Paper Group ANR 479
iParaphrasing: Extracting Visually Grounded Paraphrases via an Image. Paraphrases as Foreign Languages in Multilingual Neural Machine Translation. Project Rosetta: A Childhood Social, Emotional, and Behavioral Developmental Ontology. SPASS: Scientific Prominence Active Search System with Deep Image Captioning Network. The Error is the Feature: how …
iParaphrasing: Extracting Visually Grounded Paraphrases via an Image
Title | iParaphrasing: Extracting Visually Grounded Paraphrases via an Image |
Authors | Chenhui Chu, Mayu Otani, Yuta Nakashima |
Abstract | A paraphrase is a restatement of the meaning of a text in other words. Paraphrases have been studied to enhance the performance of many natural language processing tasks. In this paper, we propose a novel task iParaphrasing to extract visually grounded paraphrases (VGPs), which are different phrasal expressions describing the same visual concept in an image. These extracted VGPs have the potential to improve language and image multimodal tasks such as visual question answering and image captioning. How to model the similarity between VGPs is the key of iParaphrasing. We apply various existing methods as well as propose a novel neural network-based method with image attention, and report the results of the first attempt toward iParaphrasing. |
Tasks | Image Captioning, Question Answering, Visual Question Answering |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.04284v1 |
http://arxiv.org/pdf/1806.04284v1.pdf | |
PWC | https://paperswithcode.com/paper/iparaphrasing-extracting-visually-grounded |
Repo | |
Framework | |
Paraphrases as Foreign Languages in Multilingual Neural Machine Translation
Title | Paraphrases as Foreign Languages in Multilingual Neural Machine Translation |
Authors | Zhong Zhou, Matthias Sperber, Alex Waibel |
Abstract | Paraphrases, the rewordings of the same semantic meaning, are useful for improving generalization and translation. However, prior works only explore paraphrases at the word or phrase level, not at the sentence or corpus level. Unlike previous works that only explore paraphrases at the word or phrase level, we use different translations of the whole training data that are consistent in structure as paraphrases at the corpus level. We train on parallel paraphrases in multiple languages from various sources. We treat paraphrases as foreign languages, tag source sentences with paraphrase labels, and train on parallel paraphrases in the style of multilingual Neural Machine Translation (NMT). Our multi-paraphrase NMT that trains only on two languages outperforms the multilingual baselines. Adding paraphrases improves the rare word translation and increases entropy and diversity in lexical choice. Adding the source paraphrases boosts performance better than adding the target ones. Combining both the source and the target paraphrases lifts performance further; combining paraphrases with multilingual data helps but has mixed performance. We achieve a BLEU score of 57.2 for French-to-English translation using 24 corpus-level paraphrases of the Bible, which outperforms the multilingual baselines and is +34.7 above the single-source single-target NMT baseline. |
Tasks | Machine Translation |
Published | 2018-08-25 |
URL | https://arxiv.org/abs/1808.08438v2 |
https://arxiv.org/pdf/1808.08438v2.pdf | |
PWC | https://paperswithcode.com/paper/paraphrases-as-foreign-languages-in |
Repo | |
Framework | |
Project Rosetta: A Childhood Social, Emotional, and Behavioral Developmental Ontology
Title | Project Rosetta: A Childhood Social, Emotional, and Behavioral Developmental Ontology |
Authors | Alyson Maslowski, Halim Abbas, Kelley Abrams, Sharief Taraman, Ford Garberson, Susan Segar |
Abstract | There is a wide array of existing instruments used to assess childhood behavior and development for the evaluation of social, emotional and behavioral disorders. Many of these instruments either focus on one diagnostic category or encompass a broad set of childhood behaviors. We built an extensive ontology of the questions associated with key features that have diagnostic relevance for child behavioral conditions, such as Autism Spectrum Disorder (ASD), attention-deficit/hyperactivity disorder (ADHD), and anxiety, by incorporating a subset of existing child behavioral instruments and categorizing each question into clinical domains. Each existing question and set of question responses were then mapped to a new unique Rosetta question and set of answer codes encompassing the semantic meaning and identified concept(s) of as many existing questions as possible. This resulted in 1274 existing instrument questions mapping to 209 Rosetta questions creating a minimal set of questions that are comprehensive of each topic and subtopic. This resulting ontology can be used to create more concise instruments across various ages and conditions, as well as create more robust overlapping datasets for both clinical and research use. |
Tasks | |
Published | 2018-12-06 |
URL | http://arxiv.org/abs/1812.02722v1 |
http://arxiv.org/pdf/1812.02722v1.pdf | |
PWC | https://paperswithcode.com/paper/project-rosetta-a-childhood-social-emotional |
Repo | |
Framework | |
SPASS: Scientific Prominence Active Search System with Deep Image Captioning Network
Title | SPASS: Scientific Prominence Active Search System with Deep Image Captioning Network |
Authors | Dicong Qiu |
Abstract | Planetary exploration missions with Mars rovers are complicated, which generally require elaborated task planning by human experts, from the path to take to the images to capture. NASA has been using this process to acquire over 22 million images from the planet Mars. In order to improve the degree of automation and thus efficiency in this process, we propose a system for planetary rovers to actively search for prominence of prespecified scientific features in captured images. Scientists can prespecify such search tasks in natural language and upload them to a rover, on which the deployed system constantly captions captured images with a deep image captioning network and compare the auto-generated captions to the prespecified search tasks by certain metrics so as to prioritize those images for transmission. As a beneficial side effect, the proposed system can also be deployed to ground-based planetary data systems as a content-based search engine. |
Tasks | Image Captioning |
Published | 2018-09-10 |
URL | http://arxiv.org/abs/1809.03385v1 |
http://arxiv.org/pdf/1809.03385v1.pdf | |
PWC | https://paperswithcode.com/paper/spass-scientific-prominence-active-search |
Repo | |
Framework | |
The Error is the Feature: how to Forecast Lightning using a Model Prediction Error
Title | The Error is the Feature: how to Forecast Lightning using a Model Prediction Error |
Authors | Christian Schön, Jens Dittrich, Richard Müller |
Abstract | Despite the progress within the last decades, weather forecasting is still a challenging and computationally expensive task. Current satellite-based approaches to predict thunderstorms are usually based on the analysis of the observed brightness temperatures in different spectral channels and emit a warning if a critical threshold is reached. Recent progress in data science however demonstrates that machine learning can be successfully applied to many research fields in science, especially in areas dealing with large datasets. We therefore present a new approach to the problem of predicting thunderstorms based on machine learning. The core idea of our work is to use the error of two-dimensional optical flow algorithms applied to images of meteorological satellites as a feature for machine learning models. We interpret that optical flow error as an indication of convection potentially leading to thunderstorms and lightning. To factor in spatial proximity we use various manual convolution steps. We also consider effects such as the time of day or the geographic location. We train different tree classifier models as well as a neural network to predict lightning within the next few hours (called nowcasting in meteorology) based on these features. In our evaluation section we compare the predictive power of the different models and the impact of different features on the classification result. Our results show a high accuracy of 96% for predictions over the next 15 minutes which slightly decreases with increasing forecast period but still remains above 83% for forecasts of up to five hours. The high false positive rate of nearly 6% however needs further investigation to allow for an operational use of our approach. |
Tasks | Optical Flow Estimation, Weather Forecasting |
Published | 2018-11-23 |
URL | http://arxiv.org/abs/1811.09496v2 |
http://arxiv.org/pdf/1811.09496v2.pdf | |
PWC | https://paperswithcode.com/paper/the-error-is-the-feature-how-to-forecast |
Repo | |
Framework | |
Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks
Title | Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks |
Authors | Georgios Papoudakis, Kyriakos C. Chatzidimitriou, Pericles A. Mitkas |
Abstract | Recent developments in deep reinforcement learning have enabled the creation of agents for solving a large variety of games given a visual input. These methods have been proven successful for 2D games, like the Atari games, or for simple tasks, like navigating in mazes. It is still an open question, how to address more complex environments, in which the reward is sparse and the state space is huge. In this paper we propose a divide and conquer deep reinforcement learning solution and we test our agent in the first person shooter (FPS) game of Doom. Our work is based on previous works in deep reinforcement learning and in Doom agents. We also present how our agent is able to perform better in unknown environments compared to a state of the art reinforcement learning algorithm. |
Tasks | Atari Games, Game of Doom |
Published | 2018-07-05 |
URL | http://arxiv.org/abs/1807.01960v1 |
http://arxiv.org/pdf/1807.01960v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-doom-using |
Repo | |
Framework | |
Enhanced version of AdaBoostM1 with J48 Tree learning method
Title | Enhanced version of AdaBoostM1 with J48 Tree learning method |
Authors | Kyongche Kang, Jack Michalak |
Abstract | Machine Learning focuses on the construction and study of systems that can learn from data. This is connected with the classification problem, which usually is what Machine Learning algorithms are designed to solve. When a machine learning method is used by people with no special expertise in machine learning, it is important that the method be robust in classification, in the sense that reasonable performance is obtained with minimal tuning of the problem at hand. Algorithms are evaluated based on how robust they can classify the given data. In this paper, we propose a quantifiable measure of robustness, and describe a particular learning method that is robust according to this measure in the context of classification problem. We proposed Adaptive Boosting (AdaBoostM1) with J48(C4.5 tree) as a base learner with tuning weight threshold (P) and number of iterations (I) for boosting algorithm. To benchmark the performance, we used the baseline classifier, AdaBoostM1 with Decision Stump as base learner without tuning parameters. By tuning parameters and using J48 as base learner, we are able to reduce the overall average error rate ratio (errorC/errorNB) from 2.4 to 0.9 for development sets of data and 2.1 to 1.2 for evaluation sets of data. |
Tasks | |
Published | 2018-02-10 |
URL | http://arxiv.org/abs/1802.03522v1 |
http://arxiv.org/pdf/1802.03522v1.pdf | |
PWC | https://paperswithcode.com/paper/enhanced-version-of-adaboostm1-with-j48-tree |
Repo | |
Framework | |
Not all Embeddings are created Equal: Extracting Entity-specific Substructures for RDF Graph Embedding
Title | Not all Embeddings are created Equal: Extracting Entity-specific Substructures for RDF Graph Embedding |
Authors | Muhammad Rizwan Saeed, Charalampos Chelmis, Viktor K. Prasanna |
Abstract | Knowledge Graphs (KGs) are becoming essential to information systems that require access to structured data. Several approaches have been recently proposed, for obtaining vector representations of KGs suitable for Machine Learning tasks, based on identifying and extracting relevant graph substructures using uniform and biased random walks. However, such approaches lead to representations comprising mostly “popular”, instead of “relevant”, entities in the KG. In KGs, in which different types of entities often exist (such as in Linked Open Data), a given target entity may have its own distinct set of most “relevant” nodes and edges. We propose specificity as an accurate measure of identifying most relevant, entity-specific, nodes and edges. We develop a scalable method based on bidirectional random walks to compute specificity. Our experimental evaluation results show that specificity-based biased random walks extract more “meaningful” (in terms of size and relevance) RDF substructures compared to the state-of-the-art and, the graph embedding learned from the extracted substructures, outperform existing techniques in the task of entity recommendation in DBpedia. |
Tasks | Graph Embedding, Knowledge Graphs |
Published | 2018-04-14 |
URL | http://arxiv.org/abs/1804.05184v1 |
http://arxiv.org/pdf/1804.05184v1.pdf | |
PWC | https://paperswithcode.com/paper/not-all-embeddings-are-created-equal |
Repo | |
Framework | |
Using Machine Learning to reduce the energy wasted in Volunteer Computing Environments
Title | Using Machine Learning to reduce the energy wasted in Volunteer Computing Environments |
Authors | A. Stephen McGough, Matthew Forshaw, John Brennan, Noura Al Moubayed, Stephen Bonner |
Abstract | High Throughput Computing (HTC) provides a convenient mechanism for running thousands of tasks. Many HTC systems exploit computers which are provisioned for other purposes by utilising their idle time - volunteer computing. This has great advantages as it gives access to vast quantities of computational power for little or no cost. The downside is that running tasks are sacrificed if the computer is needed for its primary use. Normally terminating the task which must be restarted on a different computer - leading to wasted energy and an increase in task completion time. We demonstrate, through the use of simulation, how we can reduce this wasted energy by targeting tasks at computers less likely to be needed for primary use, predicting this idle time through machine learning. By combining two machine learning approaches, namely Random Forest and MultiLayer Perceptron, we save 51.4% of the energy without significantly affecting the time to complete tasks. |
Tasks | |
Published | 2018-10-19 |
URL | http://arxiv.org/abs/1810.08675v1 |
http://arxiv.org/pdf/1810.08675v1.pdf | |
PWC | https://paperswithcode.com/paper/using-machine-learning-to-reduce-the-energy |
Repo | |
Framework | |
Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach
Title | Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach |
Authors | He He, Dongrui Wu |
Abstract | Objective: This paper targets a major challenge in developing practical EEG-based brain-computer interfaces (BCIs): how to cope with individual differences so that better learning performance can be obtained for a new subject, with minimum or even no subject-specific data? Methods: We propose a novel approach to align EEG trials from different subjects in the Euclidean space to make them more similar, and hence improve the learning performance for a new subject. Our approach has three desirable properties: 1) it aligns the EEG trials directly in the Euclidean space, and any signal processing, feature extraction and machine learning algorithms can then be applied to the aligned trials; 2) its computational cost is very low; and, 3) it is unsupervised and does not need any label information from the new subject. Results: Both offline and simulated online experiments on motor imagery classification and event-related potential classification verified that our proposed approach outperformed a state-of-the-art Riemannian space data alignment approach, and several approaches without data alignment. Conclusion: The proposed Euclidean space EEG data alignment approach can greatly facilitate transfer learning in BCIs. Significance: Our proposed approach is effective, efficient, and easy to implement. It could be an essential pre-processing step for EEG-based BCIs. |
Tasks | EEG, Transfer Learning |
Published | 2018-08-08 |
URL | http://arxiv.org/abs/1808.05464v2 |
http://arxiv.org/pdf/1808.05464v2.pdf | |
PWC | https://paperswithcode.com/paper/transfer-learning-for-brain-computer |
Repo | |
Framework | |
Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference
Title | Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference |
Authors | An Bian, Joachim M. Buhmann, Andreas Krause |
Abstract | Mean field inference in probabilistic models is generally a highly nonconvex problem. Existing optimization methods, e.g., coordinate ascent algorithms, can only generate local optima. In this work we propose provable mean filed methods for probabilistic log-submodular models and its posterior agreement (PA) with strong approximation guarantees. The main algorithmic technique is a new Double Greedy scheme, termed DR-DoubleGreedy, for continuous DR-submodular maximization with box-constraints. It is a one-pass algorithm with linear time complexity, reaching the optimal 1/2 approximation ratio, which may be of independent interest. We validate the superior performance of our algorithms against baseline algorithms on both synthetic and real-world datasets. |
Tasks | |
Published | 2018-05-19 |
URL | http://arxiv.org/abs/1805.07482v2 |
http://arxiv.org/pdf/1805.07482v2.pdf | |
PWC | https://paperswithcode.com/paper/optimal-dr-submodular-maximization-and |
Repo | |
Framework | |
Automatic Data Registration of Geostationary Payloads for Meteorological Applications at ISRO
Title | Automatic Data Registration of Geostationary Payloads for Meteorological Applications at ISRO |
Authors | Jignesh S. Bhatt, N. Padmanabhan |
Abstract | The launch of KALPANA-1 satellite in the year 2002 heralded the establishment of an indigenous operational payload for meteorological predictions. This was further enhanced in the year 2003 with the launching of INSAT-3A satellite. The software for generating products from the data of these two satellites was taken up subsequently in the year 2004 and the same was installed at the Indian Meteorological Department, New Delhi in January 2006. Registration has been one of the most fundamental operations to generate almost all the data products from the remotely sensed data. Registration is a challenging task due to inevitable radiometric and geometric distortions during the acquisition process. Besides the presence of clouds makes the problem more complicated. In this paper, we present an algorithm for multitemporal and multiband registration. In addition, India facing reference boundaries for the CCD data of INSAT-3A have also been generated. The complete implementation is made up of the following steps: 1) automatic identification of the ground control points (GCPs) in the sensed data, 2) finding the optimal transformation model based on the match-points, and 3) resampling the transformed imagery to the reference coordinates. The proposed algorithm is demonstrated using the real datasets from KALPANA-1 and INSAT-3A. Both KALAPANA-1 and INSAT-3A have recently been decommissioned due to lack of fuel, however, the experience gained from them have given rise to a series of meteorological satellites and associated software; like INSAT-3D series which give continuous weather forecasting for the country. This paper is not so much focused on the theory (widely available in the literature) but concentrates on the implementation of operational software. |
Tasks | Weather Forecasting |
Published | 2018-05-17 |
URL | http://arxiv.org/abs/1805.08706v1 |
http://arxiv.org/pdf/1805.08706v1.pdf | |
PWC | https://paperswithcode.com/paper/automatic-data-registration-of-geostationary |
Repo | |
Framework | |
Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images
Title | Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images |
Authors | Chengsheng Mao, Yiheng Pan, Zexian Zeng, Liang Yao, Yuan Luo |
Abstract | Thoracic diseases are very serious health problems that plague a large number of people. Chest X-ray is currently one of the most popular methods to diagnose thoracic diseases, playing an important role in the healthcare workflow. However, reading the chest X-ray images and giving an accurate diagnosis remain challenging tasks for expert radiologists. With the success of deep learning in computer vision, a growing number of deep neural network architectures were applied to chest X-ray image classification. However, most of the previous deep neural network classifiers were based on deterministic architectures which are usually very noise-sensitive and are likely to aggravate the overfitting issue. In this paper, to make a deep architecture more robust to noise and to reduce overfitting, we propose using deep generative classifiers to automatically diagnose thorax diseases from the chest X-ray images. Unlike the traditional deterministic classifier, a deep generative classifier has a distribution middle layer in the deep neural network. A sampling layer then draws a random sample from the distribution layer and input it to the following layer for classification. The classifier is generative because the class label is generated from samples of a related distribution. Through training the model with a certain amount of randomness, the deep generative classifiers are expected to be robust to noise and can reduce overfitting and then achieve good performances. We implemented our deep generative classifiers based on a number of well-known deterministic neural network architectures, and tested our models on the chest X-ray14 dataset. The results demonstrated the superiority of deep generative classifiers compared with the corresponding deep deterministic classifiers. |
Tasks | Image Classification |
Published | 2018-09-20 |
URL | http://arxiv.org/abs/1809.07436v2 |
http://arxiv.org/pdf/1809.07436v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-generative-classifiers-for-thoracic |
Repo | |
Framework | |
Flash Photography for Data-Driven Hidden Scene Recovery
Title | Flash Photography for Data-Driven Hidden Scene Recovery |
Authors | Matthew Tancik, Guy Satat, Ramesh Raskar |
Abstract | Vehicles, search and rescue personnel, and endoscopes use flash lights to locate, identify, and view objects in their surroundings. Here we show the first steps of how all these tasks can be done around corners with consumer cameras. Recent techniques for NLOS imaging using consumer cameras have not been able to both localize and identify the hidden object. We introduce a method that couples traditional geometric understanding and data-driven techniques. To avoid the limitation of large dataset gathering, we train the data-driven models on rendered samples to computationally recover the hidden scene on real data. The method has three independent operating modes: 1) a regression output to localize a hidden object in 2D, 2) an identification output to identify the object type or pose, and 3) a generative network to reconstruct the hidden scene from a new viewpoint. The method is able to localize 12cm wide hidden objects in 2D with 1.7cm accuracy. The method also identifies the hidden object class with 87.7% accuracy (compared to 33.3% random accuracy). This paper also provides an analysis on the distribution of information that encodes the occluded object in the accessible scene. We show that, unlike previously thought, the area that extends beyond the corner is essential for accurate object localization and identification. |
Tasks | Object Localization |
Published | 2018-10-27 |
URL | http://arxiv.org/abs/1810.11710v1 |
http://arxiv.org/pdf/1810.11710v1.pdf | |
PWC | https://paperswithcode.com/paper/flash-photography-for-data-driven-hidden |
Repo | |
Framework | |
Word Embedding based on Low-Rank Doubly Stochastic Matrix Decomposition
Title | Word Embedding based on Low-Rank Doubly Stochastic Matrix Decomposition |
Authors | Denis Sedov, Zhirong Yang |
Abstract | Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, the similarity in embedding space is not optimized in the learning. In this paper we propose a novel neighbor embedding method which directly learns an embedding simplex where the similarities between the mapped words are optimal in terms of minimal discrepancy to the input neighborhoods. Our method is built upon two-step random walks between words via topics and thus able to better reveal the topics among the words. Experiment results indicate that our method, compared with another existing word embedding approach, is more favorable for various queries. |
Tasks | |
Published | 2018-12-12 |
URL | http://arxiv.org/abs/1812.10401v1 |
http://arxiv.org/pdf/1812.10401v1.pdf | |
PWC | https://paperswithcode.com/paper/word-embedding-based-on-low-rank-doubly |
Repo | |
Framework | |