Paper Group ANR 65
Biomedical Document Clustering and Visualization based on the Concepts of Diseases. Continuous Trajectory Planning Based on Learning Optimization in High Dimensional Input Space for Serial Manipulators. Learning Probabilistic Logic Programs in Continuous Domains. Towards Automation of Sense-type Identification of Verbs in OntoSenseNet(Telugu). Tran …
Biomedical Document Clustering and Visualization based on the Concepts of Diseases
Title | Biomedical Document Clustering and Visualization based on the Concepts of Diseases |
Authors | Setu Shah, Xiao Luo |
Abstract | Document clustering is a text mining technique used to provide better document search and browsing in digital libraries or online corpora. A lot of research has been done on biomedical document clustering that is based on using existing ontology. But, associations and co-occurrences of the medical concepts are not well represented by using ontology. In this research, a vector representation of concepts of diseases and similarity measurement between concepts are proposed. They identify the closest concepts of diseases in the context of a corpus. Each document is represented by using the vector space model. A weight scheme is proposed to consider both local content and associations between concepts. A Self-Organizing Map is used as document clustering algorithm. The vector projection and visualization features of SOM enable visualization and analysis of the clusters distributions and relationships on the two dimensional space. The experimental results show that the proposed document clustering framework generates meaningful clusters and facilitate visualization of the clusters based on the concepts of diseases. |
Tasks | |
Published | 2018-10-22 |
URL | http://arxiv.org/abs/1810.09597v1 |
http://arxiv.org/pdf/1810.09597v1.pdf | |
PWC | https://paperswithcode.com/paper/biomedical-document-clustering-and |
Repo | |
Framework | |
Continuous Trajectory Planning Based on Learning Optimization in High Dimensional Input Space for Serial Manipulators
Title | Continuous Trajectory Planning Based on Learning Optimization in High Dimensional Input Space for Serial Manipulators |
Authors | Shiyu Zhang, Shuling Dai |
Abstract | To continuously generate trajectories for serial manipulators with high dimensional degrees of freedom (DOF) in the dynamic environment, a real-time optimal trajectory generation method based on machine learning aiming at high dimensional inputs is presented in this paper. First, a learning optimization (LO) framework is established, and implementations with different sub-methods are discussed. Additionally, multiple criteria are defined to evaluate the performance of LO models. Furthermore, aiming at high dimensional inputs, a database generation method based on input space dimension-reducing mapping is proposed. At last, this method is validated on motion planning for haptic feedback manipulators (HFM) in virtual reality systems. Results show that the input space dimension-reducing method can significantly elevate the efficiency and quality of database generation and consequently improve the performance of the LO. Moreover, using this LO method, real-time trajectory generation with high dimensional inputs can be achieved, which lays a foundation for continuous trajectory planning for high-DOF-robots in complex environments. |
Tasks | Motion Planning |
Published | 2018-12-18 |
URL | http://arxiv.org/abs/1812.07221v1 |
http://arxiv.org/pdf/1812.07221v1.pdf | |
PWC | https://paperswithcode.com/paper/continuous-trajectory-planning-based-on |
Repo | |
Framework | |
Learning Probabilistic Logic Programs in Continuous Domains
Title | Learning Probabilistic Logic Programs in Continuous Domains |
Authors | Stefanie Speichert, Vaishak Belle |
Abstract | The field of statistical relational learning aims at unifying logic and probability to reason and learn from data. Perhaps the most successful paradigm in the field is probabilistic logic programming: the enabling of stochastic primitives in logic programming, which is now increasingly seen to provide a declarative background to complex machine learning applications. While many systems offer inference capabilities, the more significant challenge is that of learning meaningful and interpretable symbolic representations from data. In that regard, inductive logic programming and related techniques have paved much of the way for the last few decades. Unfortunately, a major limitation of this exciting landscape is that much of the work is limited to finite-domain discrete probability distributions. Recently, a handful of systems have been extended to represent and perform inference with continuous distributions. The problem, of course, is that classical solutions for inference are either restricted to well-known parametric families (e.g., Gaussians) or resort to sampling strategies that provide correct answers only in the limit. When it comes to learning, moreover, inducing representations remains entirely open, other than “data-fitting” solutions that force-fit points to aforementioned parametric families. In this paper, we take the first steps towards inducing probabilistic logic programs for continuous and mixed discrete-continuous data, without being pigeon-holed to a fixed set of distribution families. Our key insight is to leverage techniques from piecewise polynomial function approximation theory, yielding a principled way to learn and compositionally construct density functions. We test the framework and discuss the learned representations. |
Tasks | Relational Reasoning |
Published | 2018-07-15 |
URL | http://arxiv.org/abs/1807.05527v2 |
http://arxiv.org/pdf/1807.05527v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-probabilistic-logic-programs-in |
Repo | |
Framework | |
Towards Automation of Sense-type Identification of Verbs in OntoSenseNet(Telugu)
Title | Towards Automation of Sense-type Identification of Verbs in OntoSenseNet(Telugu) |
Authors | Sreekavitha Parupalli, Vijjini Anvesh Rao, Radhika Mamidi |
Abstract | In this paper, we discuss the enrichment of a manually developed resource of Telugu lexicon, OntoSenseNet. OntoSenseNet is a ontological sense annotated lexicon that marks each verb of Telugu with a primary and a secondary sense. The area of research is relatively recent but has a large scope of development. We provide an introductory work to enrich the OntoSenseNet to promote further research in Telugu. Classifiers are adopted to learn the sense relevant features of the words in the resource and also to automate the tagging of sense-types for verbs. We perform a comparative analysis of different classifiers applied on OntoSenseNet. The results of the experiment prove that automated enrichment of the resource is effective using SVM classifiers and Adaboost ensemble. |
Tasks | |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01677v1 |
http://arxiv.org/pdf/1807.01677v1.pdf | |
PWC | https://paperswithcode.com/paper/towards-automation-of-sense-type |
Repo | |
Framework | |
Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
Title | Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation |
Authors | Hongyu Xiong, Ruixiao Sun |
Abstract | A natural language interface (NLI) to structured query is intriguing due to its wide industrial applications and high economical values. In this work, we tackle the problem of domain adaptation for NLI with limited data on target domain. Two important approaches are considered: (a) effective general-knowledge-learning on source domain semantic parsing, and (b) data augmentation on target domain. We present a Structured Query Inference Network (SQIN) to enhance learning for domain adaptation, by separating schema information from NL and decoding SQL in a more structural-aware manner; we also propose a GAN-based augmentation technique (AugmentGAN) to mitigate the issue of lacking target domain data. We report solid results on GeoQuery, Overnight, and WikiSQL to demonstrate state-of-the-art performances for both in-domain and domain-transfer tasks. |
Tasks | Data Augmentation, Domain Adaptation, Semantic Parsing |
Published | 2018-12-04 |
URL | http://arxiv.org/abs/1812.01245v2 |
http://arxiv.org/pdf/1812.01245v2.pdf | |
PWC | https://paperswithcode.com/paper/transferable-natural-language-interface-to |
Repo | |
Framework | |
Same-different problems strain convolutional neural networks
Title | Same-different problems strain convolutional neural networks |
Authors | Matthew Ricci, Junkyung Kim, Thomas Serre |
Abstract | The robust and efficient recognition of visual relations in images is a hallmark of biological vision. We argue that, despite recent progress in visual recognition, modern machine vision algorithms are severely limited in their ability to learn visual relations. Through controlled experiments, we demonstrate that visual-relation problems strain convolutional neural networks (CNNs). The networks eventually break altogether when rote memorization becomes impossible, as when intra-class variability exceeds network capacity. Motivated by the comparable success of biological vision, we argue that feedback mechanisms including attention and perceptual grouping may be the key computational components underlying abstract visual reasoning.\ |
Tasks | Visual Reasoning |
Published | 2018-02-09 |
URL | http://arxiv.org/abs/1802.03390v3 |
http://arxiv.org/pdf/1802.03390v3.pdf | |
PWC | https://paperswithcode.com/paper/same-different-problems-strain-convolutional |
Repo | |
Framework | |
Upping the Ante: Towards a Better Benchmark for Chinese-to-English Machine Translation
Title | Upping the Ante: Towards a Better Benchmark for Chinese-to-English Machine Translation |
Authors | Christian Hadiwinoto, Hwee Tou Ng |
Abstract | There are many machine translation (MT) papers that propose novel approaches and show improvements over their self-defined baselines. The experimental setting in each paper often differs from one another. As such, it is hard to determine if a proposed approach is really useful and advances the state of the art. Chinese-to-English translation is a common translation direction in MT papers, although there is not one widely accepted experimental setting in Chinese-to-English MT. Our goal in this paper is to propose a benchmark in evaluation setup for Chinese-to-English machine translation, such that the effectiveness of a new proposed MT approach can be directly compared to previous approaches. Towards this end, we also built a highly competitive state-of-the-art MT system trained on a large-scale training set. Our system outperforms reported results on NIST OpenMT test sets in almost all papers published in major conferences and journals in computational linguistics and artificial intelligence in the past 11 years. We argue that a standardized benchmark on data and performance is important for meaningful comparison. |
Tasks | Machine Translation |
Published | 2018-05-04 |
URL | http://arxiv.org/abs/1805.01676v1 |
http://arxiv.org/pdf/1805.01676v1.pdf | |
PWC | https://paperswithcode.com/paper/upping-the-ante-towards-a-better-benchmark |
Repo | |
Framework | |
eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing
Title | eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing |
Authors | Matteo Negri, Marco Turchi, Rajen Chatterjee, Nicola Bertoldi |
Abstract | Training models for the automatic correction of machine-translated text usually relies on data consisting of (source, MT, human post- edit) triplets providing, for each source sentence, examples of translation errors with the corresponding corrections made by a human post-editor. Ideally, a large amount of data of this kind should allow the model to learn reliable correction patterns and effectively apply them at test stage on unseen (source, MT) pairs. In practice, however, their limited availability calls for solutions that also integrate in the training process other sources of knowledge. Along this direction, state-of-the-art results have been recently achieved by systems that, in addition to a limited amount of available training data, exploit artificial corpora that approximate elements of the “gold” training instances with automatic translations. Following this idea, we present eSCAPE, the largest freely-available Synthetic Corpus for Automatic Post-Editing released so far. eSCAPE consists of millions of entries in which the MT element of the training triplets has been obtained by translating the source side of publicly-available parallel corpora, and using the target side as an artificial human post-edit. Translations are obtained both with phrase-based and neural models. For each MT paradigm, eSCAPE contains 7.2 million triplets for English-German and 3.3 millions for English-Italian, resulting in a total of 14,4 and 6,6 million instances respectively. The usefulness of eSCAPE is proved through experiments in a general-domain scenario, the most challenging one for automatic post-editing. For both language directions, the models trained on our artificial data always improve MT quality with statistically significant gains. The current version of eSCAPE can be freely downloaded from: http://hltshare.fbk.eu/QT21/eSCAPE.html. |
Tasks | Automatic Post-Editing |
Published | 2018-03-20 |
URL | http://arxiv.org/abs/1803.07274v1 |
http://arxiv.org/pdf/1803.07274v1.pdf | |
PWC | https://paperswithcode.com/paper/escape-a-large-scale-synthetic-corpus-for |
Repo | |
Framework | |
Learning Multi-Modal Self-Awareness Models for Autonomous Vehicles from Human Driving
Title | Learning Multi-Modal Self-Awareness Models for Autonomous Vehicles from Human Driving |
Authors | Mahdyar Ravanbakhsh, Mohamad Baydoun, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Carlo S. Regazzoni |
Abstract | This paper presents a novel approach for learning self-awareness models for autonomous vehicles. The proposed technique is based on the availability of synchronized multi-sensor dynamic data related to different maneuvering tasks performed by a human operator. It is shown that different machine learning approaches can be used to first learn single modality models using coupled Dynamic Bayesian Networks; such models are then correlated at event level to discover contextual multi-modal concepts. In the presented case, visual perception and localization are used as modalities. Cross-correlations among modalities in time is discovered from data and are described as probabilistic links connecting shared and private multi-modal DBNs at the event (discrete) level. Results are presented on experiments performed on an autonomous vehicle, highlighting potentiality of the proposed approach to allow anomaly detection and autonomous decision making based on learned self-awareness models. |
Tasks | Anomaly Detection, Autonomous Vehicles, Decision Making |
Published | 2018-06-07 |
URL | http://arxiv.org/abs/1806.02609v1 |
http://arxiv.org/pdf/1806.02609v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-multi-modal-self-awareness-models |
Repo | |
Framework | |
Independent Vector Analysis for Data Fusion Prior to Molecular Property Prediction with Machine Learning
Title | Independent Vector Analysis for Data Fusion Prior to Molecular Property Prediction with Machine Learning |
Authors | Zois Boukouvalas, Daniel C. Elton, Peter W. Chung, Mark D. Fuge |
Abstract | Due to its high computational speed and accuracy compared to ab-initio quantum chemistry and forcefield modeling, the prediction of molecular properties using machine learning has received great attention in the fields of materials design and drug discovery. A main ingredient required for machine learning is a training dataset consisting of molecular features\textemdash for example fingerprint bits, chemical descriptors, etc. that adequately characterize the corresponding molecules. However, choosing features for any application is highly non-trivial. No “universal” method for feature selection exists. In this work, we propose a data fusion framework that uses Independent Vector Analysis to exploit underlying complementary information contained in different molecular featurization methods, bringing us a step closer to automated feature generation. Our approach takes an arbitrary number of individual feature vectors and automatically generates a single, compact (low dimensional) set of molecular features that can be used to enhance the prediction performance of regression models. At the same time our methodology retains the possibility of interpreting the generated features to discover relationships between molecular structures and properties. We demonstrate this on the QM7b dataset for the prediction of several properties such as atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity, and excitation energies. In addition, we show how our method helps improve the prediction of experimental binding affinities for a set of human BACE-1 inhibitors. To encourage more widespread use of IVA we have developed the PyIVA Python package, an open source code which is available for download on Github. |
Tasks | Drug Discovery, Feature Selection, Molecular Property Prediction |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00628v1 |
http://arxiv.org/pdf/1811.00628v1.pdf | |
PWC | https://paperswithcode.com/paper/independent-vector-analysis-for-data-fusion |
Repo | |
Framework | |
Multi-Task Deep Convolutional Neural Network for the Segmentation of Type B Aortic Dissection
Title | Multi-Task Deep Convolutional Neural Network for the Segmentation of Type B Aortic Dissection |
Authors | Jianning Li, Long Cao, Yangyang Ge, W. Cheng, M. Bowen, G. Wei |
Abstract | Segmentation of the entire aorta and true-false lumen is crucial to inform plan and follow-up for endovascular repair of the rare yet life threatening type B aortic dissection. Manual segmentation by slice is time-consuming and requires expertise, while current computer-aided methods focus on the segmentation of the entire aorta, are unable to concurrently segment true-false lumen, and some require human interaction. We here report a fully automated approach based on a 3-D multi-task deep convolutional neural network that segments the entire aorta and true-false lumen from CTA images in a unified framework. For training, we built a database containing 254 CTA images (210 preoperative and 44 postoperative) obtained using various systems from 254 unique patients with type B aortic dissection. Slice-wise manual segmentation of the entire aorta and the true-false lumen for each 3-D CTA image was provided. Upon evaluation of another 16 CTA images (11 preoperative and 5 postoperative) with ground truth segmentation provided by experienced vascular surgeons, our method achieves a mean dice similarity score(DSC) of 0.910,0.849 and 0.821 for the entire aorta,true lumen and false lumen respectively. |
Tasks | |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.09860v6 |
http://arxiv.org/pdf/1806.09860v6.pdf | |
PWC | https://paperswithcode.com/paper/multi-task-deep-convolutional-neural-network |
Repo | |
Framework | |
RDEC: Integrating Regularization into Deep Embedded Clustering for Imbalanced Datasets
Title | RDEC: Integrating Regularization into Deep Embedded Clustering for Imbalanced Datasets |
Authors | Yaling Tao, Kentaro Takagi, Kouta Nakata |
Abstract | Clustering is a fundamental machine learning task and can be used in many applications. With the development of deep neural networks (DNNs), combining techniques from DNNs with clustering has become a new research direction and achieved some success. However, few studies have focused on the imbalanced-data problem which commonly occurs in real-world applications. In this paper, we propose a clustering method, regularized deep embedding clustering (RDEC), that integrates virtual adversarial training (VAT), a network regularization technique, with a clustering method called deep embedding clustering (DEC). DEC optimizes cluster assignments by pushing data more densely around centroids in latent space, but it is sometimes sensitive to the initial location of centroids, especially in the case of imbalanced data, where the minor class has less chance to be assigned a good centroid. RDEC introduces regularization using VAT to ensure the model’s robustness to local perturbations of data. VAT pushes data that are similar in the original space closer together in the latent space, bunching together data from minor classes and thereby facilitating cluster identification by RDEC. Combining the advantages of DEC and VAT, RDEC attains state-of-the-art performance on both balanced and imbalanced benchmark/real-world datasets. For example, accuracies are as high as 98.41% on MNIST dataset and 85.45% on a highly imbalanced dataset derived from the MNIST, which is nearly 8% higher than the current best result. |
Tasks | |
Published | 2018-12-06 |
URL | http://arxiv.org/abs/1812.02293v1 |
http://arxiv.org/pdf/1812.02293v1.pdf | |
PWC | https://paperswithcode.com/paper/rdec-integrating-regularization-into-deep |
Repo | |
Framework | |
Pose estimation of a single circle using default intrinsic calibration
Title | Pose estimation of a single circle using default intrinsic calibration |
Authors | Mariyanayagam Damien, Gurdjos Pierre, Chambon Sylvie, Brunet Florent, Charvillat Vincent |
Abstract | Circular markers are planar markers which offer great performances for detection and pose estimation. For an uncalibrated camera with an unknown focal length, at least the images of at least two coplanar circles are generally required to recover their poses. Unfortunately, detecting more than one ellipse in the image must be tricky and time-consuming, especially regarding concentric circles. On the other hand, when the camera is calibrated, one circle suffices but the solution is twofold and can hardly be disambiguated. Our contribution is to put beyond this limit by dealing with the uncalibrated case of a camera seeing one circle and discussing how to remove the ambiguity. We propose a new problem formulation that enables to show how to detect geometric configurations in which the ambiguity can be removed. Furthermore, we introduce the notion of default camera intrinsics and show, using intensive empirical works, the surprising observation that very approximate calibration can lead to accurate circle pose estimation. |
Tasks | Calibration, Pose Estimation |
Published | 2018-04-13 |
URL | http://arxiv.org/abs/1804.04922v1 |
http://arxiv.org/pdf/1804.04922v1.pdf | |
PWC | https://paperswithcode.com/paper/pose-estimation-of-a-single-circle-using |
Repo | |
Framework | |
A Trustworthy, Responsible and Interpretable System to Handle Chit Chat in Conversational Bots
Title | A Trustworthy, Responsible and Interpretable System to Handle Chit Chat in Conversational Bots |
Authors | Parag Agrawal, Anshuman Suri, Tulasi Menon |
Abstract | Most often, chat-bots are built to solve the purpose of a search engine or a human assistant: Their primary goal is to provide information to the user or help them complete a task. However, these chat-bots are incapable of responding to unscripted queries like “Hi, what’s up”, “What’s your favourite food”. Human evaluation judgments show that 4 humans come to a consensus on the intent of a given query which is from chat domain only 77% of the time, thus making it evident how non-trivial this task is. In our work, we show why it is difficult to break the chitchat space into clearly defined intents. We propose a system to handle this task in chat-bots, keeping in mind scalability, interpretability, appropriateness, trustworthiness, relevance and coverage. Our work introduces a pipeline for query understanding in chitchat using hierarchical intents as well as a way to use seq-seq auto-generation models in professional bots. We explore an interpretable model for chat domain detection and also show how various components such as adult/offensive classification, grammars/regex patterns, curated personality based responses, generic guided evasive responses and response generation models can be combined in a scalable way to solve this problem. |
Tasks | |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07600v2 |
http://arxiv.org/pdf/1811.07600v2.pdf | |
PWC | https://paperswithcode.com/paper/a-trustworthy-responsible-and-interpretable |
Repo | |
Framework | |
Modeling the Formation of Social Conventions from Embodied Real-Time Interactions
Title | Modeling the Formation of Social Conventions from Embodied Real-Time Interactions |
Authors | Ismael T. Freire, Clement Moulin-Frier, Marti Sanchez-Fibla, Xerxes D. Arsiwalla, Paul Verschure |
Abstract | What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral data in a social decision-making game that was analyzed both in discrete-time and continuous-time setups. Furthermore, unlike previous approaches, our model takes into account the role of sensorimotor control loops in embodied decision-making scenarios. For this purpose, we introduce the Control-based Reinforcement Learning (CRL) model. CRL is grounded in the Distributed Adaptive Control (DAC) theory of mind and brain, where low-level sensorimotor control is modulated through perceptual and behavioral learning in a layered structure. CRL follows these principles by implementing a feedback control loop handling the agent’s reactive behaviors (pre-wired reflexes), along with an adaptive layer that uses reinforcement learning to maximize long-term reward. We test our model in a multi-agent game-theoretic task in which coordination must be achieved to find an optimal solution. We show that CRL is able to reach human-level performance on standard game-theoretic metrics such as efficiency in acquiring rewards and fairness in reward distribution. |
Tasks | Decision Making |
Published | 2018-02-16 |
URL | https://arxiv.org/abs/1802.06108v3 |
https://arxiv.org/pdf/1802.06108v3.pdf | |
PWC | https://paperswithcode.com/paper/modeling-the-formation-of-social-conventions |
Repo | |
Framework | |