October 18, 2019

2820 words 14 mins read

Paper Group ANR 642

Experiments with Neural Networks for Small and Large Scale Authorship Verification. Rapid seismic domain transfer: Seismic velocity inversion and modeling using deep generative neural networks. Rapid Customization for Event Extraction. Adaptive Re-ranking of Deep Feature for Person Re-identification. Pronoun Translation in English-French Machine Tr …

Experiments with Neural Networks for Small and Large Scale Authorship Verification


Title	Experiments with Neural Networks for Small and Large Scale Authorship Verification
Authors	Marjan Hosseinia, Arjun Mukherjee
Abstract	We propose two models for a special case of authorship verification problem. The task is to investigate whether the two documents of a given pair are written by the same author. We consider the authorship verification problem for both small and large scale datasets. The underlying small-scale problem has two main challenges: First, the authors of the documents are unknown to us because no previous writing samples are available. Second, the two documents are short (a few hundred to a few thousand words) and may differ considerably in the genre and/or topic. To solve it we propose transformation encoder to transform one document of the pair into the other. This document transformation generates a loss which is used as a recognizable feature to verify if the authors of the pair are identical. For the large scale problem where various authors are engaged and more examples are available with larger length, a parallel recurrent neural network is proposed. It compares the language models of the two documents. We evaluate our methods on various types of datasets including Authorship Identification datasets of PAN competition, Amazon reviews, and machine learning articles. Experiments show that both methods achieve stable and competitive performance compared to the baselines.
Tasks
Published	2018-03-17
URL	http://arxiv.org/abs/1803.06456v1
PDF	http://arxiv.org/pdf/1803.06456v1.pdf
PWC	https://paperswithcode.com/paper/experiments-with-neural-networks-for-small
Repo
Framework

Rapid seismic domain transfer: Seismic velocity inversion and modeling using deep generative neural networks


Title	Rapid seismic domain transfer: Seismic velocity inversion and modeling using deep generative neural networks
Authors	Lukas Mosser, Wouter Kimman, Jesper Dramsch, Steve Purves, Alfredo De la Fuente, Graham Ganssle
Abstract	Traditional physics-based approaches to infer sub-surface properties such as full-waveform inversion or reflectivity inversion are time-consuming and computationally expensive. We present a deep-learning technique that eliminates the need for these computationally complex methods by posing the problem as one of domain transfer. Our solution is based on a deep convolutional generative adversarial network and dramatically reduces computation time. Training based on two different types of synthetic data produced a neural network that generates realistic velocity models when applied to a real dataset. The system’s ability to generalize means it is robust against the inherent occurrence of velocity errors and artifacts in both training and test datasets.
Tasks
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08826v1
PDF	http://arxiv.org/pdf/1805.08826v1.pdf
PWC	https://paperswithcode.com/paper/rapid-seismic-domain-transfer-seismic
Repo
Framework

Rapid Customization for Event Extraction


Title	Rapid Customization for Event Extraction
Authors	Yee Seng Chan, Joshua Fasching, Haoling Qiu, Bonan Min
Abstract	We present a system for rapidly customizing event extraction capability to find new event types and their arguments. The system allows a user to find, expand and filter event triggers for a new event type by exploring an unannotated corpus. The system will then automatically generate mention-level event annotation automatically, and train a Neural Network model for finding the corresponding event. Additionally, the system uses the ACE corpus to train an argument model for extracting Actor, Place, and Time arguments for any event types, including ones not seen in its training data. Experiments show that with less than 10 minutes of human effort per event type, the system achieves good performance for 67 novel event types. The code, documentation, and a demonstration video will be released as open source on github.com.
Tasks
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07783v1
PDF	http://arxiv.org/pdf/1809.07783v1.pdf
PWC	https://paperswithcode.com/paper/rapid-customization-for-event-extraction
Repo
Framework

Adaptive Re-ranking of Deep Feature for Person Re-identification


Title	Adaptive Re-ranking of Deep Feature for Person Re-identification
Authors	Yong Liu, Lin Shang, Andy Song
Abstract	Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep feature to boost the re-ID performance. First, we propose a Deep Feature Fusion (DFF) method to exploit the diverse information embedded in a deep feature. DFF treats each sub-feature as an information carrier and employs a diffusion process to exchange their information. Second, we propose an Adaptive Re-Ranking (ARR) method to exploit the contextual information encoded in the features of neighbors. ARR utilizes the contextual information to re-rank the retrieval results in an iterative manner. Particularly, it adds more contextual information after each iteration automatically to consider more matches. Third, we propose a strategy that combines DFF and ARR to enhance the performance. Extensive comparative evaluations demonstrate the superiority of the proposed methods on three large benchmarks.
Tasks	Person Re-Identification
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08561v1
PDF	http://arxiv.org/pdf/1811.08561v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-re-ranking-of-deep-feature-for
Repo
Framework

Pronoun Translation in English-French Machine Translation: An Analysis of Error Types


Title	Pronoun Translation in English-French Machine Translation: An Analysis of Error Types
Authors	Christian Hardmeier, Liane Guillou
Abstract	Pronouns are a long-standing challenge in machine translation. We present a study of the performance of a range of rule-based, statistical and neural MT systems on pronoun translation based on an extensive manual evaluation using the PROTEST test suite, which enables a fine-grained analysis of different pronoun types and sheds light on the difficulties of the task. We find that the rule-based approaches in our corpus perform poorly as a result of oversimplification, whereas SMT and early NMT systems exhibit significant shortcomings due to a lack of awareness of the functional and referential properties of pronouns. A recent Transformer-based NMT system with cross-sentence context shows very promising results on non-anaphoric pronouns and intra-sentential anaphora, but there is still considerable room for improvement in examples with cross-sentence dependencies.
Tasks	Machine Translation
Published	2018-08-30
URL	http://arxiv.org/abs/1808.10196v1
PDF	http://arxiv.org/pdf/1808.10196v1.pdf
PWC	https://paperswithcode.com/paper/pronoun-translation-in-english-french-machine
Repo
Framework

Deep Learning with Convolutional Neural Network for Objective Skill Evaluation in Robot-assisted Surgery


Title	Deep Learning with Convolutional Neural Network for Objective Skill Evaluation in Robot-assisted Surgery
Authors	Ziheng Wang, Ann Majewicz Fey
Abstract	With the advent of robot-assisted surgery, the role of data-driven approaches to integrate statistics and machine learning is growing rapidly with prominent interests in objective surgical skill assessment. However, most existing work requires translating robot motion kinematics into intermediate features or gesture segments that are expensive to extract, lack efficiency, and require significant domain-specific knowledge. We propose an analytical deep learning framework for skill assessment in surgical training. A deep convolutional neural network is implemented to map multivariate time series data of the motion kinematics to individual skill levels. We perform experiments on the public minimally invasive surgical robotic dataset, JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS). Our proposed learning model achieved a competitive accuracy of 92.5%, 95.4%, and 91.3%, in the standard training tasks: Suturing, Needle-passing, and Knot-tying, respectively. Without the need of engineered features or carefully-tuned gesture segmentation, our model can successfully decode skill information from raw motion profiles via end-to-end learning. Meanwhile, the proposed model is able to reliably interpret skills within 1-3 second window, without needing an observation of entire training trial. This study highlights the potentials of deep architectures for an proficient online skill assessment in modern surgical training.
Tasks	Time Series
Published	2018-06-15
URL	http://arxiv.org/abs/1806.05796v2
PDF	http://arxiv.org/pdf/1806.05796v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-with-convolutional-neural-2
Repo
Framework

UOLO - automatic object detection and segmentation in biomedical images


Title	UOLO - automatic object detection and segmentation in biomedical images
Authors	Teresa Araújo, Guilherme Aresta, Adrian Galdran, Pedro Costa, Ana Maria Mendonça, Aurélio Campilho
Abstract	We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneously for detecting a class of objects and segmenting an optionally different class of structures. UOLO is trained on a set of bounding boxes enclosing the objects to detect, as well as pixel-wise segmentation information, when available. A new loss function is devised, taking into account whether a reference segmentation is accessible for each training image, in order to suitably backpropagate the error. We validate UOLO on the task of simultaneous optic disc (OD) detection, fovea detection, and OD segmentation from retinal images, achieving state-of-the-art performance on public datasets.
Tasks	Medical Image Segmentation, Object Detection, Semantic Segmentation
Published	2018-10-09
URL	http://arxiv.org/abs/1810.05729v1
PDF	http://arxiv.org/pdf/1810.05729v1.pdf
PWC	https://paperswithcode.com/paper/uolo-automatic-object-detection-and
Repo
Framework

Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification


Title	Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification
Authors	Marc Combalia, Veronica Vilaplana
Abstract	We propose a patch sampling strategy based on a sequential Monte-Carlo method for high resolution image classification in the context of Multiple Instance Learning. When compared with grid sampling and uniform sampling techniques, it achieves higher generalization performance. We validate the strategy on two artificial datasets and two histological datasets for breast cancer and sun exposure classification.
Tasks	Image Classification, Multiple Instance Learning
Published	2018-12-30
URL	http://arxiv.org/abs/1812.11560v1
PDF	http://arxiv.org/pdf/1812.11560v1.pdf
PWC	https://paperswithcode.com/paper/monte-carlo-sampling-applied-to-multiple
Repo
Framework

Modified Causal Forests for Estimating Heterogeneous Causal Effects


Title	Modified Causal Forests for Estimating Heterogeneous Causal Effects
Authors	Michael Lechner
Abstract	Uncovering the heterogeneity of causal effects of policies and business decisions at various levels of granularity provides substantial value to decision makers. This paper develops new estimation and inference procedures for multiple treatment models in a selection-on-observables framework by modifying the Causal Forest approach suggested by Wager and Athey (2018) in several dimensions. The new estimators have desirable theoretical, computational and practical properties for various aggregation levels of the causal effects. While an Empirical Monte Carlo study suggests that they outperform previously suggested estimators, an application to the evaluation of an active labour market programme shows the value of the new methods for applied research.
Tasks
Published	2018-12-22
URL	https://arxiv.org/abs/1812.09487v2
PDF	https://arxiv.org/pdf/1812.09487v2.pdf
PWC	https://paperswithcode.com/paper/modified-causal-forests-for-estimating
Repo
Framework

A Multi-Axis Annotation Scheme for Event Temporal Relations


Title	A Multi-Axis Annotation Scheme for Event Temporal Relations
Authors	Qiang Ning, Hao Wu, Dan Roth
Abstract	Existing temporal relation (TempRel) annotation schemes often have low inter-annotator agreements (IAA) even between experts, suggesting that the current annotation task needs a better definition. This paper proposes a new multi-axis modeling to better capture the temporal structure of events. In addition, we identify that event end-points are a major source of confusion in annotation, so we also propose to annotate TempRels based on start-points only. A pilot expert annotation using the proposed scheme shows significant improvement in IAA from the conventional 60’s to 80’s (Cohen’s Kappa). This better-defined annotation scheme further enables the use of crowdsourcing to alleviate the labor intensity for each annotator. We hope that this work can foster more interesting studies towards event understanding.
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07828v2
PDF	http://arxiv.org/pdf/1804.07828v2.pdf
PWC	https://paperswithcode.com/paper/a-multi-axis-annotation-scheme-for-event
Repo
Framework

Attacking Convolutional Neural Network using Differential Evolution


Title	Attacking Convolutional Neural Network using Differential Evolution
Authors	Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai
Abstract	The output of Convolutional Neural Networks (CNN) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbations. That is, images modified by adding such perturbations(i.e. adversarial perturbations) that make little difference to human eyes, can completely alter the CNN classification results. In this paper, we propose a practical attack using differential evolution(DE) for generating effective adversarial perturbations. We comprehensively evaluate the effectiveness of different types of DEs for conducting the attack on different network structures. The proposed method is a black-box attack which only requires the miracle feedback of the target CNN systems. The results show that under strict constraints which simultaneously control the number of pixels changed and overall perturbation strength, attacking can achieve 72.29%, 78.24% and 61.28% non-targeted attack success rates, with 88.68%, 99.85% and 73.07% confidence on average, on three common types of CNNs. The attack only requires modifying 5 pixels with 20.44, 14.76 and 22.98 pixel values distortion. Thus, the result shows that the current DNNs are also vulnerable to such simpler black-box attacks even under very limited attack conditions.
Tasks
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07062v1
PDF	http://arxiv.org/pdf/1804.07062v1.pdf
PWC	https://paperswithcode.com/paper/attacking-convolutional-neural-network-using
Repo
Framework

Knowledge Discovery from Layered Neural Networks based on Non-negative Task Decomposition


Title	Knowledge Discovery from Layered Neural Networks based on Non-negative Task Decomposition
Authors	Chihiro Watanabe, Kaoru Hiramatsu, Kunio Kashino
Abstract	Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship between large number of parameters, we failed to understand how they could achieve input-output mappings with a given data set. In this paper, we propose the non-negative task decomposition method, which applies non-negative matrix factorization to a trained layered neural network. This enables us to decompose the inference mechanism of a trained layered neural network into multiple principal tasks of input-output mapping, and reveal the roles of hidden units in terms of their contribution to each principal task.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07137v2
PDF	http://arxiv.org/pdf/1805.07137v2.pdf
PWC	https://paperswithcode.com/paper/knowledge-discovery-from-layered-neural
Repo
Framework

FRnet-DTI: Deep Convolutional Neural Networks with Evolutionary and Structural Features for Drug-Target Interaction


Title	FRnet-DTI: Deep Convolutional Neural Networks with Evolutionary and Structural Features for Drug-Target Interaction
Authors	Farshid Rayhan, Sajid Ahmed, Zaynab Mousavian, Dewan Md Farid, Swakkhar Shatabda
Abstract	The task of drug-target interaction prediction holds significant importance in pharmacology and therapeutic drug design. In this paper, we present FRnet-DTI, an auto encoder and a convolutional classifier for feature manipulation and drug target interaction prediction. Two convolutional neural neworks are proposed where one model is used for feature manipulation and the other one for classification. Using the first method FRnet-1, we generate 4096 features for each of the instances in each of the datasets and use the second method, FRnet-2, to identify interaction probability employing those features. We have tested our method on four gold standard datasets exhaustively used by other researchers. Experimental results shows that our method significantly improves over the state-of-the-art method on three of the four drug-target interaction gold standard datasets on both area under curve for Receiver Operating Characteristic(auROC) and area under Precision Recall curve(auPR) metric. We also introduce twenty new potential drug-target pairs for interaction based on high prediction scores. Codes Available: https: // github. com/ farshidrayhanuiu/ FRnet-DTI/ Web Implementation: http: // farshidrayhan. pythonanywhere. com/ FRnet-DTI/
Tasks
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07174v3
PDF	http://arxiv.org/pdf/1806.07174v3.pdf
PWC	https://paperswithcode.com/paper/frnet-dti-deep-convolutional-neural-networks
Repo
Framework

OmicsMapNet: Transforming omics data to take advantage of Deep Convolutional Neural Network for discovery


Title	OmicsMapNet: Transforming omics data to take advantage of Deep Convolutional Neural Network for discovery
Authors	Shiyong Ma, Zhen Zhang
Abstract	We developed OmicsMapNet approach to take advantage of existing deep leaning frameworks to analyze high-dimensional omics data as 2-dimensional images. The omics data of individual samples were first rearranged into 2D images in which molecular features related in functions, ontologies, or other relationships were organized in spatially adjacent and patterned locations. Deep learning neural networks were trained to classify the images. Molecular features informative of classes of different phenotypes were subsequently identified. As an example, we used the KEGG BRITE database to rearrange RNA-Seq expression data of TCGA diffuse glioma samples as treemaps to capture the functional hierarchical structure of genes in 2D images. Deep Convolutional Neural Networks (CNN) were derived using tools from TensorFlow to learn the grade of TCGA LGG and GBM samples with relatively high accuracy. The most contributory features in the trained CNN were confirmed in pathway analysis for their plausible functional involvement.
Tasks
Published	2018-04-14
URL	https://arxiv.org/abs/1804.05283v2
PDF	https://arxiv.org/pdf/1804.05283v2.pdf
PWC	https://paperswithcode.com/paper/omicsmapnet-transforming-omics-data-to-take
Repo
Framework

A Recurrent Neural Network Survival Model: Predicting Web User Return Time


Title	A Recurrent Neural Network Survival Model: Predicting Web User Return Time
Authors	Georg L. Grob, Ângelo Cardoso, C. H. Bryan Liu, Duncan A. Little, Benjamin Paul Chamberlain
Abstract	The size of a website’s active user base directly affects its value. Thus, it is important to monitor and influence a user’s likelihood to return to a site. Essential to this is predicting when a user will return. Current state of the art approaches to solve this problem come in two flavors: (1) Recurrent Neural Network (RNN) based solutions and (2) survival analysis methods. We observe that both techniques are severely limited when applied to this problem. Survival models can only incorporate aggregate representations of users instead of automatically learning a representation directly from a raw time series of user actions. RNNs can automatically learn features, but can not be directly trained with examples of non-returning users who have no target value for their return time. We develop a novel RNN survival model that removes the limitations of the state of the art methods. We demonstrate that this model can successfully be applied to return time prediction on a large e-commerce dataset with a superior ability to discriminate between returning and non-returning users than either method applied in isolation.
Tasks	Survival Analysis, Time Series
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04098v1
PDF	http://arxiv.org/pdf/1807.04098v1.pdf
PWC	https://paperswithcode.com/paper/a-recurrent-neural-network-survival-model
Repo
Framework