Paper Group ANR 602
Stress Test Evaluation for Natural Language Inference. Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method. Foundations of Comparison-Based Hierarchical Clustering. Guided Graph Spectral Embedding: Application to the C. elegans Connectome. Learning Representations of Social Media Users. Mapping Un …
Stress Test Evaluation for Natural Language Inference
Title | Stress Test Evaluation for Natural Language Inference |
Authors | Aakanksha Naik, Abhilasha Ravichander, Norman Sadeh, Carolyn Rose, Graham Neubig |
Abstract | Natural language inference (NLI) is the task of determining if a natural language hypothesis can be inferred from a given premise in a justifiable manner. NLI was proposed as a benchmark task for natural language understanding. Existing models perform well at standard datasets for NLI, achieving impressive results across different genres of text. However, the extent to which these models understand the semantic content of sentences is unclear. In this work, we propose an evaluation methodology consisting of automatically constructed “stress tests” that allow us to examine whether systems have the ability to make real inferential decisions. Our evaluation of six sentence-encoder models on these stress tests reveals strengths and weaknesses of these models with respect to challenging linguistic phenomena, and suggests important directions for future work in this area. |
Tasks | Natural Language Inference |
Published | 2018-06-02 |
URL | http://arxiv.org/abs/1806.00692v3 |
http://arxiv.org/pdf/1806.00692v3.pdf | |
PWC | https://paperswithcode.com/paper/stress-test-evaluation-for-natural-language |
Repo | |
Framework | |
Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method
Title | Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method |
Authors | Xin Zhang, Bingfang Wu, Liang Zhu, Fuyou Tian, Miao Zhang, Yuanzeng |
Abstract | The Three Gorges Dam, a massive cross-century project spans the Yangtze River by the town of Sandouping, located in Yichang, Hubei province, China, was built to provide great power, improve the River shipping, control floods in the upper reaches of the Yangtze River, and increase the dry season flow in the middle and lower reaches of the Yangtze River. Benefits are enormous and comprehensive. However, the social and environmental impacts are also immense and far-reaching to its surrounding areas. Mapping land use /land cover changed (LUCC) is critical for tracking the impacts. Remote sensing has been proved to be an effective way to map and monitor land use change in real time and in large areas such as the Three Gorges Reservoir Area(TGRA) by using pixel based or oriented based classifier in different resolution. In this paper, we first test the state of the art semantic segmentation deep learning classifiers for LUCC mapping with 7 categories in the TGRA area with rapideye 5m resolution data. The topographic information was also added for better accuracy in mountain area. By compared with the pixel-based classifier, the semantic segmentation deep learning method has better accuracy and robustness at 5m resolution level. |
Tasks | Semantic Segmentation |
Published | 2018-03-18 |
URL | http://arxiv.org/abs/1804.00498v1 |
http://arxiv.org/pdf/1804.00498v1.pdf | |
PWC | https://paperswithcode.com/paper/land-use-mapping-in-the-three-gorges |
Repo | |
Framework | |
Foundations of Comparison-Based Hierarchical Clustering
Title | Foundations of Comparison-Based Hierarchical Clustering |
Authors | Debarghya Ghoshdastidar, Michaël Perrot, Ulrike von Luxburg |
Abstract | We address the classical problem of hierarchical clustering, but in a framework where one does not have access to a representation of the objects or their pairwise similarities. Instead, we assume that only a set of comparisons between objects is available, that is, statements of the form “objects $i$ and $j$ are more similar than objects $k$ and $l$.” Such a scenario is commonly encountered in crowdsourcing applications. The focus of this work is to develop comparison-based hierarchical clustering algorithms that do not rely on the principles of ordinal embedding. We show that single and complete linkage are inherently comparison-based and we develop variants of average linkage. We provide statistical guarantees for the different methods under a planted hierarchical partition model. We also empirically demonstrate the performance of the proposed approaches on several datasets. |
Tasks | |
Published | 2018-11-02 |
URL | https://arxiv.org/abs/1811.00928v2 |
https://arxiv.org/pdf/1811.00928v2.pdf | |
PWC | https://paperswithcode.com/paper/foundations-of-comparison-based-hierarchical |
Repo | |
Framework | |
Guided Graph Spectral Embedding: Application to the C. elegans Connectome
Title | Guided Graph Spectral Embedding: Application to the C. elegans Connectome |
Authors | Miljan Petrović, Thomas A. W. Bolton, Maria Giulia Preti, Raphaël Liégeois, Dimitri Van De Ville |
Abstract | Graph spectral analysis can yield meaningful embeddings of graphs by providing insight into distributed features not directly accessible in nodal domain. Recent efforts in graph signal processing have proposed new decompositions-e.g., based on wavelets and Slepians-that can be applied to filter signals defined on the graph. In this work, we take inspiration from these constructions to define a new guided spectral embedding that combines maximizing energy concentration with minimizing modified embedded distance for a given importance weighting of the nodes. We show these optimization goals are intrinsically opposite, leading to a well-defined and stable spectral decomposition. The importance weighting allows to put the focus on particular nodes and tune the trade-off between global and local effects. Following the derivation of our new optimization criterion and its linear approximation, we exemplify the methodology on the C. elegans structural connectome. The results of our analyses confirm known observations on the nematode’s neural network in terms of functionality and importance of cells. Compared to Laplacian embedding, the guided approach, focused on a certain class of cells (sensory, inter- and motoneurons), provides more biological insights, such as the distinction between somatic positions of cells, and their involvement in low or high order processing functions. |
Tasks | |
Published | 2018-12-10 |
URL | http://arxiv.org/abs/1812.03684v3 |
http://arxiv.org/pdf/1812.03684v3.pdf | |
PWC | https://paperswithcode.com/paper/guided-graph-spectral-embedding-application |
Repo | |
Framework | |
Learning Representations of Social Media Users
Title | Learning Representations of Social Media Users |
Authors | Adrian Benton |
Abstract | User representations are routinely used in recommendation systems by platform developers, targeted advertisements by marketers, and by public policy researchers to gauge public opinion across demographic groups. Computer scientists consider the problem of inferring user representations more abstractly; how does one extract a stable user representation - effective for many downstream tasks - from a medium as noisy and complicated as social media? The quality of a user representation is ultimately task-dependent (e.g. does it improve classifier performance, make more accurate recommendations in a recommendation system) but there are proxies that are less sensitive to the specific task. Is the representation predictive of latent properties such as a person’s demographic features, socioeconomic class, or mental health state? Is it predictive of the user’s future behavior? In this thesis, we begin by showing how user representations can be learned from multiple types of user behavior on social media. We apply several extensions of generalized canonical correlation analysis to learn these representations and evaluate them at three tasks: predicting future hashtag mentions, friending behavior, and demographic features. We then show how user features can be employed as distant supervision to improve topic model fit. Finally, we show how user features can be integrated into and improve existing classifiers in the multitask learning framework. We treat user representations - ground truth gender and mental health features - as auxiliary tasks to improve mental health state prediction. We also use distributed user representations learned in the first chapter to improve tweet-level stance classifiers, showing that distant user information can inform classification tasks at the granularity of a single message. |
Tasks | Recommendation Systems |
Published | 2018-12-02 |
URL | http://arxiv.org/abs/1812.00436v1 |
http://arxiv.org/pdf/1812.00436v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-representations-of-social-media |
Repo | |
Framework | |
Mapping Unparalleled Clinical Professional and Consumer Languages with Embedding Alignment
Title | Mapping Unparalleled Clinical Professional and Consumer Languages with Embedding Alignment |
Authors | Wei-Hung Weng, Peter Szolovits |
Abstract | Mapping and translating professional but arcane clinical jargons to consumer language is essential to improve the patient-clinician communication. Researchers have used the existing biomedical ontologies and consumer health vocabulary dictionary to translate between the languages. However, such approaches are limited by expert efforts to manually build the dictionary, which is hard to be generalized and scalable. In this work, we utilized the embeddings alignment method for the word mapping between unparalleled clinical professional and consumer language embeddings. To map semantically similar words in two different word embeddings, we first independently trained word embeddings on both the corpus with abundant clinical professional terms and the other with mainly healthcare consumer terms. Then, we aligned the embeddings by the Procrustes algorithm. We also investigated the approach with the adversarial training with refinement. We evaluated the quality of the alignment through the similar words retrieval both by computing the model precision and as well as judging qualitatively by human. We show that the Procrustes algorithm can be performant for the professional consumer language embeddings alignment, whereas adversarial training with refinement may find some relations between two languages. |
Tasks | Word Embeddings |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09542v1 |
http://arxiv.org/pdf/1806.09542v1.pdf | |
PWC | https://paperswithcode.com/paper/mapping-unparalleled-clinical-professional |
Repo | |
Framework | |
A Deep One-Shot Network for Query-based Logo Retrieval
Title | A Deep One-Shot Network for Query-based Logo Retrieval |
Authors | Ayan Kumar Bhunia, Ankan Kumar Bhunia, Shuvozit Ghose, Abhirup Das, Partha Pratim Roy, Umapada Pal |
Abstract | Logo detection in real-world scene images is an important problem with applications in advertisement and marketing. Existing general-purpose object detection methods require large training data with annotations for every logo class. These methods do not satisfy the incremental demand of logo classes necessary for practical deployment since it is practically impossible to have such annotated data for new unseen logo. In this work, we develop an easy-to-implement query-based logo detection and localization system by employing a one-shot learning technique. Given an image of a query logo, our model searches for it within a given target image and predicts the possible location of the logo by estimating a binary segmentation mask. The proposed model consists of a conditional branch and a segmentation branch. The former gives a conditional latent representation of the given query logo which is combined with feature maps of the segmentation branch at multiple scales in order to find the matching position of the query logo in a target image, should it be present. Feature matching between the latent query representation and multi-scale feature maps of segmentation branch using simple concatenation operation followed by 1x1 convolution layer makes our model scale-invariant. Despite its simplicity, our query-based logo retrieval framework achieved superior performance in FlickrLogos-32 and TopLogos-10 dataset over different existing baselines. |
Tasks | Object Detection, One-Shot Learning |
Published | 2018-11-04 |
URL | https://arxiv.org/abs/1811.01395v5 |
https://arxiv.org/pdf/1811.01395v5.pdf | |
PWC | https://paperswithcode.com/paper/query-based-logo-segmentation |
Repo | |
Framework | |
Dream Formulations and Deep Neural Networks: Humanistic Themes in the Iconology of the Machine-Learned Image
Title | Dream Formulations and Deep Neural Networks: Humanistic Themes in the Iconology of the Machine-Learned Image |
Authors | Emily L. Spratt |
Abstract | This paper addresses the interpretability of deep learning-enabled image recognition processes in computer vision science in relation to theories in art history and cognitive psychology on the vision-related perceptual capabilities of humans. Examination of what is determinable about the machine-learned image in comparison to humanistic theories of visual perception, particularly in regard to art historian Erwin Panofsky’s methodology for image analysis and psychologist Eleanor Rosch’s theory of graded categorization according to prototypes, finds that there are surprising similarities between the two that suggest that researchers in the arts and the sciences would have much to benefit from closer collaborations. Utilizing the examples of Google’s DeepDream and the Machine Learning and Perception Lab at Georgia Tech’s Grad-CAM: Gradient-weighted Class Activation Mapping programs, this study suggests that a revival of art historical research in iconography and formalism in the age of AI is essential for shaping the future navigation and interpretation of all machine-learned images, given the rapid developments in image recognition technologies. |
Tasks | |
Published | 2018-02-05 |
URL | http://arxiv.org/abs/1802.01274v1 |
http://arxiv.org/pdf/1802.01274v1.pdf | |
PWC | https://paperswithcode.com/paper/dream-formulations-and-deep-neural-networks |
Repo | |
Framework | |
Cluster analysis of homicide rates in the Brazilian state of Goias from 2002 to 2014
Title | Cluster analysis of homicide rates in the Brazilian state of Goias from 2002 to 2014 |
Authors | Samuel Bruno da Silva Sousa, Ronaldo de Castro Del-Fiaco, Lilian Berton |
Abstract | Homicide mortality is a worldwide concern and has occupied the agenda of researchers and public managers. In Brazil, homicide is the third leading cause of death in the general population and the first in the 15-39 age group. In South America, Brazil has the third highest homicide mortality, behind Venezuela and Colombia. To measure the impacts of violence it is important to assess health systems and criminal justice, as well as other areas. In this paper, we analyze the spatial distribution of homicide mortality in the state of Goias, Center-West of Brazil, since the homicide rate increased from 24.5 per 100,000 in 2002 to 42.6 per 100,000 in 2014 in this location. Moreover, this state had the fifth position of homicides in Brazil in 2014. We considered socio-demographic variables for the state, performed analysis about correlation and employed three clustering algorithms: K-means, Density-based and Hierarchical. The results indicate the homicide rates are higher in cities neighbors of large urban centers, although these cities have the best socioeconomic indicators. |
Tasks | |
Published | 2018-11-11 |
URL | http://arxiv.org/abs/1811.06366v2 |
http://arxiv.org/pdf/1811.06366v2.pdf | |
PWC | https://paperswithcode.com/paper/cluster-analysis-of-homicide-rates-in-the |
Repo | |
Framework | |
From Shannon’s Channel to Semantic Channel via New Bayes’ Formulas for Machine Learning
Title | From Shannon’s Channel to Semantic Channel via New Bayes’ Formulas for Machine Learning |
Authors | Chenguang Lu |
Abstract | A group of transition probability functions form a Shannon’s channel whereas a group of truth functions form a semantic channel. By the third kind of Bayes’ theorem, we can directly convert a Shannon’s channel into an optimized semantic channel. When a sample is not big enough, we can use a truth function with parameters to produce the likelihood function, then train the truth function by the conditional sampling distribution. The third kind of Bayes’ theorem is proved. A semantic information theory is simply introduced. The semantic information measure reflects Popper’s hypothesis-testing thought. The Semantic Information Method (SIM) adheres to maximum semantic information criterion which is compatible with maximum likelihood criterion and Regularized Least Squares criterion. It supports Wittgenstein’s view: the meaning of a word lies in its use. Letting the two channels mutually match, we obtain the Channels’ Matching (CM) algorithm for machine learning. The CM algorithm is used to explain the evolution of the semantic meaning of natural language, such as “Old age”. The semantic channel for medical tests and the confirmation measures of test-positive and test-negative are discussed. The applications of the CM algorithm to semi-supervised learning and non-supervised learning are simply introduced. As a predictive model, the semantic channel fits variable sources and hence can overcome class-imbalance problem. The SIM strictly distinguishes statistical probability and logical probability and uses both at the same time. This method is compatible with the thoughts of Bayes, Fisher, Shannon, Zadeh, Tarski, Davidson, Wittgenstein, and Popper.It is a competitive alternative to Bayesian inference. |
Tasks | Bayesian Inference |
Published | 2018-03-22 |
URL | http://arxiv.org/abs/1803.08979v1 |
http://arxiv.org/pdf/1803.08979v1.pdf | |
PWC | https://paperswithcode.com/paper/from-shannons-channel-to-semantic-channel-via |
Repo | |
Framework | |
Ecological Data Analysis Based on Machine Learning Algorithms
Title | Ecological Data Analysis Based on Machine Learning Algorithms |
Authors | Md. Siraj-Ud-Doula, Md. Ashad Alam |
Abstract | Classification is an important supervised machine learning method, which is necessary and challenging issue for ecological research. It offers a way to classify a dataset into subsets that share common patterns. Notably, there are many classification algorithms to choose from, each making certain assumptions about the data and about how classification should be formed. In this paper, we applied eight machine learning classification algorithms such as Decision Trees, Random Forest, Artificial Neural Network, Support Vector Machine, Linear Discriminant Analysis, k-nearest neighbors, Logistic Regression and Naive Bayes on ecological data. The goal of this study is to compare different machine learning classification algorithms in ecological dataset. In this analysis we have checked the accuracy test among the algorithms. In our study we conclude that Linear Discriminant Analysis and k-nearest neighbors are the best methods among all other methods |
Tasks | |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.09138v1 |
http://arxiv.org/pdf/1812.09138v1.pdf | |
PWC | https://paperswithcode.com/paper/ecological-data-analysis-based-on-machine |
Repo | |
Framework | |
Emotion Recognition from Speech based on Relevant Feature and Majority Voting
Title | Emotion Recognition from Speech based on Relevant Feature and Majority Voting |
Authors | Md. Kamruzzaman Sarker, Kazi Md. Rokibul Alam, Md. Arifuzzaman |
Abstract | This paper proposes an approach to detect emotion from human speech employing majority voting technique over several machine learning techniques. The contribution of this work is in two folds: firstly it selects those features of speech which is most promising for classification and secondly it uses the majority voting technique that selects the exact class of emotion. Here, majority voting technique has been applied over Neural Network (NN), Decision Tree (DT), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Input vector of NN, DT, SVM and KNN consists of various acoustic and prosodic features like Pitch, Mel-Frequency Cepstral coefficients etc. From speech signal many feature have been extracted and only promising features have been selected. To consider a feature as promising, Fast Correlation based feature selection (FCBF) and Fisher score algorithms have been used and only those features are selected which are highly ranked by both of them. The proposed approach has been tested on Berlin dataset of emotional speech [3] and Electromagnetic Articulography (EMA) dataset [4]. The experimental result shows that majority voting technique attains better accuracy over individual machine learning techniques. The employment of the proposed approach can effectively recognize the emotion of human beings in case of social robot, intelligent chat client, call-center of a company etc. |
Tasks | Emotion Recognition, Feature Selection |
Published | 2018-07-11 |
URL | http://arxiv.org/abs/1807.03909v1 |
http://arxiv.org/pdf/1807.03909v1.pdf | |
PWC | https://paperswithcode.com/paper/emotion-recognition-from-speech-based-on |
Repo | |
Framework | |
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
Title | Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss |
Authors | Yong Guo, Qi Chen, Jian Chen, Junzhou Huang, Yanwu Xu, Jiezhang Cao, Peilin Zhao, Mingkui Tan |
Abstract | Deep neural networks have exhibited promising performance in image super-resolution (SR) due to the power in learning the non-linear mapping from low-resolution (LR) images to high-resolution (HR) images. However, most deep learning methods employ feed-forward architectures, and thus the dependencies between LR and HR images are not fully exploited, leading to limited learning performance. Moreover, most deep learning based SR methods apply the pixel-wise reconstruction error as the loss, which, however, may fail to capture high-frequency information and produce perceptually unsatisfying results, whilst the recent perceptual loss relies on some pre-trained deep model and they may not generalize well. In this paper, we introduce a mask to separate the image into low- and high-frequency parts based on image gradient magnitude, and then devise a gradient sensitive loss to well capture the structures in the image without sacrificing the recovery of low-frequency content. Moreover, by investigating the duality in SR, we develop a dual reconstruction network (DRN) to improve the SR performance. We provide theoretical analysis on the generalization performance of our method and demonstrate its effectiveness and superiority with thorough experiments. |
Tasks | Image Super-Resolution, Super-Resolution |
Published | 2018-09-19 |
URL | http://arxiv.org/abs/1809.07099v1 |
http://arxiv.org/pdf/1809.07099v1.pdf | |
PWC | https://paperswithcode.com/paper/dual-reconstruction-nets-for-image-super |
Repo | |
Framework | |
Convolutional capsule network for classification of breast cancer histology images
Title | Convolutional capsule network for classification of breast cancer histology images |
Authors | Tomas Iesmantas, Robertas Alzbutas |
Abstract | Automatization of the diagnosis of any kind of disease is of great importance and it’s gaining speed as more and more deep learning solutions are applied to different problems. One of such computer aided systems could be a decision support too able to accurately differentiate between different types of breast cancer histological images - normal tissue or carcinoma. In this paper authors present a deep learning solution, based on convolutional capsule network for classification of four types of images of breast tissue biopsy when hematoxylin and eusin staining is applied. The cross-validation accuracy was achieved to be 0.87 with equaly high sensitivity. |
Tasks | Classification Of Breast Cancer Histology Images |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08376v1 |
http://arxiv.org/pdf/1804.08376v1.pdf | |
PWC | https://paperswithcode.com/paper/convolutional-capsule-network-for |
Repo | |
Framework | |
Adapting Auxiliary Losses Using Gradient Similarity
Title | Adapting Auxiliary Losses Using Gradient Similarity |
Authors | Yunshu Du, Wojciech M. Czarnecki, Siddhant M. Jayakumar, Razvan Pascanu, Balaji Lakshminarayanan |
Abstract | One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations. However, it is not always trivial to know if an auxiliary task will be helpful for the main task and when it could start hurting. We propose to use the cosine similarity between gradients of tasks as an adaptive weight to detect when an auxiliary loss is helpful to the main loss. We show that our approach is guaranteed to converge to critical points of the main task and demonstrate the practical usefulness of the proposed algorithm in a few domains: multi-task supervised learning on subsets of ImageNet, reinforcement learning on gridworld, and reinforcement learning on Atari games. |
Tasks | Atari Games |
Published | 2018-12-05 |
URL | http://arxiv.org/abs/1812.02224v1 |
http://arxiv.org/pdf/1812.02224v1.pdf | |
PWC | https://paperswithcode.com/paper/adapting-auxiliary-losses-using-gradient |
Repo | |
Framework | |