yudong Chen |
| Abstract | We consider the problem of estimating the discrete clustering structures under Sub-Gaussian Mixture Models. Our main results establish a hidden integrality property of a semidefinite programming (SDP) relaxation for this problem: while the optimal solutions to the SDP are not integer-valued in general, their estimation errors can be upper bounded in terms of the error of an idealized integer program. The error of the integer program, and hence that of the SDP, are further shown to decay exponentially in the signal-to-noise ratio. To the best of our knowledge, this is the first exponentially decaying error bound for convex relaxations of mixture models, and our results reveal the “global-to-local” mechanism that drives the performance of the SDP relaxation. A corollary of our results shows that in certain regimes the SDP solutions are in fact integral and exact, improving on existing exact recovery results for convex relaxations. More generally, our results establish sufficient conditions for the SDP to correctly recover the cluster memberships of $(1-\delta)$ fraction of the points for any $\delta\in(0,1)$. As a special case, we show that under the $d$-dimensional Stochastic Ball Model, SDP achieves non-trivial (sometimes exact) recovery when the center separation is as small as $\sqrt{1/d}$, which complements previous exact recovery results that require constant separation. |
| Tasks | |
| Published | 2018-03-17 |
| URL | http://arxiv.org/abs/1803.06510v1 |
| http://arxiv.org/pdf/1803.06510v1.pdf | |
| PWC | https://paperswithcode.com/paper/hidden-integrality-of-sdp-relaxation-for-sub |
| Repo | |
| Framework | |
Computationally Efficient Estimation of the Spectral Gap of a Markov Chain
| Title | Computationally Efficient Estimation of the Spectral Gap of a Markov Chain |
| Authors | Richard Combes, Mikael Touati |
| Abstract | We consider the problem of estimating from sample paths the absolute spectral gap $\gamma_*$ of a reversible, irreducible and aperiodic Markov chain $(X_t)_{t \in \mathbb{N}}$ over a finite state space $\Omega$. We propose the ${\tt UCPI}$ (Upper Confidence Power Iteration) algorithm for this problem, a low-complexity algorithm which estimates the spectral gap in time ${\cal O}(n)$ and memory space ${\cal O}((\ln n)^2)$ given $n$ samples. This is in stark contrast with most known methods which require at least memory space ${\cal O}(\Omega)$, so that they cannot be applied to large state spaces. Furthermore, ${\tt UCPI}$ is amenable to parallel implementation. |
| Tasks | |
| Published | 2018-06-15 |
| URL | http://arxiv.org/abs/1806.06047v2 |
| http://arxiv.org/pdf/1806.06047v2.pdf | |
| PWC | https://paperswithcode.com/paper/computationally-efficient-estimation-of-the |
| Repo | |
| Framework | |
Investigations on End-to-End Audiovisual Fusion
| Title | Investigations on End-to-End Audiovisual Fusion |
| Authors | Michael Wand, Ngoc Thang Vu, Juergen Schmidhuber |
| Abstract | Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separately model the process of decision fusion as in conventional (e.g. HMM-based) systems. The fusion system outperforms single-modality recognition under all noise conditions. Investigation of the saliency of the input features shows that the neural network automatically adapts to different noise levels in the acoustic signal. |
| Tasks | Speech Recognition |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1804.11127v1 |
| http://arxiv.org/pdf/1804.11127v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigations-on-end-to-end-audiovisual |
| Repo | |
| Framework | |
Per-decision Multi-step Temporal Difference Learning with Control Variates
| Title | Per-decision Multi-step Temporal Difference Learning with Control Variates |
| Authors | Kristopher De Asis, Richard S. Sutton |
| Abstract | Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be poor, and incorporating longer sampled reward sequences into the updates. Especially in the off-policy setting, where the agent aims to learn about a policy different from the one generating its behaviour, the variance in the updates can cause learning to diverge as the number of sampled rewards used in the estimates increases. In this paper, we introduce per-decision control variates for multi-step TD algorithms, and compare them to existing methods. Our results show that including the control variates can greatly improve performance on both on and off-policy multi-step temporal difference learning tasks. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.01830v1 |
| http://arxiv.org/pdf/1807.01830v1.pdf | |
| PWC | https://paperswithcode.com/paper/per-decision-multi-step-temporal-difference |
| Repo | |
| Framework | |
Learning and analyzing vector encoding of symbolic representations
| Title | Learning and analyzing vector encoding of symbolic representations |
| Authors | Roland Fernandez, Asli Celikyilmaz, Rishabh Singh, Paul Smolensky |
| Abstract | We present a formal language with expressions denoting general symbol structures and queries which access information in those structures. A sequence-to-sequence network processing this language learns to encode symbol structures and query them. The learned representation (approximately) shares a simple linearity property with theoretical techniques for performing this task. |
| Tasks | |
| Published | 2018-03-10 |
| URL | http://arxiv.org/abs/1803.03834v1 |
| http://arxiv.org/pdf/1803.03834v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-and-analyzing-vector-encoding-of |
| Repo | |
| Framework | |
Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing
| Title | Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing |
| Authors | Daniel Fried, Dan Klein |
| Abstract | Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser’s transition system. We explore using a policy gradient method as a parser-agnostic alternative. In addition to directly optimizing for a tree-level metric such as F1, policy gradient has the potential to reduce exposure bias by allowing exploration during training; moreover, it does not require a dynamic oracle for supervision. On four constituency parsers in three languages, the method substantially outperforms static oracle likelihood training in almost all settings. For parsers where a dynamic oracle is available (including a novel oracle which we define for the transition system of Dyer et al. 2016), policy gradient typically recaptures a substantial fraction of the performance gain afforded by the dynamic oracle. |
| Tasks | Constituency Parsing |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03290v1 |
| http://arxiv.org/pdf/1806.03290v1.pdf | |
| PWC | https://paperswithcode.com/paper/policy-gradient-as-a-proxy-for-dynamic |
| Repo | |
| Framework | |
