Paper Group ANR 232
A Biomedical Information Extraction Primer for NLP Researchers. Emo, Love, and God: Making Sense of Urban Dictionary, a Crowd-Sourced Online Dictionary. Improving high-pass fusion method using wavelets. Detecting confounding in multivariate linear models via spectral analysis. Nearest Labelset Using Double Distances for Multi-label Classification. …
A Biomedical Information Extraction Primer for NLP Researchers
| Title | A Biomedical Information Extraction Primer for NLP Researchers |
| Authors | Surag Nair |
| Abstract | Biomedical Information Extraction is an exciting field at the crossroads of Natural Language Processing, Biology and Medicine. It encompasses a variety of different tasks that require application of state-of-the-art NLP techniques, such as NER and Relation Extraction. This paper provides an overview of the problems in the field and discusses some of the techniques used for solving them. |
| Tasks | Relation Extraction |
| Published | 2017-05-10 |
| URL | http://arxiv.org/abs/1705.05437v1 |
| http://arxiv.org/pdf/1705.05437v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-biomedical-information-extraction-primer |
| Repo | |
| Framework | |
Emo, Love, and God: Making Sense of Urban Dictionary, a Crowd-Sourced Online Dictionary
| Title | Emo, Love, and God: Making Sense of Urban Dictionary, a Crowd-Sourced Online Dictionary |
| Authors | Dong Nguyen, Barbara McGillivray, Taha Yasseri |
| Abstract | The Internet facilitates large-scale collaborative projects and the emergence of Web 2.0 platforms, where producers and consumers of content unify, has drastically changed the information market. On the one hand, the promise of the “wisdom of the crowd” has inspired successful projects such as Wikipedia, which has become the primary source of crowd-based information in many languages. On the other hand, the decentralized and often un-monitored environment of such projects may make them susceptible to low quality content. In this work, we focus on Urban Dictionary, a crowd-sourced online dictionary. We combine computational methods with qualitative annotation and shed light on the overall features of Urban Dictionary in terms of growth, coverage and types of content. We measure a high presence of opinion-focused entries, as opposed to the meaning-focused entries that we expect from traditional dictionaries. Furthermore, Urban Dictionary covers many informal, unfamiliar words as well as proper nouns. Urban Dictionary also contains offensive content, but highly offensive content tends to receive lower scores through the dictionary’s voting system. The low threshold to include new material in Urban Dictionary enables quick recording of new words and new meanings, but the resulting heterogeneous content can pose challenges in using Urban Dictionary as a source to study language innovation. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08647v2 |
| http://arxiv.org/pdf/1712.08647v2.pdf | |
| PWC | https://paperswithcode.com/paper/emo-love-and-god-making-sense-of-urban |
| Repo | |
| Framework | |
Improving high-pass fusion method using wavelets
| Title | Improving high-pass fusion method using wavelets |
| Authors | Hamid Reza Shahdoosti |
| Abstract | In an appropriate image fusion method, spatial information of the panchromatic image is injected into the multispectral images such that the spectral information is not distorted. The high-pass modulation method is a successful method in image fusion. However, the main drawback of this method is that this technique uses the boxcar filter to extract the high frequency information of the panchromatic image. Using the boxcar filter introduces the ringing effect into the fused image. To cope with this problem, we use the wavelet transform instead of boxcar filters. Then, the results of the proposed method and those of other methods such as, Brovey, IHS, and PCA ones are compared. Experiments show the superiority of the proposed method in terms of correlation coefficient and mutual information. |
| Tasks | |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07343v1 |
| http://arxiv.org/pdf/1702.07343v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-high-pass-fusion-method-using |
| Repo | |
| Framework | |
Detecting confounding in multivariate linear models via spectral analysis
| Title | Detecting confounding in multivariate linear models via spectral analysis |
| Authors | Dominik Janzing, Bernhard Schoelkopf |
| Abstract | We study a model where one target variable Y is correlated with a vector X:=(X_1,…,X_d) of predictor variables being potential causes of Y. We describe a method that infers to what extent the statistical dependences between X and Y are due to the influence of X on Y and to what extent due to a hidden common cause (confounder) of X and Y. The method relies on concentration of measure results for large dimensions d and an independence assumption stating that, in the absence of confounding, the vector of regression coefficients describing the influence of each X on Y typically has `generic orientation’ relative to the eigenspaces of the covariance matrix of X. For the special case of a scalar confounder we show that confounding typically spoils this generic orientation in a characteristic way that can be used to quantitatively estimate the amount of confounding. | |
| Tasks | |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01430v1 |
| http://arxiv.org/pdf/1704.01430v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-confounding-in-multivariate-linear |
| Repo | |
| Framework | |
Nearest Labelset Using Double Distances for Multi-label Classification
| Title | Nearest Labelset Using Double Distances for Multi-label Classification |
| Authors | Hyukjun Gweon, Matthias Schonlau, Stefan Steiner |
| Abstract | Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this paper we propose a novel approach, Nearest Labelset using Double Distances (NLDD), that predicts the labelset observed in the training data that minimizes a weighted sum of the distances in both the feature space and the label space to the new instance. The weights specify the relative tradeoff between the two distances. The weights are estimated from a binomial regression of the number of misclassified labels as a function of the two distances. Model parameters are estimated by maximum likelihood. NLDD only considers labelsets observed in the training data, thus implicitly taking into account label dependencies. Experiments on benchmark multi-label data sets show that the proposed method on average outperforms other well-known approaches in terms of Hamming loss, 0/1 loss, and multi-label accuracy and ranks second after ECC on the F-measure. |
| Tasks | Multi-Label Classification |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04684v1 |
| http://arxiv.org/pdf/1702.04684v1.pdf | |
| PWC | https://paperswithcode.com/paper/nearest-labelset-using-double-distances-for |
| Repo | |
| Framework | |
Simultaneously Solving Mixed Model Assembly Line Balancing and Sequencing problems with FSS Algorithm
| Title | Simultaneously Solving Mixed Model Assembly Line Balancing and Sequencing problems with FSS Algorithm |
| Authors | Joao Batista Monteiro Filho, Isabela Maria Carneiro de Albuquerque, Fernando Buarque de Lima Neto |
| Abstract | Many assembly lines related optimization problems have been tackled by researchers in the last decades due to its relevance for the decision makers within manufacturing industry. Many of theses problems, more specifically Assembly Lines Balancing and Sequencing problems, are known to be NP-Hard. Therefore, Computational Intelligence solution approaches have been conceived in order to provide practical use decision making tools. In this work, we proposed a simultaneous solution approach in order to tackle both Balancing and Sequencing problems utilizing an effective meta-heuristic algorithm referred as Fish School Search. Three different test instances were solved with the original and two modified versions of this algorithm and the results were compared with Particle Swarm Optimization Algorithm. |
| Tasks | Decision Making |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.06185v1 |
| http://arxiv.org/pdf/1707.06185v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneously-solving-mixed-model-assembly |
| Repo | |
| Framework | |
Making Neural Programming Architectures Generalize via Recursion
| Title | Making Neural Programming Architectures Generalize via Recursion |
| Authors | Jonathon Cai, Richard Shin, Dawn Song |
| Abstract | Empirically, neural networks that attempt to learn programs from data have exhibited poor generalizability. Moreover, it has traditionally been difficult to reason about the behavior of these models beyond a certain level of input complexity. In order to address these issues, we propose augmenting neural architectures with a key abstraction: recursion. As an application, we implement recursion in the Neural Programmer-Interpreter framework on four tasks: grade-school addition, bubble sort, topological sort, and quicksort. We demonstrate superior generalizability and interpretability with small amounts of training data. Recursion divides the problem into smaller pieces and drastically reduces the domain of each neural network component, making it tractable to prove guarantees about the overall system’s behavior. Our experience suggests that in order for neural architectures to robustly learn program semantics, it is necessary to incorporate a concept like recursion. |
| Tasks | |
| Published | 2017-04-21 |
| URL | http://arxiv.org/abs/1704.06611v1 |
| http://arxiv.org/pdf/1704.06611v1.pdf | |
| PWC | https://paperswithcode.com/paper/making-neural-programming-architectures |
| Repo | |
| Framework | |
Cooperative Multi-Agent Planning: A Survey
| Title | Cooperative Multi-Agent Planning: A Survey |
| Authors | Alejandro Torreño, Eva Onaindia, Antonín Komenda, Michal Štolba |
| Abstract | Cooperative multi-agent planning (MAP) is a relatively recent research field that combines technologies, algorithms and techniques developed by the Artificial Intelligence Planning and Multi-Agent Systems communities. While planning has been generally treated as a single-agent task, MAP generalizes this concept by considering multiple intelligent agents that work cooperatively to develop a course of action that satisfies the goals of the group. This paper reviews the most relevant approaches to MAP, putting the focus on the solvers that took part in the 2015 Competition of Distributed and Multi-Agent Planning, and classifies them according to their key features and relative performance. |
| Tasks | |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.09057v1 |
| http://arxiv.org/pdf/1711.09057v1.pdf | |
| PWC | https://paperswithcode.com/paper/cooperative-multi-agent-planning-a-survey |
| Repo | |
| Framework | |
Deep Learning for User Comment Moderation
| Title | Deep Learning for User Comment Moderation |
| Authors | John Pavlopoulos, Prodromos Malakasiotis, Ion Androutsopoulos |
| Abstract | Experimenting with a new dataset of 1.6M user comments from a Greek news portal and existing datasets of English Wikipedia comments, we show that an RNN outperforms the previous state of the art in moderation. A deep, classification-specific attention mechanism improves further the overall performance of the RNN. We also compare against a CNN and a word-list baseline, considering both fully automatic and semi-automatic moderation. |
| Tasks | |
| Published | 2017-05-28 |
| URL | http://arxiv.org/abs/1705.09993v2 |
| http://arxiv.org/pdf/1705.09993v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-user-comment-moderation |
| Repo | |
| Framework | |
Subject Specific Stream Classification Preprocessing Algorithm for Twitter Data Stream
| Title | Subject Specific Stream Classification Preprocessing Algorithm for Twitter Data Stream |
| Authors | Nisansa de Silva, Danaja Maldeniya, Chamilka Wijeratne |
| Abstract | Micro-blogging service Twitter is a lucrative source for data mining applications on global sentiment. But due to the omnifariousness of the subjects mentioned in each data item; it is inefficient to run a data mining algorithm on the raw data. This paper discusses an algorithm to accurately classify the entire stream in to a given number of mutually exclusive collectively exhaustive streams upon each of which the data mining algorithm can be run separately yielding more relevant results with a high efficiency. |
| Tasks | |
| Published | 2017-05-28 |
| URL | http://arxiv.org/abs/1705.09995v1 |
| http://arxiv.org/pdf/1705.09995v1.pdf | |
| PWC | https://paperswithcode.com/paper/subject-specific-stream-classification |
| Repo | |
| Framework | |
S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
| Title | S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension |
| Authors | Chuanqi Tan, Furu Wei, Nan Yang, Bowen Du, Weifeng Lv, Ming Zhou |
| Abstract | In this paper, we present a novel approach to machine reading comprehension for the MS-MARCO dataset. Unlike the SQuAD dataset that aims to answer a question with exact text spans in a passage, the MS-MARCO dataset defines the task as answering a question from multiple passages and the words in the answer are not necessary in the passages. We therefore develop an extraction-then-synthesis framework to synthesize answers from extraction results. Specifically, the answer extraction model is first employed to predict the most important sub-spans from the passage as evidence, and the answer synthesis model takes the evidence as additional features along with the question and passage to further elaborate the final answers. We build the answer extraction model with state-of-the-art neural networks for single passage reading comprehension, and propose an additional task of passage ranking to help answer extraction in multiple passages. The answer synthesis model is based on the sequence-to-sequence neural networks with extracted evidences as features. Experiments show that our extraction-then-synthesis method outperforms state-of-the-art methods. |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.04815v6 |
| http://arxiv.org/pdf/1706.04815v6.pdf | |
| PWC | https://paperswithcode.com/paper/s-net-from-answer-extraction-to-answer |
| Repo | |
| Framework | |
3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
| Title | 3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks |
| Authors | Mengwei Ren, Liang Niu, Yi Fang |
| Abstract | Recently researchers have been shifting their focus towards learned 3D shape descriptors from hand-craft ones to better address challenging issues of the deformation and structural variation inherently present in 3D objects. 3D geometric data are often transformed to 3D Voxel grids with regular format in order to be better fed to a deep neural net architecture. However, the computational intractability of direct application of 3D convolutional nets to 3D volumetric data severely limits the efficiency (i.e. slow processing) and effectiveness (i.e. unsatisfied accuracy) in processing 3D geometric data. In this paper, powered with a novel design of adversarial networks (3D-A-Nets), we have developed a novel 3D deep dense shape descriptor (3D-DDSD) to address the challenging issues of efficient and effective 3D volumetric data processing. We developed new definition of 2D multilayer dense representation (MDR) of 3D volumetric data to extract concise but geometrically informative shape description and a novel design of adversarial networks that jointly train a set of convolution neural network (CNN), recurrent neural network (RNN) and an adversarial discriminator. More specifically, the generator network produces 3D shape features that encourages the clustering of samples from the same category with correct class label, whereas the discriminator network discourages the clustering by assigning them misleading adversarial class labels. By addressing the challenges posed by the computational inefficiency of direct application of CNN to 3D volumetric data, 3D-A-Nets can learn high-quality 3D-DSDD which demonstrates superior performance on 3D shape classification and retrieval over other state-of-the-art techniques by a great margin. |
| Tasks | |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10108v1 |
| http://arxiv.org/pdf/1711.10108v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-a-nets-3d-deep-dense-descriptor-for |
| Repo | |
| Framework | |
Generalised Reichenbachian Common Cause Systems
| Title | Generalised Reichenbachian Common Cause Systems |
| Authors | Claudio Mazzola |
| Abstract | The principle of the common cause claims that if an improbable coincidence has occurred, there must exist a common cause. This is generally taken to mean that positive correlations between non-causally related events should disappear when conditioning on the action of some underlying common cause. The extended interpretation of the principle, by contrast, urges that common causes should be called for in order to explain positive deviations between the estimated correlation of two events and the expected value of their correlation. The aim of this paper is to provide the extended reading of the principle with a general probabilistic model, capturing the simultaneous action of a system of multiple common causes. To this end, two distinct models are elaborated, and the necessary and sufficient conditions for their existence are determined. |
| Tasks | |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.06109v1 |
| http://arxiv.org/pdf/1703.06109v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalised-reichenbachian-common-cause |
| Repo | |
| Framework | |
Gazing into the Abyss: Real-time Gaze Estimation
| Title | Gazing into the Abyss: Real-time Gaze Estimation |
| Authors | George He, Sami Oueida, Tucker Ward |
| Abstract | Gaze and face tracking algorithms have traditionally battled a compromise between computational complexity and accuracy; the most accurate neural net algorithms cannot be implemented in real time, but less complex real-time algorithms suffer from higher error. This project seeks to better bridge that gap by improving on real-time eye and facial recognition algorithms in order to develop accurate, real-time gaze estimation with an emphasis on minimizing training data and computational complexity. Our goal is to use eye and facial recognition techniques to enable users to perform limited tasks based on gaze and facial input using only a standard, low-quality web cam found in most modern laptops and smart phones and the limited computational power and training data typical of those scenarios. We therefore identified seven promising, fundamentally different algorithms based on different user features and developed one outstanding, one workable, and one honorable mention gaze tracking pipelines that match the performance of modern gaze trackers while using no training data. |
| Tasks | Gaze Estimation |
| Published | 2017-11-18 |
| URL | http://arxiv.org/abs/1711.06918v1 |
| http://arxiv.org/pdf/1711.06918v1.pdf | |
| PWC | https://paperswithcode.com/paper/gazing-into-the-abyss-real-time-gaze |
| Repo | |
| Framework | |
Video Frame Interpolation via Adaptive Convolution
| Title | Video Frame Interpolation via Adaptive Convolution |
| Authors | Simon Niklaus, Long Mai, Feng Liu |
| Abstract | Video frame interpolation typically involves two steps: motion estimation and pixel synthesis. Such a two-step approach heavily depends on the quality of motion estimation. This paper presents a robust video frame interpolation method that combines these two steps into a single process. Specifically, our method considers pixel synthesis for the interpolated frame as local convolution over two input frames. The convolution kernel captures both the local motion between the input frames and the coefficients for pixel synthesis. Our method employs a deep fully convolutional neural network to estimate a spatially-adaptive convolution kernel for each pixel. This deep neural network can be directly trained end to end using widely available video data without any difficult-to-obtain ground-truth data like optical flow. Our experiments show that the formulation of video interpolation as a single convolution process allows our method to gracefully handle challenges like occlusion, blur, and abrupt brightness change and enables high-quality video frame interpolation. |
| Tasks | Motion Estimation, Optical Flow Estimation, Video Frame Interpolation |
| Published | 2017-03-22 |
| URL | http://arxiv.org/abs/1703.07514v1 |
| http://arxiv.org/pdf/1703.07514v1.pdf | |
| PWC | https://paperswithcode.com/paper/video-frame-interpolation-via-adaptive-1 |
| Repo | |
| Framework | |
