May 6, 2019

2681 words 13 mins read

Paper Group ANR 399

Question Answering on Freebase via Relation Extraction and Textual Evidence. Beating level-set methods for 3D seismic data interpolation: a primal-dual alternating approach. An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages. Answering Complicated Question Intents Expressed in Decomposed Question Sequenc …

Question Answering on Freebase via Relation Extraction and Textual Evidence


Title	Question Answering on Freebase via Relation Extraction and Textual Evidence
Authors	Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, Dongyan Zhao
Abstract	Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F_1 of 53.3%, a substantial improvement over the state-of-the-art.
Tasks	Question Answering, Relation Extraction, Semantic Parsing
Published	2016-03-03
URL	http://arxiv.org/abs/1603.00957v3
PDF	http://arxiv.org/pdf/1603.00957v3.pdf
PWC	https://paperswithcode.com/paper/question-answering-on-freebase-via-relation
Repo
Framework

Beating level-set methods for 3D seismic data interpolation: a primal-dual alternating approach


Title	Beating level-set methods for 3D seismic data interpolation: a primal-dual alternating approach
Authors	Rajiv Kumar, Oscar López, Damek Davis, Aleksandr Y. Aravkin, Felix J. Herrmann
Abstract	Acquisition cost is a crucial bottleneck for seismic workflows, and low-rank formulations for data interpolation allow practitioners to `fill in’ data volumes from critically subsampled data acquired in the field. Tremendous size of seismic data volumes required for seismic processing remains a major challenge for these techniques. We propose a new approach to solve residual constrained formulations for interpolation. We represent the data volume using matrix factors, and build a block-coordinate algorithm with constrained convex subproblems that are solved with a primal-dual splitting scheme. The new approach is competitive with state of the art level-set algorithms that interchange the role of objectives with constraints. We use the new algorithm to successfully interpolate a large scale 5D seismic data volume, generated from the geologically complex synthetic 3D Compass velocity model, where 80% of the data has been removed. \|
Tasks
Published	2016-07-09
URL	http://arxiv.org/abs/1607.02624v1
PDF	http://arxiv.org/pdf/1607.02624v1.pdf
PWC	https://paperswithcode.com/paper/beating-level-set-methods-for-3d-seismic-data
Repo
Framework

An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages


Title	An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages
Authors	Antonios Anastasopoulos, David Chiang, Long Duong
Abstract	For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training speech translation systems. A first step towards making use of such data would be to automatically align spoken words with their translations. We present a model that combines Dyer et al.‘s reparameterization of IBM Model 2 (fast-align) and k-means clustering using Dynamic Time Warping as a distance metric. The two components are trained jointly using expectation-maximization. In an extremely low-resource scenario, our model performs significantly better than both a neural model and a strong baseline.
Tasks
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08139v1
PDF	http://arxiv.org/pdf/1609.08139v1.pdf
PWC	https://paperswithcode.com/paper/an-unsupervised-probability-model-for-speech
Repo
Framework

Answering Complicated Question Intents Expressed in Decomposed Question Sequences


Title	Answering Complicated Question Intents Expressed in Decomposed Question Sequences
Authors	Mohit Iyyer, Wen-tau Yih, Ming-Wei Chang
Abstract	Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans. In an effort to explore a conversational QA setting, we present a more realistic task: answering sequences of simple but inter-related questions. We collect a dataset of 6,066 question sequences that inquire about semi-structured tables from Wikipedia, with 17,553 question-answer pairs in total. Existing QA systems face two major problems when evaluated on our dataset: (1) handling questions that contain coreferences to previous questions or answers, and (2) matching words or phrases in a question to corresponding entries in the associated table. We conclude by proposing strategies to handle both of these issues.
Tasks	Question Answering, Semantic Parsing
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01242v1
PDF	http://arxiv.org/pdf/1611.01242v1.pdf
PWC	https://paperswithcode.com/paper/answering-complicated-question-intents
Repo
Framework

A method for the segmentation of images based on thresholding and applied to vesicular textures


Title	A method for the segmentation of images based on thresholding and applied to vesicular textures
Authors	Amelia Carolina Sparavigna
Abstract	In image processing, a segmentation is a process of partitioning an image into multiple sets of pixels, that are defined as super-pixels. Each super-pixel is characterized by a label or parameter. Here, we are proposing a method for determining the super-pixels based on the thresholding of the image. This approach is quite useful for studying the images showing vesicular textures.
Tasks
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01131v1
PDF	http://arxiv.org/pdf/1612.01131v1.pdf
PWC	https://paperswithcode.com/paper/a-method-for-the-segmentation-of-images-based
Repo
Framework

EM-Based Mixture Models Applied to Video Event Detection


Title	EM-Based Mixture Models Applied to Video Event Detection
Authors	Alessandra Martins Coelho, Vania V. Estrela
Abstract	Surveillance system (SS) development requires hi-tech support to prevail over the shortcomings related to the massive quantity of visual information from SSs. Anything but reduced human monitoring became impossible by means of its physical and economic implications, and an advance towards an automated surveillance becomes the only way out. When it comes to a computer vision system, automatic video event comprehension is a challenging task due to motion clutter, event understanding under complex scenes, multilevel semantic event inference, contextualization of events and views obtained from multiple cameras, unevenness of motion scales, shape changes, occlusions and object interactions among lots of other impairments. In recent years, state-of-the-art models for video event classification and recognition include modeling events to discern context, detecting incidents with only one camera, low-level feature extraction and description, high-level semantic event classification, and recognition. Even so, it is still very burdensome to recuperate or label a specific video part relying solely on its content. Principal component analysis (PCA) has been widely known and used, but when combined with other techniques such as the expectation-maximization (EM) algorithm its computation becomes more efficient. This chapter introduces advances associated with the concept of Probabilistic PCA (PPCA) analysis of video event and it also aims at looking closely to ways and metrics to evaluate these less intensive EM implementations of PCA and KPCA.
Tasks
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02923v1
PDF	http://arxiv.org/pdf/1610.02923v1.pdf
PWC	https://paperswithcode.com/paper/em-based-mixture-models-applied-to-video
Repo
Framework

Action-Affect Classification and Morphing using Multi-Task Representation Learning


Title	Action-Affect Classification and Morphing using Multi-Task Representation Learning
Authors	Timothy J. Shields, Mohamed R. Amer, Max Ehrlich, Amir Tamrakar
Abstract	Most recent work focused on affect from facial expressions, and not as much on body. This work focuses on body affect analysis. Affect does not occur in isolation. Humans usually couple affect with an action in natural interactions; for example, a person could be talking and smiling. Recognizing body affect in sequences requires efficient algorithms to capture both the micro movements that differentiate between happy and sad and the macro variations between different actions. We depart from traditional approaches for time-series data analytics by proposing a multi-task learning model that learns a shared representation that is well-suited for action-affect classification as well as generation. For this paper we choose Conditional Restricted Boltzmann Machines to be our building block. We propose a new model that enhances the CRBM model with a factored multi-task component to become Multi-Task Conditional Restricted Boltzmann Machines (MTCRBMs). We evaluate our approach on two publicly available datasets, the Body Affect dataset and the Tower Game dataset, and show superior classification performance improvement over the state-of-the-art, as well as the generative abilities of our model.
Tasks	Multi-Task Learning, Representation Learning, Time Series
Published	2016-03-21
URL	http://arxiv.org/abs/1603.06554v1
PDF	http://arxiv.org/pdf/1603.06554v1.pdf
PWC	https://paperswithcode.com/paper/action-affect-classification-and-morphing
Repo
Framework

High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks


Title	High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
Authors	Zifeng Wu, Chunhua Shen, Anton van den Hengel
Abstract	We propose a method for high-performance semantic image segmentation (or semantic pixel labelling) based on very deep residual networks, which achieves the state-of-the-art performance. A few design factors are carefully considered to this end. We make the following contributions. (i) First, we evaluate different variations of a fully convolutional residual network so as to find the best configuration, including the number of layers, the resolution of feature maps, and the size of field-of-view. Our experiments show that further enlarging the field-of-view and increasing the resolution of feature maps are typically beneficial, which however inevitably leads to a higher demand for GPU memories. To walk around the limitation, we propose a new method to simulate a high resolution network with a low resolution network, which can be applied during training and/or testing. (ii) Second, we propose an online bootstrapping method for training. We demonstrate that online bootstrapping is critically important for achieving good accuracy. (iii) Third we apply the traditional dropout to some of the residual blocks, which further improves the performance. (iv) Finally, our method achieves the currently best mean intersection-over-union 78.3% on the PASCAL VOC 2012 dataset, as well as on the recent dataset Cityscapes.
Tasks	Semantic Segmentation
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04339v1
PDF	http://arxiv.org/pdf/1604.04339v1.pdf
PWC	https://paperswithcode.com/paper/high-performance-semantic-segmentation-using
Repo
Framework

Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA


Title	Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA
Authors	Aapo Hyvarinen, Hiroshi Morioka
Abstract	Nonlinear independent component analysis (ICA) provides an appealing framework for unsupervised feature learning, but the models proposed so far are not identifiable. Here, we first propose a new intuitive principle of unsupervised deep learning from time series which uses the nonstationary structure of the data. Our learning principle, time-contrastive learning (TCL), finds a representation which allows optimal discrimination of time segments (windows). Surprisingly, we show how TCL can be related to a nonlinear ICA model, when ICA is redefined to include temporal nonstationarities. In particular, we show that TCL combined with linear ICA estimates the nonlinear ICA model up to point-wise transformations of the sources, and this solution is unique — thus providing the first identifiability result for nonlinear ICA which is rigorous, constructive, as well as very general.
Tasks	Time Series
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06336v1
PDF	http://arxiv.org/pdf/1605.06336v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-feature-extraction-by-time
Repo
Framework

Memcomputing Numerical Inversion with Self-Organizing Logic Gates


Title	Memcomputing Numerical Inversion with Self-Organizing Logic Gates
Authors	Haik Manukian, Fabio L. Traversa, Massimiliano Di Ventra
Abstract	We propose to use Digital Memcomputing Machines (DMMs), implemented with self-organizing logic gates (SOLGs), to solve the problem of numerical inversion. Starting from fixed-point scalar inversion we describe the generalization to solving linear systems and matrix inversion. This method, when realized in hardware, will output the result in only one computational step. As an example, we perform simulations of the scalar case using a 5-bit logic circuit made of SOLGs, and show that the circuit successfully performs the inversion. Our method can be extended efficiently to any level of precision, since we prove that producing n-bit precision in the output requires extending the circuit by at most n bits. This type of numerical inversion can be implemented by DMM units in hardware, it is scalable, and thus of great benefit to any real-time computing application.
Tasks
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04316v3
PDF	http://arxiv.org/pdf/1612.04316v3.pdf
PWC	https://paperswithcode.com/paper/memcomputing-numerical-inversion-with-self
Repo
Framework

Enhanced Object Detection via Fusion With Prior Beliefs from Image Classification


Title	Enhanced Object Detection via Fusion With Prior Beliefs from Image Classification
Authors	Yilun Cao, Hyungtae Lee, Heesung Kwon
Abstract	In this paper, we introduce a novel fusion method that can enhance object detection performance by fusing decisions from two different types of computer vision tasks: object detection and image classification. In the proposed work, the class label of an image obtained from image classification is viewed as prior knowledge about existence or non-existence of certain objects. The prior knowledge is then fused with the decisions of object detection to improve detection accuracy by mitigating false positives of an object detector that are strongly contradicted with the prior knowledge. A recently introduced novel fusion approach called dynamic belief fusion (DBF) is used to fuse the detector output with the classification prior. Experimental results show that the detection performance of all the detection algorithms used in the proposed work is improved on benchmark datasets via the proposed fusion framework.
Tasks	Image Classification, Object Detection
Published	2016-10-21
URL	http://arxiv.org/abs/1610.06907v1
PDF	http://arxiv.org/pdf/1610.06907v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-object-detection-via-fusion-with
Repo
Framework

Distant supervision for emotion detection using Facebook reactions


Title	Distant supervision for emotion detection using Facebook reactions
Authors	Chris Pool, Malvina Nissim
Abstract	We exploit the Facebook reaction feature in a distant supervised fashion to train a support vector machine classifier for emotion detection, using several feature combinations and combining different Facebook pages. We test our models on existing benchmarks for emotion detection and show that employing only information that is derived completely automatically, thus without relying on any handcrafted lexicon as it’s usually done, we can achieve competitive results. The results also show that there is large room for improvement, especially by gearing the collection of Facebook pages, with a view to the target domain.
Tasks
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02988v1
PDF	http://arxiv.org/pdf/1611.02988v1.pdf
PWC	https://paperswithcode.com/paper/distant-supervision-for-emotion-detection
Repo
Framework

Multi-class classification: mirror descent approach


Title	Multi-class classification: mirror descent approach
Authors	Daria Reshetova
Abstract	We consider the problem of multi-class classification and a stochastic opti- mization approach to it. We derive risk bounds for stochastic mirror descent algorithm and provide examples of set geometries that make the use of the algorithm efficient in terms of error in k.
Tasks
Published	2016-06-30
URL	http://arxiv.org/abs/1607.00076v2
PDF	http://arxiv.org/pdf/1607.00076v2.pdf
PWC	https://paperswithcode.com/paper/multi-class-classification-mirror-descent
Repo
Framework

Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja’s Algorithm


Title	Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja’s Algorithm
Authors	Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford
Abstract	This work provides improved guarantees for streaming principle component analysis (PCA). Given $A_1, \ldots, A_n\in \mathbb{R}^{d\times d}$ sampled independently from distributions satisfying $\mathbb{E}[A_i] = \Sigma$ for $\Sigma \succeq \mathbf{0}$, this work provides an $O(d)$-space linear-time single-pass streaming algorithm for estimating the top eigenvector of $\Sigma$. The algorithm nearly matches (and in certain cases improves upon) the accuracy obtained by the standard batch method that computes top eigenvector of the empirical covariance $\frac{1}{n} \sum_{i \in [n]} A_i$ as analyzed by the matrix Bernstein inequality. Moreover, to achieve constant accuracy, our algorithm improves upon the best previous known sample complexities of streaming algorithms by either a multiplicative factor of $O(d)$ or $1/\mathrm{gap}$ where $\mathrm{gap}$ is the relative distance between the top two eigenvalues of $\Sigma$. These results are achieved through a novel analysis of the classic Oja’s algorithm, one of the oldest and most popular algorithms for streaming PCA. In particular, this work shows that simply picking a random initial point $w_0$ and applying the update rule $w_{i + 1} = w_i + \eta_i A_i w_i$ suffices to accurately estimate the top eigenvector, with a suitable choice of $\eta_i$. We believe our result sheds light on how to efficiently perform streaming PCA both in theory and in practice and we hope that our analysis may serve as the basis for analyzing many variants and extensions of streaming PCA.
Tasks
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06929v2
PDF	http://arxiv.org/pdf/1602.06929v2.pdf
PWC	https://paperswithcode.com/paper/streaming-pca-matching-matrix-bernstein-and
Repo
Framework

Using Big Data to Enhance the Bosch Production Line Performance: A Kaggle Challenge


Title	Using Big Data to Enhance the Bosch Production Line Performance: A Kaggle Challenge
Authors	Ankita Mangal, Nishant Kumar
Abstract	This paper describes our approach to the Bosch production line performance challenge run by Kaggle.com. Maximizing the production yield is at the heart of the manufacturing industry. At the Bosch assembly line, data is recorded for products as they progress through each stage. Data science methods are applied to this huge data repository consisting records of tests and measurements made for each component along the assembly line to predict internal failures. We found that it is possible to train a model that predicts which parts are most likely to fail. Thus a smarter failure detection system can be built and the parts tagged likely to fail can be salvaged to decrease operating costs and increase the profit margins.
Tasks
Published	2016-12-29
URL	http://arxiv.org/abs/1701.00705v1
PDF	http://arxiv.org/pdf/1701.00705v1.pdf
PWC	https://paperswithcode.com/paper/using-big-data-to-enhance-the-bosch
Repo
Framework