Paper Group ANR 18
Sentence Modeling via Multiple Word Embeddings and Multi-level Comparison for Semantic Textual Similarity. Estimation and Tracking of AP-diameter of the Inferior Vena Cava in Ultrasound Images Using a Novel Active Circle Algorithm. Prediction of Autism Treatment Response from Baseline fMRI using Random Forests and Tree Bagging. Learning Sentence Em …
Sentence Modeling via Multiple Word Embeddings and Multi-level Comparison for Semantic Textual Similarity
| Title | Sentence Modeling via Multiple Word Embeddings and Multi-level Comparison for Semantic Textual Similarity |
| Authors | Huy Nguyen Tien, Minh Nguyen Le, Yamasaki Tomohiro, Izuha Tatsuya |
| Abstract | Different word embedding models capture different aspects of linguistic properties. This inspired us to propose a model (M-MaxLSTM-CNN) for employing multiple sets of word embeddings for evaluating sentence similarity/relation. Representing each word by multiple word embeddings, the MaxLSTM-CNN encoder generates a novel sentence embedding. We then learn the similarity/relation between our sentence embeddings via Multi-level comparison. Our method M-MaxLSTM-CNN consistently shows strong performances in several tasks (i.e., measure textual similarity, identify paraphrase, recognize textual entailment). According to the experimental results on STS Benchmark dataset and SICK dataset from SemEval, M-MaxLSTM-CNN outperforms the state-of-the-art methods for textual similarity tasks. Our model does not use hand-crafted features (e.g., alignment features, Ngram overlaps, dependency features) as well as does not require pre-trained word embeddings to have the same dimension. |
| Tasks | Natural Language Inference, Semantic Textual Similarity, Sentence Embedding, Sentence Embeddings, Word Embeddings |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07882v1 |
| http://arxiv.org/pdf/1805.07882v1.pdf | |
| PWC | https://paperswithcode.com/paper/sentence-modeling-via-multiple-word |
| Repo | |
| Framework | |
Estimation and Tracking of AP-diameter of the Inferior Vena Cava in Ultrasound Images Using a Novel Active Circle Algorithm
| Title | Estimation and Tracking of AP-diameter of the Inferior Vena Cava in Ultrasound Images Using a Novel Active Circle Algorithm |
| Authors | Ebrahim Karami, Mohamed Shehata, Andrew Smith |
| Abstract | Medical research suggests that the anterior-posterior (AP)-diameter of the inferior vena cava (IVC) and its associated temporal variation as imaged by bedside ultrasound is useful in guiding fluid resuscitation of the critically-ill patient. Unfortunately, indistinct edges and gaps in vessel walls are frequently present which impede accurate estimation of the IVC AP-diameter for both human operators and segmentation algorithms. The majority of research involving use of the IVC to guide fluid resuscitation involves manual measurement of the maximum and minimum AP-diameter as it varies over time. This effort proposes using a time-varying circle fitted inside the typically ellipsoid IVC as an efficient, consistent and novel approach to tracking and approximating the AP-diameter even in the context of poor image quality. In this active-circle algorithm, a novel evolution functional is proposed and shown to be a useful tool for ultrasound image processing. The proposed algorithm is compared with an expert manual measurement, and state-of-the-art relevant algorithms. It is shown that the algorithm outperforms other techniques and performs very close to manual measurement. |
| Tasks | |
| Published | 2018-05-05 |
| URL | http://arxiv.org/abs/1805.02125v3 |
| http://arxiv.org/pdf/1805.02125v3.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-and-tracking-of-ap-diameter-of-the |
| Repo | |
| Framework | |
Prediction of Autism Treatment Response from Baseline fMRI using Random Forests and Tree Bagging
| Title | Prediction of Autism Treatment Response from Baseline fMRI using Random Forests and Tree Bagging |
| Authors | Nicha C. Dvornek, Daniel Yang, Archana Venkataraman, Pamela Ventola, Lawrence H. Staib, Kevin A. Pelphrey, James S. Duncan |
| Abstract | Treating children with autism spectrum disorders (ASD) with behavioral interventions, such as Pivotal Response Treatment (PRT), has shown promise in recent studies. However, deciding which therapy is best for a given patient is largely by trial and error, and choosing an ineffective intervention results in loss of valuable treatment time. We propose predicting patient response to PRT from baseline task-based fMRI by the novel application of a random forest and tree bagging strategy. Our proposed learning pipeline uses random forest regression to determine candidate brain voxels that may be informative in predicting treatment response. The candidate voxels are then tested stepwise for inclusion in a bagged tree ensemble. After the predictive model is constructed, bias correction is performed to further increase prediction accuracy. Using data from 19 ASD children who underwent a 16 week trial of PRT and a leave-one-out cross-validation framework, the presented learning pipeline was tested against several standard methods and variations of the pipeline and resulted in the highest prediction accuracy. |
| Tasks | |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09799v1 |
| http://arxiv.org/pdf/1805.09799v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-autism-treatment-response-from |
| Repo | |
| Framework | |
Learning Sentence Embeddings for Coherence Modelling and Beyond
| Title | Learning Sentence Embeddings for Coherence Modelling and Beyond |
| Authors | Tanner Bohn, Yining Hu, Jinhang Zhang, Charles X. Ling |
| Abstract | We present a novel and effective technique for performing text coherence tasks while facilitating deeper insights into the data. Despite obtaining ever-increasing task performance, modern deep-learning approaches to NLP tasks often only provide users with the final network decision and no additional understanding of the data. In this work, we show that a new type of sentence embedding learned through self-supervision can be applied effectively to text coherence tasks while serving as a window through which deeper understanding of the data can be obtained. To produce these sentence embeddings, we train a recurrent neural network to take individual sentences and predict their location in a document in the form of a distribution over locations. We demonstrate that these embeddings, combined with simple visual heuristics, can be used to achieve performance competitive with state-of-the-art on multiple text coherence tasks, outperforming more complex and specialized approaches. Additionally, we demonstrate that these embeddings can provide insights useful to writers for improving writing quality and informing document structuring, and assisting readers in summarizing and locating information. |
| Tasks | Sentence Embedding, Sentence Embeddings |
| Published | 2018-04-22 |
| URL | https://arxiv.org/abs/1804.08053v2 |
| https://arxiv.org/pdf/1804.08053v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-sentence-location-prediction-for |
| Repo | |
| Framework | |
Beyond $1/2$-Approximation for Submodular Maximization on Massive Data Streams
| Title | Beyond $1/2$-Approximation for Submodular Maximization on Massive Data Streams |
| Authors | Ashkan Norouzi-Fard, Jakub Tarnawski, Slobodan Mitrović, Amir Zandieh, Aida Mousavifar, Ola Svensson |
| Abstract | Many tasks in machine learning and data mining, such as data diversification, non-parametric learning, kernel machines, clustering etc., require extracting a small but representative summary from a massive dataset. Often, such problems can be posed as maximizing a submodular set function subject to a cardinality constraint. We consider this question in the streaming setting, where elements arrive over time at a fast pace and thus we need to design an efficient, low-memory algorithm. One such method, proposed by Badanidiyuru et al. (2014), always finds a $0.5$-approximate solution. Can this approximation factor be improved? We answer this question affirmatively by designing a new algorithm SALSA for streaming submodular maximization. It is the first low-memory, single-pass algorithm that improves the factor $0.5$, under the natural assumption that elements arrive in a random order. We also show that this assumption is necessary, i.e., that there is no such algorithm with better than $0.5$-approximation when elements arrive in arbitrary order. Our experiments demonstrate that SALSA significantly outperforms the state of the art in applications related to exemplar-based clustering, social graph analysis, and recommender systems. |
| Tasks | Recommendation Systems |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.01842v1 |
| http://arxiv.org/pdf/1808.01842v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-12-approximation-for-submodular |
| Repo | |
| Framework | |
A determinantal point process for column subset selection
| Title | A determinantal point process for column subset selection |
| Authors | Ayoub Belhadji, Rémi Bardenet, Pierre Chainais |
| Abstract | Dimensionality reduction is a first step of many machine learning pipelines. Two popular approaches are principal component analysis, which projects onto a small number of well chosen but non-interpretable directions, and feature selection, which selects a small number of the original features. Feature selection can be abstracted as a numerical linear algebra problem called the column subset selection problem (CSSP). CSSP corresponds to selecting the best subset of columns of a matrix $X \in \mathbb{R}^{N \times d}$, where \emph{best} is often meant in the sense of minimizing the approximation error, i.e., the norm of the residual after projection of $X$ onto the space spanned by the selected columns. Such an optimization over subsets of ${1,\dots,d}$ is usually impractical. One workaround that has been vastly explored is to resort to polynomial-cost, random subset selection algorithms that favor small values of this approximation error. We propose such a randomized algorithm, based on sampling from a projection determinantal point process (DPP), a repulsive distribution over a fixed number $k$ of indices ${1,\dots,d}$ that favors diversity among the selected columns. We give bounds on the ratio of the expected approximation error for this DPP over the optimal error of PCA. These bounds improve over the state-of-the-art bounds of \emph{volume sampling} when some realistic structural assumptions are satisfied for $X$. Numerical experiments suggest that our bounds are tight, and that our algorithms have comparable performance with the \emph{double phase} algorithm, often considered to be the practical state-of-the-art. Column subset selection with DPPs thus inherits the best of both worlds: good empirical performance and tight error bounds. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2018-12-23 |
| URL | http://arxiv.org/abs/1812.09771v1 |
| http://arxiv.org/pdf/1812.09771v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-determinantal-point-process-for-column |
| Repo | |
| Framework | |
An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering
| Title | An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering |
| Authors | Hui Han Chin, Paul Pu Liang |
| Abstract | The power of randomized algorithms in numerical methods have led to fast solutions which use the Singular Value Decomposition (SVD) as a core routine. However, given the large data size of modern and the modest runtime of SVD, most practical algorithms would require some form of approximation, such as sketching, when running SVD. While these approximation methods satisfy many theoretical guarantees, we provide the first algorithmic implementations for sketch-and-solve SVD problems on real-world, large-scale datasets. We provide a comprehensive empirical evaluation of these algorithms and provide guidelines on how to ensure accurate deployment to real-world data. As an application of sketched SVD, we present Sketched Leverage Score Ordering, a technique for determining the ordering of data in the training of neural networks. Our technique is based on the distributed computation of leverage scores using random projections. These computed leverage scores provide a flexible and efficient method to determine the optimal ordering of training data without manual intervention or annotations. We present empirical results on an extensive set of experiments across image classification, language sentiment analysis, and multi-modal sentiment analysis. Our method is faster compared to standard randomized projection algorithms and shows improvements in convergence and results. |
| Tasks | Image Classification, Sentiment Analysis |
| Published | 2018-12-19 |
| URL | http://arxiv.org/abs/1812.07903v1 |
| http://arxiv.org/pdf/1812.07903v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-empirical-evaluation-of-sketched-svd-and |
| Repo | |
| Framework | |
Explainable Recommendation: A Survey and New Perspectives
| Title | Explainable Recommendation: A Survey and New Perspectives |
| Authors | Yongfeng Zhang, Xu Chen |
| Abstract | Explainable recommendation attempts to develop models that generate not only high-quality recommendations but also intuitive explanations. The explanations may either be post-hoc or directly come from an explainable model (also called interpretable or transparent model in some contexts). Explainable recommendation tries to address the problem of why: by providing explanations to users or system designers, it helps humans to understand why certain items are recommended by the algorithm, where the human can either be users or system designers. Explainable recommendation helps to improve the transparency, persuasiveness, effectiveness, trustworthiness, and satisfaction of recommendation systems. It also facilitates system designers for better system debugging. In recent years, a large number of explainable recommendation approaches – especially model-based methods – have been proposed and applied in real-world systems. In this survey, we provide a comprehensive review for the explainable recommendation research. We first highlight the position of explainable recommendation in recommender system research by categorizing recommendation problems into the 5W, i.e., what, when, who, where, and why. We then conduct a comprehensive survey of explainable recommendation on three perspectives: 1) We provide a chronological research timeline of explainable recommendation. 2) We provide a two-dimensional taxonomy to classify existing explainable recommendation research. 3) We summarize how explainable recommendation applies to different recommendation tasks. We also devote a chapter to discuss the explanation perspectives in broader IR and AI/ML research. We end the survey by discussing potential future directions to promote the explainable recommendation research area and beyond. |
| Tasks | Product Recommendation, Recommendation Systems |
| Published | 2018-04-30 |
| URL | https://arxiv.org/abs/1804.11192v9 |
| https://arxiv.org/pdf/1804.11192v9.pdf | |
| PWC | https://paperswithcode.com/paper/explainable-recommendation-a-survey-and-new |
| Repo | |
| Framework | |
Machine learning architectures to predict motion sickness using a Virtual Reality rollercoaster simulation tool
| Title | Machine learning architectures to predict motion sickness using a Virtual Reality rollercoaster simulation tool |
| Authors | Stefan Hell, Vasileios Argyriou |
| Abstract | Virtual Reality (VR) can cause an unprecedented immersion and feeling of presence yet a lot of users experience motion sickness when moving through a virtual environment. Rollercoaster rides are popular in Virtual Reality but have to be well designed to limit the amount of nausea the user may feel. This paper describes a novel framework to get automated ratings on motion sickness using Neural Networks. An application that lets users create rollercoasters directly in VR, share them with other users and ride and rate them is used to gather real-time data related to the in-game behaviour of the player, the track itself and users’ ratings based on a Simulator Sickness Questionnaire (SSQ) integrated into the application. Machine learning architectures based on deep neural networks are trained using this data aiming to predict motion sickness levels. While this paper focuses on rollercoasters this framework could help to rate any VR application on motion sickness and intensity that involves camera movement. A new well defined dataset is provided in this paper and the performance of the proposed architectures are evaluated in a comparative study. |
| Tasks | |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.01106v1 |
| http://arxiv.org/pdf/1811.01106v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-architectures-to-predict |
| Repo | |
| Framework | |
Closed-loop Bayesian Semantic Data Fusion for Collaborative Human-Autonomy Target Search
| Title | Closed-loop Bayesian Semantic Data Fusion for Collaborative Human-Autonomy Target Search |
| Authors | Luke Burks, Ian Loefgren, Luke Barbier, Jeremy Muesing, Jamison McGinley, Sousheel Vunnam, Nisar Ahmed |
| Abstract | In search applications, autonomous unmanned vehicles must be able to efficiently reacquire and localize mobile targets that can remain out of view for long periods of time in large spaces. As such, all available information sources must be actively leveraged – including imprecise but readily available semantic observations provided by humans. To achieve this, this work develops and validates a novel collaborative human-machine sensing solution for dynamic target search. Our approach uses continuous partially observable Markov decision process (CPOMDP) planning to generate vehicle trajectories that optimally exploit imperfect detection data from onboard sensors, as well as semantic natural language observations that can be specifically requested from human sensors. The key innovation is a scalable hierarchical Gaussian mixture model formulation for efficiently solving CPOMDPs with semantic observations in continuous dynamic state spaces. The approach is demonstrated and validated with a real human-robot team engaged in dynamic indoor target search and capture scenarios on a custom testbed. |
| Tasks | |
| Published | 2018-06-03 |
| URL | http://arxiv.org/abs/1806.00727v1 |
| http://arxiv.org/pdf/1806.00727v1.pdf | |
| PWC | https://paperswithcode.com/paper/closed-loop-bayesian-semantic-data-fusion-for |
| Repo | |
| Framework | |
Fast Artificial Immune Systems
| Title | Fast Artificial Immune Systems |
| Authors | Dogan Corus, Pietro S. Oliveto, Donya Yazdani |
| Abstract | Various studies have shown that characteristic Artificial Immune System (AIS) operators such as hypermutations and ageing can be very efficient at escaping local optima of multimodal optimisation problems. However, this efficiency comes at the expense of considerably slower runtimes during the exploitation phase compared to standard evolutionary algorithms. We propose modifications to the traditional hypermutations with mutation potential' (HMP) that allow them to be efficient at exploitation as well as maintaining their effective explorative characteristics. Rather than deterministically evaluating fitness after each bitflip of a hypermutation, we sample the fitness function stochastically with a parabolic’ distribution which allows the `stop at first constructive mutation’ (FCM) variant of HMP to reduce the linear amount of wasted function evaluations when no improvement is found to a constant. By returning the best sampled solution during the hypermutation, rather than the first constructive mutation, we then turn the extremely inefficient HMP operator without FCM, into a very effective operator for the standard Opt-IA AIS using hypermutation, cloning and ageing. We rigorously prove the effectiveness of the two proposed operators by analysing them on all problems where the performance of HPM is rigorously understood in the literature. % | |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00299v1 |
| http://arxiv.org/pdf/1806.00299v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-artificial-immune-systems |
| Repo | |
| Framework | |
On the Behavior of the Expectation-Maximization Algorithm for Mixture Models
| Title | On the Behavior of the Expectation-Maximization Algorithm for Mixture Models |
| Authors | Babak Barazandeh, Meisam Razaviyayn |
| Abstract | Finite mixture models are among the most popular statistical models used in different data science disciplines. Despite their broad applicability, inference under these models typically leads to computationally challenging non-convex problems. While the Expectation-Maximization (EM) algorithm is the most popular approach for solving these non-convex problems, the behavior of this algorithm is not well understood. In this work, we focus on the case of mixture of Laplacian (or Gaussian) distribution. We start by analyzing a simple equally weighted mixture of two single dimensional Laplacian distributions and show that every local optimum of the population maximum likelihood estimation problem is globally optimal. Then, we prove that the EM algorithm converges to the ground truth parameters almost surely with random initialization. Our result extends the existing results for Gaussian distribution to Laplacian distribution. Then we numerically study the behavior of mixture models with more than two components. Motivated by our extensive numerical experiments, we propose a novel stochastic method for estimating the mean of components of a mixture model. Our numerical experiments show that our algorithm outperforms the Naive EM algorithm in almost all scenarios. |
| Tasks | |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.08705v1 |
| http://arxiv.org/pdf/1809.08705v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-behavior-of-the-expectation |
| Repo | |
| Framework | |
PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
| Title | PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening |
| Authors | Xiangyu Liu, Yunhong Wang, Qingjie Liu |
| Abstract | Remote sensing image fusion (also known as pan-sharpening) aims to generate a high resolution multi-spectral image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral (MS) image. In this paper, we propose PSGAN, a generative adversarial network (GAN) for remote sensing image pan-sharpening. To the best of our knowledge, this is the first attempt at producing high quality pan-sharpened images with GANs. The PSGAN consists of two parts. Firstly, a two-stream fusion architecture is designed to generate the desired high resolution multi-spectral images, then a fully convolutional network serving as a discriminator is applied to distinct “real” or “pan-sharpened” MS images. Experiments on images acquired by Quickbird and GaoFen-1 satellites demonstrate that the proposed PSGAN can fuse PAN and MS images effectively and significantly improve the results over the state of the art traditional and CNN based pan-sharpening methods. |
| Tasks | |
| Published | 2018-05-09 |
| URL | https://arxiv.org/abs/1805.03371v3 |
| https://arxiv.org/pdf/1805.03371v3.pdf | |
| PWC | https://paperswithcode.com/paper/psgan-a-generative-adversarial-network-for |
| Repo | |
| Framework | |
Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis
| Title | Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis |
| Authors | Zi Wang, Dali Wang, Chengcheng Li, Yichi Xu, Husheng Li, Zhirong Bao |
| Abstract | Cell movement in the early phase of C. elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have shown that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulation networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse images. We present a deep reinforcement learning approach within an ABM system to characterize cell movement in C. elegans embryogenesis. Our modeling system captures the complexity of cell movement patterns in the embryo and overcomes the local optimization problem encountered by traditional rule-based, ABM that uses greedy algorithms. We tested our model with two real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the rearrangement of the left-right asymmetry. In the first case, model results showed that Cpaaa’s intercalation is an active directional cell movement caused by the continuous effects from a longer distance, as opposed to a passive movement caused by neighbor cell movements. This is because the learning-based simulation found that a passive movement model could not lead Cpaaa to the predefined destination. In the second case, a leader-follower mechanism well explained the collective cell movement pattern. These results showed that our approach to introduce deep reinforcement learning into ABM can test regulatory mechanisms by exploring cell migration paths in a reverse engineering perspective. This model opens new doors to explore large datasets generated by live imaging. |
| Tasks | |
| Published | 2018-01-14 |
| URL | http://arxiv.org/abs/1801.04600v2 |
| http://arxiv.org/pdf/1801.04600v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-of-cell-movement |
| Repo | |
| Framework | |
Optimal Seeding and Self-Reproduction from a Mathematical Point of View
| Title | Optimal Seeding and Self-Reproduction from a Mathematical Point of View |
| Authors | Rita Gitik |
| Abstract | P. Kabamba developed generation theory as a tool for studying self-reproducing systems. We provide an alternative definition of a generation system and give a complete solution to the problem of finding optimal seeds for a finite self-replicating system. We also exhibit examples illustrating a connection between self-replication and fixed-point theory. |
| Tasks | |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.09506v1 |
| http://arxiv.org/pdf/1806.09506v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-seeding-and-self-reproduction-from-a |
| Repo | |
| Framework | |
