July 27, 2019

2942 words 14 mins read

Paper Group ANR 620

A case study on English-Malayalam Machine Translation. Speaker identification from the sound of the human breath. Scaling Text with the Class Affinity Model. ALL-IN-1: Short Text Classification with One Model for All Languages. Multi-frequency image reconstruction for radio-interferometry with self-tuned regularization parameters. Dynamical selecti …

A case study on English-Malayalam Machine Translation


Title	A case study on English-Malayalam Machine Translation
Authors	Sreelekha S, Pushpak Bhattacharyya
Abstract	In this paper we present our work on a case study on Statistical Machine Translation (SMT) and Rule based machine translation (RBMT) for translation from English to Malayalam and Malayalam to English. One of the motivations of our study is to make a three way performance comparison, such as, a) SMT and RBMT b) English to Malayalam SMT and Malayalam to English SMT c) English to Malayalam RBMT and Malayalam to English RBMT. We describe the development of English to Malayalam and Malayalam to English baseline phrase based SMT system and the evaluation of its performance compared against the RBMT system. Based on our study the observations are: a) SMT systems outperform RBMT systems, b) In the case of SMT, English - Malayalam systems perform better than that of Malayalam - English systems, c) In the case RBMT, Malayalam to English systems are performing better than English to Malayalam systems. Based on our evaluations and detailed error analysis, we describe the requirements of incorporating morphological processing into the SMT to improve the accuracy of translation.
Tasks	Machine Translation
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08217v1
PDF	http://arxiv.org/pdf/1702.08217v1.pdf
PWC	https://paperswithcode.com/paper/a-case-study-on-english-malayalam-machine
Repo
Framework

Speaker identification from the sound of the human breath


Title	Speaker identification from the sound of the human breath
Authors	Wenbo Zhao, Yang Gao, Rita Singh
Abstract	This paper examines the speaker identification potential of breath sounds in continuous speech. Speech is largely produced during exhalation. In order to replenish air in the lungs, speakers must periodically inhale. When inhalation occurs in the midst of continuous speech, it is generally through the mouth. Intra-speech breathing behavior has been the subject of much study, including the patterns, cadence, and variations in energy levels. However, an often ignored characteristic is the {\em sound} produced during the inhalation phase of this cycle. Intra-speech inhalation is rapid and energetic, performed with open mouth and glottis, effectively exposing the entire vocal tract to enable maximum intake of air. This results in vocal tract resonances evoked by turbulence that are characteristic of the speaker’s speech-producing apparatus. Consequently, the sounds of inhalation are expected to carry information about the speaker’s identity. Moreover, unlike other spoken sounds which are subject to active control, inhalation sounds are generally more natural and less affected by voluntary influences. The goal of this paper is to demonstrate that breath sounds are indeed bio-signatures that can be used to identify speakers. We show that these sounds by themselves can yield remarkably accurate speaker recognition with appropriate feature representations and classification frameworks.
Tasks	Speaker Identification, Speaker Recognition
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00171v2
PDF	http://arxiv.org/pdf/1712.00171v2.pdf
PWC	https://paperswithcode.com/paper/speaker-identification-from-the-sound-of-the
Repo
Framework

Scaling Text with the Class Affinity Model


Title	Scaling Text with the Class Affinity Model
Authors	Patrick O. Perry, Kenneth Benoit
Abstract	Probabilistic methods for classifying text form a rich tradition in machine learning and natural language processing. For many important problems, however, class prediction is uninteresting because the class is known, and instead the focus shifts to estimating latent quantities related to the text, such as affect or ideology. We focus on one such problem of interest, estimating the ideological positions of 55 Irish legislators in the 1991 D'ail confidence vote. To solve the D'ail scaling problem and others like it, we develop a text modeling framework that allows actors to take latent positions on a “gray” spectrum between “black” and “white” polar opposites. We are able to validate results from this model by measuring the influences exhibited by individual words, and we are able to quantify the uncertainty in the scaling estimates by using a sentence-level block bootstrap. Applying our method to the D'ail debate, we are able to scale the legislators between extreme pro-government and pro-opposition in a way that reveals nuances in their speeches not captured by their votes or party affiliations.
Tasks
Published	2017-10-24
URL	http://arxiv.org/abs/1710.08963v1
PDF	http://arxiv.org/pdf/1710.08963v1.pdf
PWC	https://paperswithcode.com/paper/scaling-text-with-the-class-affinity-model
Repo
Framework

ALL-IN-1: Short Text Classification with One Model for All Languages


Title	ALL-IN-1: Short Text Classification with One Model for All Languages
Authors	Barbara Plank
Abstract	We present ALL-IN-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and character n-grams. Our model is simple, easily extendable yet very effective, overall ranking 1st (out of 12 teams) in the IJCNLP 2017 shared task on customer feedback analysis in four languages: English, French, Japanese and Spanish.
Tasks	Multilingual text classification, Multilingual Word Embeddings, Text Classification, Word Embeddings
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09589v1
PDF	http://arxiv.org/pdf/1710.09589v1.pdf
PWC	https://paperswithcode.com/paper/all-in-1-short-text-classification-with-one
Repo
Framework

Multi-frequency image reconstruction for radio-interferometry with self-tuned regularization parameters


Title	Multi-frequency image reconstruction for radio-interferometry with self-tuned regularization parameters
Authors	Rita Ammanouil, André Ferrari, Rémi Flamary, Chiara Ferrari, David Mary
Abstract	As the world’s largest radio telescope, the Square Kilometer Array (SKA) will provide radio interferometric data with unprecedented detail. Image reconstruction algorithms for radio interferometry are challenged to scale well with TeraByte image sizes never seen before. In this work, we investigate one such 3D image reconstruction algorithm known as MUFFIN (MUlti-Frequency image reconstruction For radio INterferometry). In particular, we focus on the challenging task of automatically finding the optimal regularization parameter values. In practice, finding the regularization parameters using classical grid search is computationally intensive and nontrivial due to the lack of ground- truth. We adopt a greedy strategy where, at each iteration, the optimal parameters are found by minimizing the predicted Stein unbiased risk estimate (PSURE). The proposed self-tuned version of MUFFIN involves parallel and computationally efficient steps, and scales well with large- scale data. Finally, numerical results on a 3D image are presented to showcase the performance of the proposed approach.
Tasks	Image Reconstruction, Radio Interferometry
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03608v1
PDF	http://arxiv.org/pdf/1703.03608v1.pdf
PWC	https://paperswithcode.com/paper/multi-frequency-image-reconstruction-for
Repo
Framework

Dynamical selection of Nash equilibria using Experience Weighted Attraction Learning: emergence of heterogeneous mixed equilibria


Title	Dynamical selection of Nash equilibria using Experience Weighted Attraction Learning: emergence of heterogeneous mixed equilibria
Authors	Robin Nicole, Peter Sollich
Abstract	We study the distribution of strategies in a large game that models how agents choose among different double auction markets. We classify the possible mean field Nash equilibria, which include potentially segregated states where an agent population can split into subpopulations adopting different strategies. As the game is aggregative, the actual equilibrium strategy distributions remain undetermined, however. We therefore compare with the results of Experience-Weighted Attraction (EWA) learning, which at long times leads to Nash equilibria in the appropriate limits of large intensity of choice, low noise (long agent memory) and perfect imputation of missing scores (fictitious play). The learning dynamics breaks the indeterminacy of the Nash equilibria. Non-trivially, depending on how the relevant limits are taken, more than one type of equilibrium can be selected. These include the standard homogeneous mixed and heterogeneous pure states, but also \emph{heterogeneous mixed} states where different agents play different strategies that are not all pure. The analysis of the EWA learning involves Fokker-Planck modeling combined with large deviation methods. The theoretical results are confirmed by multi-agent simulations.
Tasks	Imputation
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09763v1
PDF	http://arxiv.org/pdf/1706.09763v1.pdf
PWC	https://paperswithcode.com/paper/dynamical-selection-of-nash-equilibria-using
Repo
Framework

Learning with Bounded Instance- and Label-dependent Label Noise


Title	Learning with Bounded Instance- and Label-dependent Label Noise
Authors	Jiacheng Cheng, Tongliang Liu, Kotagiri Ramamohanarao, Dacheng Tao
Abstract	Instance- and Label-dependent label Noise (ILN) is widely existed in real-world datasets but has been rarely studied. In this paper, we focus on Bounded Instance- and Label-dependent label Noise (BILN), a particular case of ILN where the label noise rates, the probabilities that the true labels of examples flip into the corrupted ones, have upper bounds. Specifically, we introduce the concept of distilled examples, i.e. examples whose labels are identical with the labels assigned for them by the Bayes optimal classifier, and prove that under certain conditions classifier learnt on distilled examples will converge to the Bayes optimal classifier. Inspired by the idea of learning with distilled examples, we then propose a learning algorithm with theoretical guarantees for its robustness to BILN. At last, empirical evaluations on both synthetic and real-world datasets show effectiveness of our algorithm in learning with BILN.
Tasks
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03768v2
PDF	http://arxiv.org/pdf/1709.03768v2.pdf
PWC	https://paperswithcode.com/paper/learning-with-bounded-instance-and-label
Repo
Framework

Deep Extreme Multi-label Learning


Title	Deep Extreme Multi-label Learning
Authors	Wenjie Zhang, Junchi Yan, Xiangfeng Wang, Hongyuan Zha
Abstract	Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves $2^L$ possible label sets especially when the label dimension $L$ is huge, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by originally establishing an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems including multi-label classification, however it has not been properly introduced to XML, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Extensive experiments on public datasets for XML show that our method performs competitive against state-of-the-art result.
Tasks	Extreme Multi-Label Classification, Multi-Label Classification, Multi-Label Learning
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03718v4
PDF	http://arxiv.org/pdf/1704.03718v4.pdf
PWC	https://paperswithcode.com/paper/deep-extreme-multi-label-learning
Repo
Framework

Function space analysis of deep learning representation layers


Title	Function space analysis of deep learning representation layers
Authors	Oren Elisha, Shai Dekel
Abstract	In this paper we propose a function space approach to Representation Learning and the analysis of the representation layers in deep learning architectures. We show how to compute a weak-type Besov smoothness index that quantifies the geometry of the clustering in the feature space. This approach was already applied successfully to improve the performance of machine learning algorithms such as the Random Forest and tree-based Gradient Boosting. Our experiments demonstrate that in well-known and well-performing trained networks, the Besov smoothness of the training set, measured in the corresponding hidden layer feature map representation, increases from layer to layer. We also contribute to the understanding of generalization by showing how the Besov smoothness of the representations, decreases as we add more mis-labeling to the training data. We hope this approach will contribute to the de-mystification of some aspects of deep learning.
Tasks	Representation Learning
Published	2017-10-09
URL	http://arxiv.org/abs/1710.03263v1
PDF	http://arxiv.org/pdf/1710.03263v1.pdf
PWC	https://paperswithcode.com/paper/function-space-analysis-of-deep-learning
Repo
Framework

Deep Supervised Discrete Hashing


Title	Deep Supervised Discrete Hashing
Authors	Qi Li, Zhenan Sun, Ran He, Tieniu Tan
Abstract	With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years. Benefit from recent advances in deep learning, deep hashing methods have achieved promising results for image retrieval. However, there are some limitations of previous deep hashing methods (e.g., the semantic information is not fully exploited). In this paper, we develop a deep supervised discrete hashing algorithm based on the assumption that the learned binary codes should be ideal for classification. Both the pairwise label information and the classification information are used to learn the hash codes within one stream framework. We constrain the outputs of the last layer to be binary codes directly, which is rarely investigated in deep hashing algorithm. Because of the discrete nature of hash codes, an alternating minimization method is used to optimize the objective function. Experimental results have shown that our method outperforms current state-of-the-art methods on benchmark datasets.
Tasks	Image Retrieval
Published	2017-05-31
URL	http://arxiv.org/abs/1705.10999v2
PDF	http://arxiv.org/pdf/1705.10999v2.pdf
PWC	https://paperswithcode.com/paper/deep-supervised-discrete-hashing
Repo
Framework

An Enhanced Hybrid MobileNet


Title	An Enhanced Hybrid MobileNet
Authors	Hong-Yen Chen, Chung-Yen Su
Abstract	Complicated and deep neural network models can achieve high accuracy for image recognition. However, they require a huge amount of computations and model parameters, which are not suitable for mobile and embedded devices. Therefore, MobileNet was proposed, which can reduce the number of parameters and computational cost dramatically. The main idea of MobileNet is to use a depthwise separable convolution. Two hyper-parameters, a width multiplier and a resolution multiplier are used to the trade-off between the accuracy and the latency. In this paper, we propose a new architecture to improve the MobileNet. Instead of using the resolution multiplier, we use a depth multiplier and combine with either Fractional Max Pooling or the max pooling. Experimental results on CIFAR database show that the proposed architecture can reduce the amount of computational cost and increase the accuracy simultaneously.
Tasks
Published	2017-12-13
URL	https://arxiv.org/abs/1712.04698v2
PDF	https://arxiv.org/pdf/1712.04698v2.pdf
PWC	https://paperswithcode.com/paper/the-enhanced-hybrid-mobilenet
Repo
Framework

Landmark Guided Probabilistic Roadmap Queries


Title	Landmark Guided Probabilistic Roadmap Queries
Authors	Brian Paden, Yannik Nager, Emilio Frazzoli
Abstract	A landmark based heuristic is investigated for reducing query phase run-time of the probabilistic roadmap (\PRM) motion planning method. The heuristic is generated by storing minimum spanning trees from a small number of vertices within the \PRM graph and using these trees to approximate the cost of a shortest path between any two vertices of the graph. The intermediate step of preprocessing the graph increases the time and memory requirements of the classical motion planning technique in exchange for speeding up individual queries making the method advantageous in multi-query applications. This paper investigates these trade-offs on \PRM graphs constructed in randomized environments as well as a practical manipulator simulation.We conclude that the method is preferable to Dijkstra’s algorithm or the ${\rm A}^*$ algorithm with conventional heuristics in multi-query applications.
Tasks	Motion Planning
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01886v1
PDF	http://arxiv.org/pdf/1704.01886v1.pdf
PWC	https://paperswithcode.com/paper/landmark-guided-probabilistic-roadmap-queries
Repo
Framework

Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis


Title	Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis
Authors	Yi Tay, Anh Tuan Luu, Siu Cheung Hui
Abstract	Aspect-based sentiment analysis (ABSA) tries to predict the polarity of a given document with respect to a given aspect entity. While neural network architectures have been successful in predicting the overall polarity of sentences, aspect-specific sentiment analysis still remains as an open problem. In this paper, we propose a novel method for integrating aspect information into the neural model. More specifically, we incorporate aspect information into the neural model by modeling word-aspect relationships. Our novel model, \textit{Aspect Fusion LSTM} (AF-LSTM) learns to attend based on associative relationships between sentence words and aspect which allows our model to adaptively focus on the correct words given an aspect term. This ameliorates the flaws of other state-of-the-art models that utilize naive concatenations to model word-aspect similarity. Instead, our model adopts circular convolution and circular correlation to model the similarity between aspect and words and elegantly incorporates this within a differentiable neural attention framework. Finally, our model is end-to-end differentiable and highly related to convolution-correlation (holographic like) memories. Our proposed neural model achieves state-of-the-art performance on benchmark datasets, outperforming ATAE-LSTM by $4%-5%$ on average across multiple datasets.
Tasks	Aspect-Based Sentiment Analysis
Published	2017-12-14
URL	http://arxiv.org/abs/1712.05403v1
PDF	http://arxiv.org/pdf/1712.05403v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-attend-via-word-aspect
Repo
Framework

Network Model Selection Using Task-Focused Minimum Description Length


Title	Network Model Selection Using Task-Focused Minimum Description Length
Authors	Ivan Brugere, Tanya Y. Berger-Wolf
Abstract	Networks are fundamental models for data used in practically every application domain. In most instances, several implicit or explicit choices about the network definition impact the translation of underlying data to a network representation, and the subsequent question(s) about the underlying system being represented. Users of downstream network data may not even be aware of these choices or their impacts. We propose a task-focused network model selection methodology which addresses several key challenges. Our approach constructs network models from underlying data and uses minimum description length (MDL) criteria for selection. Our methodology measures efficiency, a general and comparable measure of the network’s performance of a local (i.e. node-level) predictive task of interest. Selection on efficiency favors parsimonious (e.g. sparse) models to avoid overfitting and can be applied across arbitrary tasks and representations. We show stability, sensitivity, and significance testing in our methodology.
Tasks	Model Selection
Published	2017-10-14
URL	http://arxiv.org/abs/1710.05207v2
PDF	http://arxiv.org/pdf/1710.05207v2.pdf
PWC	https://paperswithcode.com/paper/network-model-selection-using-task-focused
Repo
Framework

Rank Determination for Low-Rank Data Completion


Title	Rank Determination for Low-Rank Data Completion
Authors	Morteza Ashraphijuo, Xiaodong Wang, Vaneet Aggarwal
Abstract	Recently, fundamental conditions on the sampling patterns have been obtained for finite completability of low-rank matrices or tensors given the corresponding ranks. In this paper, we consider the scenario where the rank is not given and we aim to approximate the unknown rank based on the location of sampled entries and some given completion. We consider a number of data models, including single-view matrix, multi-view matrix, CP tensor, tensor-train tensor and Tucker tensor. For each of these data models, we provide an upper bound on the rank when an arbitrary low-rank completion is given. We characterize these bounds both deterministically, i.e., with probability one given that the sampling pattern satisfies certain combinatorial properties, and probabilistically, i.e., with high probability given that the sampling probability is above some threshold. Moreover, for both single-view matrix and CP tensor, we are able to show that the obtained upper bound is exactly equal to the unknown rank if the lowest-rank completion is given. Furthermore, we provide numerical experiments for the case of single-view matrix, where we use nuclear norm minimization to find a low-rank completion of the sampled data and we observe that in most of the cases the proposed upper bound on the rank is equal to the true rank.
Tasks
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00622v1
PDF	http://arxiv.org/pdf/1707.00622v1.pdf
PWC	https://paperswithcode.com/paper/rank-determination-for-low-rank-data
Repo
Framework