May 6, 2019

2865 words 14 mins read

Paper Group ANR 374

Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes. Stream Packing for Asynchronous Multi-Context Systems using ASP. Polymetric Rhythmic Feel for a Cognitive Drum Computer. Brundlefly at SemEval-2016 Task 12: Recurrent Neural Networks vs. Joint Inference for Clinical Temporal Informatio …

Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes


Title	Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes
Authors	Aditya Balu, Sambit Ghadai, Kin Gwn Lore, Gavin Young, Adarsh Krishnamurthy, Soumik Sarkar
Abstract	3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. In this paper, we present a 3D-CNN based method to learn distinct local geometric features of interest within an object. In this context, the voxelized representation may not be sufficient to capture the distinguishing information about such local features. To enable efficient learning, we augment the voxel data with surface normals of the object boundary. We then train a 3D-CNN with this augmented data and identify the local features critical for decision-making using 3D gradient-weighted class activation maps. An application of this feature identification framework is to recognize difficult-to-manufacture drilled hole features in a complex CAD geometry. The framework can be extended to identify difficult-to-manufacture features at multiple spatial scales leading to a real-time decision support system for design for manufacturability.
Tasks	Decision Making, Object Recognition
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02141v2
PDF	http://arxiv.org/pdf/1612.02141v2.pdf
PWC	https://paperswithcode.com/paper/learning-localized-geometric-features-using
Repo
Framework

Stream Packing for Asynchronous Multi-Context Systems using ASP


Title	Stream Packing for Asynchronous Multi-Context Systems using ASP
Authors	Stefan Ellmauthaler, Jörg Pührer
Abstract	When a processing unit relies on data from external streams, we may face the problem that the stream data needs to be rearranged in a way that allows the unit to perform its task(s). On arrival of new data, we must decide whether there is sufficient information available to start processing or whether to wait for more data. Furthermore, we need to ensure that the data meets the input specification of the processing step. In the case of multiple input streams it is also necessary to coordinate which data from which incoming stream should form the input of the next process instantiation. In this work, we propose a declarative approach as an interface between multiple streams and a processing unit. The idea is to specify via answer-set programming how to arrange incoming data in packages that are suitable as input for subsequent processing. Our approach is intended for use in asynchronous multi-context systems (aMCSs), a recently proposed framework for loose coupling of knowledge representation formalisms that allows for online reasoning in a dynamic environment. Contexts in aMCSs process data streams from external sources and other contexts.
Tasks
Published	2016-11-17
URL	http://arxiv.org/abs/1611.05640v1
PDF	http://arxiv.org/pdf/1611.05640v1.pdf
PWC	https://paperswithcode.com/paper/stream-packing-for-asynchronous-multi-context
Repo
Framework

Polymetric Rhythmic Feel for a Cognitive Drum Computer


Title	Polymetric Rhythmic Feel for a Cognitive Drum Computer
Authors	Oliver Weede
Abstract	This paper addresses a question about music cognition: how do we derive polymetric structures. A preference rule system is presented which is implemented into a drum computer. The preference rule system allows inferring local polymetric structures, like two-over-three and three-over-two. By analyzing the micro-timing of West African percussion music a timing pattern consisting of six pulses was discovered. It integrates binary and ternary rhythmic feels. The presented drum computer integrates the discovered superimposed polymetric swing (timing and velocity) appropriate to the rhythmic sequence the user inputs. For binary sequences, the amount of binary swing is increased and for ternary sequences, the ternary swing is increased.
Tasks
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06197v2
PDF	http://arxiv.org/pdf/1606.06197v2.pdf
PWC	https://paperswithcode.com/paper/polymetric-rhythmic-feel-for-a-cognitive-drum
Repo
Framework

Brundlefly at SemEval-2016 Task 12: Recurrent Neural Networks vs. Joint Inference for Clinical Temporal Information Extraction


Title	Brundlefly at SemEval-2016 Task 12: Recurrent Neural Networks vs. Joint Inference for Clinical Temporal Information Extraction
Authors	Jason Alan Fries
Abstract	We submitted two systems to the SemEval-2016 Task 12: Clinical TempEval challenge, participating in Phase 1, where we identified text spans of time and event expressions in clinical notes and Phase 2, where we predicted a relation between an event and its parent document creation time. For temporal entity extraction, we find that a joint inference-based approach using structured prediction outperforms a vanilla recurrent neural network that incorporates word embeddings trained on a variety of large clinical document sets. For document creation time relations, we find that a combination of date canonicalization and distant supervision rules for predicting relations on both events and time expressions improves classification, though gains are limited, likely due to the small scale of training data.
Tasks	Entity Extraction, Structured Prediction, Temporal Information Extraction, Word Embeddings
Published	2016-06-04
URL	http://arxiv.org/abs/1606.01433v1
PDF	http://arxiv.org/pdf/1606.01433v1.pdf
PWC	https://paperswithcode.com/paper/brundlefly-at-semeval-2016-task-12-recurrent
Repo
Framework

Pragmatic factors in image description: the case of negations


Title	Pragmatic factors in image description: the case of negations
Authors	Emiel van Miltenburg, Roser Morante, Desmond Elliott
Abstract	We provide a qualitative analysis of the descriptions containing negations (no, not, n’t, nobody, etc) in the Flickr30K corpus, and a categorization of negation uses. Based on this analysis, we provide a set of requirements that an image description system should have in order to generate negation sentences. As a pilot experiment, we used our categorization to manually annotate sentences containing negations in the Flickr30K corpus, with an agreement score of K=0.67. With this paper, we hope to open up a broader discussion of subjective language in image descriptions.
Tasks
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06164v2
PDF	http://arxiv.org/pdf/1606.06164v2.pdf
PWC	https://paperswithcode.com/paper/pragmatic-factors-in-image-description-the
Repo
Framework

First-Order Bayesian Network Specifications Capture the Complexity Class PP


Title	First-Order Bayesian Network Specifications Capture the Complexity Class PP
Authors	Fabio Gagliardi Cozman
Abstract	The point of this note is to prove that a language is in the complexity class PP if and only if the strings of the language encode valid inferences in a Bayesian network defined using function-free first-order logic with equality.
Tasks
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03437v1
PDF	http://arxiv.org/pdf/1609.03437v1.pdf
PWC	https://paperswithcode.com/paper/first-order-bayesian-network-specifications
Repo
Framework

Embedding Lexical Features via Low-Rank Tensors


Title	Embedding Lexical Features via Low-Rank Tensors
Authors	Mo Yu, Mark Dredze, Raman Arora, Matthew Gormley
Abstract	Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a new model that represents complex lexical features—comprised of parts for words, contextual information and labels—in a tensor that captures conjunction information among these parts. We apply low-rank tensor approximations to the corresponding parameter tensors to reduce the parameter space and improve prediction speed. Furthermore, we investigate two methods for handling features that include $n$-grams of mixed lengths. Our model achieves state-of-the-art results on tasks in relation extraction, PP-attachment, and preposition disambiguation.
Tasks	Relation Extraction
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00461v1
PDF	http://arxiv.org/pdf/1604.00461v1.pdf
PWC	https://paperswithcode.com/paper/embedding-lexical-features-via-low-rank
Repo
Framework

One-class classifiers based on entropic spanning graphs


Title	One-class classifiers based on entropic spanning graphs
Authors	Lorenzo Livi, Cesare Alippi
Abstract	One-class classifiers offer valuable tools to assess the presence of outliers in data. In this paper, we propose a design methodology for one-class classifiers based on entropic spanning graphs. Our approach takes into account the possibility to process also non-numeric data by means of an embedding procedure. The spanning graph is learned on the embedded input data and the outcoming partition of vertices defines the classifier. The final partition is derived by exploiting a criterion based on mutual information minimization. Here, we compute the mutual information by using a convenient formulation provided in terms of the $\alpha$-Jensen difference. Once training is completed, in order to associate a confidence level with the classifier decision, a graph-based fuzzy model is constructed. The fuzzification process is based only on topological information of the vertices of the entropic spanning graph. As such, the proposed one-class classifier is suitable also for data characterized by complex geometric structures. We provide experiments on well-known benchmarks containing both feature vectors and labeled graphs. In addition, we apply the method to the protein solubility recognition problem by considering several representations for the input samples. Experimental results demonstrate the effectiveness and versatility of the proposed method with respect to other state-of-the-art approaches.
Tasks	One-class classifier
Published	2016-04-08
URL	http://arxiv.org/abs/1604.02477v4
PDF	http://arxiv.org/pdf/1604.02477v4.pdf
PWC	https://paperswithcode.com/paper/one-class-classifiers-based-on-entropic
Repo
Framework

A One class Classifier based Framework using SVDD : Application to an Imbalanced Geological Dataset


Title	A One class Classifier based Framework using SVDD : Application to an Imbalanced Geological Dataset
Authors	Soumi Chaki, Akhilesh Kumar Verma, Aurobinda Routray, William K. Mohanty, Mamata Jenamani
Abstract	Evaluation of hydrocarbon reservoir requires classification of petrophysical properties from available dataset. However, characterization of reservoir attributes is difficult due to the nonlinear and heterogeneous nature of the subsurface physical properties. In this context, present study proposes a generalized one class classification framework based on Support Vector Data Description (SVDD) to classify a reservoir characteristic water saturation into two classes (Class high and Class low) from four logs namely gamma ray, neutron porosity, bulk density, and P sonic using an imbalanced dataset. A comparison is carried out among proposed framework and different supervised classification algorithms in terms of g metric means and execution time. Experimental results show that proposed framework has outperformed other classifiers in terms of these performance evaluators. It is envisaged that the classification analysis performed in this study will be useful in further reservoir modeling.
Tasks	One-class classifier
Published	2016-12-02
URL	http://arxiv.org/abs/1612.01349v1
PDF	http://arxiv.org/pdf/1612.01349v1.pdf
PWC	https://paperswithcode.com/paper/a-one-class-classifier-based-framework-using
Repo
Framework

Development of a hybrid learning system based on SVM, ANFIS and domain knowledge: DKFIS


Title	Development of a hybrid learning system based on SVM, ANFIS and domain knowledge: DKFIS
Authors	Soumi Chaki, Aurobinda Routray, William K. Mohanty, Mamata Jenamani
Abstract	This paper presents the development of a hybrid learning system based on Support Vector Machines (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS) and domain knowledge to solve prediction problem. The proposed two-stage Domain Knowledge based Fuzzy Information System (DKFIS) improves the prediction accuracy attained by ANFIS alone. The proposed framework has been implemented on a noisy and incomplete dataset acquired from a hydrocarbon field located at western part of India. Here, oil saturation has been predicted from four different well logs i.e. gamma ray, resistivity, density, and clay volume. In the first stage, depending on zero or near zero and non-zero oil saturation levels the input vector is classified into two classes (Class 0 and Class 1) using SVM. The classification results have been further fine-tuned applying expert knowledge based on the relationship among predictor variables i.e. well logs and target variable - oil saturation. Second, an ANFIS is designed to predict non-zero (Class 1) oil saturation values from predictor logs. The predicted output has been further refined based on expert knowledge. It is apparent from the experimental results that the expert intervention with qualitative judgment at each stage has rendered the prediction into the feasible and realistic ranges. The performance analysis of the prediction in terms of four performance metrics such as correlation coefficient (CC), root mean square error (RMSE), and absolute error mean (AEM), scatter index (SI) has established DKFIS as a useful tool for reservoir characterization.
Tasks
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00585v1
PDF	http://arxiv.org/pdf/1612.00585v1.pdf
PWC	https://paperswithcode.com/paper/development-of-a-hybrid-learning-system-based
Repo
Framework

Interaction Pursuit with Feature Screening and Selection


Title	Interaction Pursuit with Feature Screening and Selection
Authors	Yingying Fan, Yinfei Kong, Daoji Li, Jinchi Lv
Abstract	Understanding how features interact with each other is of paramount importance in many scientific discoveries and contemporary applications. Yet interaction identification becomes challenging even for a moderate number of covariates. In this paper, we suggest an efficient and flexible procedure, called the interaction pursuit (IP), for interaction identification in ultra-high dimensions. The suggested method first reduces the number of interactions and main effects to a moderate scale by a new feature screening approach, and then selects important interactions and main effects in the reduced feature space using regularization methods. Compared to existing approaches, our method screens interactions separately from main effects and thus can be more effective in interaction screening. Under a fairly general framework, we establish that for both interactions and main effects, the method enjoys the sure screening property in screening and oracle inequalities in selection. Our method and theoretical results are supported by several simulation and real data examples.
Tasks
Published	2016-05-28
URL	http://arxiv.org/abs/1605.08933v1
PDF	http://arxiv.org/pdf/1605.08933v1.pdf
PWC	https://paperswithcode.com/paper/interaction-pursuit-with-feature-screening
Repo
Framework

Part-of-Speech Tagging for Historical English


Title	Part-of-Speech Tagging for Historical English
Authors	Yi Yang, Jacob Eisenstein
Abstract	As more historical texts are digitized, there is interest in applying natural language processing tools to these archives. However, the performance of these tools is often unsatisfactory, due to language change and genre differences. Spelling normalization heuristics are the dominant solution for dealing with historical texts, but this approach fails to account for changes in usage and vocabulary. In this empirical paper, we assess the capability of domain adaptation techniques to cope with historical texts, focusing on the classic benchmark task of part-of-speech tagging. We evaluate several domain adaptation methods on the task of tagging Early Modern English and Modern British English texts in the Penn Corpora of Historical English. We demonstrate that the Feature Embedding method for unsupervised domain adaptation outperforms word embeddings and Brown clusters, showing the importance of embedding the entire feature space, rather than just individual words. Feature Embeddings also give better performance than spelling normalization, but the combination of the two methods is better still, yielding a 5% raw improvement in tagging accuracy on Early Modern English texts.
Tasks	Domain Adaptation, Part-Of-Speech Tagging, Unsupervised Domain Adaptation, Word Embeddings
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03144v2
PDF	http://arxiv.org/pdf/1603.03144v2.pdf
PWC	https://paperswithcode.com/paper/part-of-speech-tagging-for-historical-english
Repo
Framework

Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning


Title	Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning
Authors	Yulia Tsvetkov, Sunayana Sitaram, Manaal Faruqui, Guillaume Lample, Patrick Littell, David Mortensen, Alan W Black, Lori Levin, Chris Dyer
Abstract	We introduce polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to be predicted. We apply these to the problem of modeling phone sequences—a domain in which universal symbol inventories and cross-linguistically shared feature representations are a natural fit. Intrinsic evaluation on held-out perplexity, qualitative analysis of the learned representations, and extrinsic evaluation in two downstream applications that make use of phonetic features show (i) that polyglot models better generalize to held-out data than comparable monolingual models and (ii) that polyglot phonetic feature representations are of higher quality than those learned monolingually.
Tasks	Representation Learning
Published	2016-05-12
URL	http://arxiv.org/abs/1605.03832v1
PDF	http://arxiv.org/pdf/1605.03832v1.pdf
PWC	https://paperswithcode.com/paper/polyglot-neural-language-models-a-case-study
Repo
Framework

Multilevel Anomaly Detection for Mixed Data


Title	Multilevel Anomaly Detection for Mixed Data
Authors	Kien Do, Truyen Tran, Svetha Venkatesh
Abstract	Anomalies are those deviating from the norm. Unsupervised anomaly detection often translates to identifying low density regions. Major problems arise when data is high-dimensional and mixed of discrete and continuous attributes. We propose MIXMAD, which stands for MIXed data Multilevel Anomaly Detection, an ensemble method that estimates the sparse regions across multiple levels of abstraction of mixed data. The hypothesis is for domains where multiple data abstractions exist, a data point may be anomalous with respect to the raw representation or more abstract representations. To this end, our method sequentially constructs an ensemble of Deep Belief Nets (DBNs) with varying depths. Each DBN is an energy-based detector at a predefined abstraction level. At the bottom level of each DBN, there is a Mixed-variate Restricted Boltzmann Machine that models the density of mixed data. Predictions across the ensemble are finally combined via rank aggregation. The proposed MIXMAD is evaluated on high-dimensional realworld datasets of different characteristics. The results demonstrate that for anomaly detection, (a) multilevel abstraction of high-dimensional and mixed data is a sensible strategy, and (b) empirically, MIXMAD is superior to popular unsupervised detection methods for both homogeneous and mixed data.
Tasks	Anomaly Detection, Unsupervised Anomaly Detection
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06249v1
PDF	http://arxiv.org/pdf/1610.06249v1.pdf
PWC	https://paperswithcode.com/paper/multilevel-anomaly-detection-for-mixed-data
Repo
Framework

Sequential Learning without Feedback


Title	Sequential Learning without Feedback
Authors	Manjesh Hanawal, Csaba Szepesvari, Venkatesh Saligrama
Abstract	In many security and healthcare systems a sequence of features/sensors/tests are used for detection and diagnosis. Each test outputs a prediction of the latent state, and carries with it inherent costs. Our objective is to {\it learn} strategies for selecting tests to optimize accuracy & costs. Unfortunately it is often impossible to acquire in-situ ground truth annotations and we are left with the problem of unsupervised sensor selection (USS). We pose USS as a version of stochastic partial monitoring problem with an {\it unusual} reward structure (even noisy annotations are unavailable). Unsurprisingly no learner can achieve sublinear regret without further assumptions. To this end we propose the notion of weak-dominance. This is a condition on the joint probability distribution of test outputs and latent state and says that whenever a test is accurate on an example, a later test in the sequence is likely to be accurate as well. We empirically verify that weak dominance holds on real datasets and prove that it is a maximal condition for achieving sublinear regret. We reduce USS to a special case of multi-armed bandit problem with side information and develop polynomial time algorithms that achieve sublinear regret.
Tasks
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05394v1
PDF	http://arxiv.org/pdf/1610.05394v1.pdf
PWC	https://paperswithcode.com/paper/sequential-learning-without-feedback
Repo
Framework