April 2, 2020

3194 words 15 mins read

Paper Group ANR 220

Retrospective Reader for Machine Reading Comprehension. Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing. Investigating Software Usage in the Social Sciences: A Knowledge Graph Approach. Is Aligning Embedding Spaces a Challenging Task? An Analysis of the Existing Methods. Assortment Optimization with Repeated Exposures …

Retrospective Reader for Machine Reading Comprehension


Title	Retrospective Reader for Machine Reading Comprehension
Authors	Zhuosheng Zhang, Junjie Yang, Hai Zhao
Abstract	Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. MRC systems must not only answer question when necessary but also distinguish when no answer is available according to the given passage and then tactfully abstain from answering. When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder, though the latest practice on MRC modeling still most benefits from adopting well pre-trained language models as the encoder block by only focusing on the “reading”. This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions. Inspired by how humans solve reading comprehension questions, we proposed a retrospective reader (Retro-Reader) that integrates two stages of reading and verification strategies: 1) sketchy reading that briefly investigates the overall interactions of passage and question, and yield an initial judgment; 2) intensive reading that verifies the answer and gives the final prediction. The proposed reader is evaluated on two benchmark MRC challenge datasets SQuAD2.0 and NewsQA, achieving new state-of-the-art results. Significance tests show that our model is significantly better than the strong ALBERT baseline. A series of analysis is also conducted to interpret the effectiveness of the proposed reader.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2020-01-27
URL	https://arxiv.org/abs/2001.09694v1
PDF	https://arxiv.org/pdf/2001.09694v1.pdf
PWC	https://paperswithcode.com/paper/retrospective-reader-for-machine-reading
Repo
Framework

Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing


Title	Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing
Authors	Xi Chen, Yining Wang
Abstract	Data-driven sequential decision has found a wide range of applications in modern operations management, such as dynamic pricing, inventory control, and assortment optimization. Most existing research on data-driven sequential decision focuses on designing an online policy to maximize the revenue. However, the research on uncertainty quantification on the underlying true model function (e.g., demand function), a critical problem for practitioners, has not been well explored. In this paper, using the problem of demand function prediction in dynamic pricing as the motivating example, we study the problem of constructing accurate confidence intervals for the demand function. The main challenge is that sequentially collected data leads to significant distributional bias in the maximum likelihood estimator or the empirical risk minimization estimate, making classical statistics approaches such as the Wald’s test no longer valid. We address this challenge by developing a debiased approach and provide the asymptotic normality guarantee of the debiased estimator. Based this the debiased estimator, we provide both point-wise and uniform confidence intervals of the demand function.
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07017v1
PDF	https://arxiv.org/pdf/2003.07017v1.pdf
PWC	https://paperswithcode.com/paper/uncertainty-quantification-for-demand
Repo
Framework


Title	Investigating Software Usage in the Social Sciences: A Knowledge Graph Approach
Authors	David Schindler, Benjamin Zapilko, Frank Krüger
Abstract	Knowledge about the software used in scientific investigations is necessary for different reasons, including provenance of the results, measuring software impact to attribute developers, and bibliometric software citation analysis in general. Additionally, providing information about whether and how the software and the source code are available allows an assessment about the state and role of open source software in science in general. While such analyses can be done manually, large scale analyses require the application of automated methods of information extraction and linking. In this paper, we present SoftwareKG - a knowledge graph that contains information about software mentions from more than 51,000 scientific articles from the social sciences. A silver standard corpus, created by a distant and weak supervision approach, and a gold standard corpus, created by manual annotation, were used to train an LSTM based neural network to identify software mentions in scientific articles. The model achieves a recognition rate of .82 F-score in exact matches. As a result, we identified more than 133,000 software mentions. For entity disambiguation, we used the public domain knowledge base DBpedia. Furthermore, we linked the entities of the knowledge graph to other knowledge bases such as the Microsoft Academic Knowledge Graph, the Software Ontology, and Wikidata. Finally, we illustrate, how SoftwareKG can be used to assess the role of software in the social sciences.
Tasks	Entity Disambiguation
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10715v1
PDF	https://arxiv.org/pdf/2003.10715v1.pdf
PWC	https://paperswithcode.com/paper/investigating-software-usage-in-the-social
Repo
Framework

Is Aligning Embedding Spaces a Challenging Task? An Analysis of the Existing Methods


Title	Is Aligning Embedding Spaces a Challenging Task? An Analysis of the Existing Methods
Authors	Russa Biswas, Mehwish Alam, Harald Sack
Abstract	Representation Learning of words and Knowledge Graphs (KG) into low dimensional vector spaces along with its applications to many real-world scenarios have recently gained momentum. In order to make use of multiple KG embeddings for knowledge-driven applications such as question answering, named entity disambiguation, knowledge graph completion, etc., alignment of different KG embedding spaces is necessary. In addition to multilinguality and domain-specific information, different KGs pose the problem of structural differences making the alignment of the KG embeddings more challenging. This paper provides a theoretical analysis and comparison of the state-of-the-art alignment methods between two embedding spaces representing entity-entity and entity-word. This paper also aims at assessing the capability and short-comings of the existing alignment methods on the pretext of different applications.
Tasks	Entity Disambiguation, Knowledge Graph Completion, Knowledge Graphs, Question Answering, Representation Learning
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09247v1
PDF	https://arxiv.org/pdf/2002.09247v1.pdf
PWC	https://paperswithcode.com/paper/is-aligning-embedding-spaces-a-challenging
Repo
Framework

Assortment Optimization with Repeated Exposures and Product-dependent Patience Cost


Title	Assortment Optimization with Repeated Exposures and Product-dependent Patience Cost
Authors	Shaojie Tang
Abstract	In this paper, we study the assortment optimization problem faced by many online retailers such as Amazon. We develop a \emph{cascade multinomial logit model}, based on the classic multinomial logit model, to capture the consumers’ purchasing behavior across multiple stages. Different from existing studies, our model allows for repeated exposures of a product, i.e., the same product can be displayed multiple times across different stages. In addition, each consumer has a \emph{patience budget} that is sampled from a known distribution and each product is associated with a \emph{patience cost}, which captures the cognitive efforts spent on browsing that product. Given an assortment of products, a consumer sequentially browses them stage by stage. After browsing all products in one stage, if the utility of a product exceeds the utility of the outside option, the consumer proceeds to purchase the product and leave the platform. Otherwise, if the patience cost of all products browsed up to that point is no larger than her patience budget, she continues to view the next stage. We propose an approximation solution to this problem.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05321v1
PDF	https://arxiv.org/pdf/2002.05321v1.pdf
PWC	https://paperswithcode.com/paper/assortment-optimization-with-repeated
Repo
Framework

Visual Storytelling via Predicting Anchor Word Embeddings in the Stories


Title	Visual Storytelling via Predicting Anchor Word Embeddings in the Stories
Authors	Bowen Zhang, Hexiang Hu, Fei Sha
Abstract	We propose a learning model for the task of visual storytelling. The main idea is to predict anchor word embeddings from the images and use the embeddings and the image features jointly to generate narrative sentences. We use the embeddings of randomly sampled nouns from the groundtruth stories as the target anchor word embeddings to learn the predictor. To narrate a sequence of images, we use the predicted anchor word embeddings and the image features as the joint input to a seq2seq model. As opposed to state-of-the-art methods, the proposed model is simple in design, easy to optimize, and attains the best results in most automatic evaluation metrics. In human evaluation, the method also outperforms competing methods.
Tasks	Visual Storytelling, Word Embeddings
Published	2020-01-13
URL	https://arxiv.org/abs/2001.04541v1
PDF	https://arxiv.org/pdf/2001.04541v1.pdf
PWC	https://paperswithcode.com/paper/visual-storytelling-via-predicting-anchor
Repo
Framework

Sensor-based Continuous Authentication of Smartphones’ Users Using Behavioral Biometrics: A Survey


Title	Sensor-based Continuous Authentication of Smartphones’ Users Using Behavioral Biometrics: A Survey
Authors	Mohammed Abuhamad, Ahmed Abusnaina, DaeHun Nyang, David Mohaisen
Abstract	Mobile devices and technologies have become increasingly popular, offering comparable storage and computational capabilities to desktop computers allowing users to store and interact with sensitive and private information. The security and protection of such personal information are becoming more and more important since mobile devices are vulnerable to unauthorized access or theft. User authentication is a task of paramount importance that grants access to legitimate users at the point-of-entry and continuously through the usage session. This task is made possible with today’s smartphones’ embedded sensors that enable continuous and implicit user authentication by capturing behavioral biometrics and traits. In this paper, we survey more than 140 recent behavioral biometric-based approaches for continuous user authentication, including motion-based methods (27 studies), gait-based methods (23 studies), keystroke dynamics-based methods (20 studies), touch gesture-based methods (29 studies), voice-based methods (16 studies), and multimodal-based methods (33 studies). The survey provides an overview of the current state-of-the-art approaches for continuous user authentication using behavioral biometrics captured by smartphones’ embedded sensors, including insights and open challenges for adoption, usability, and performance.
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08578v1
PDF	https://arxiv.org/pdf/2001.08578v1.pdf
PWC	https://paperswithcode.com/paper/sensor-based-continuous-authentication-of
Repo
Framework

AlphaNet: An Attention Guided Deep Network for Automatic Image Matting


Title	AlphaNet: An Attention Guided Deep Network for Automatic Image Matting
Authors	Rishab Sharma, Rahul Deora, Anirudha Vishvakarma
Abstract	In this paper, we propose an end to end solution for image matting i.e high-precision extraction of foreground objects from natural images. Image matting and background detection can be achieved easily through chroma keying in a studio setting when the background is either pure green or blue. Nonetheless, image matting in natural scenes with complex and uneven depth backgrounds remains a tedious task that requires human intervention. To achieve complete automatic foreground extraction in natural scenes, we propose a method that assimilates semantic segmentation and deep image matting processes into a single network to generate detailed semantic mattes for image composition task. The contribution of our proposed method is two-fold, firstly it can be interpreted as a fully automated semantic image matting method and secondly as a refinement of existing semantic segmentation models. We propose a novel model architecture as a combination of segmentation and matting that unifies the function of upsampling and downsampling operators with the notion of attention. As shown in our work, attention guided downsampling and upsampling can extract high-quality boundary details, unlike other normal downsampling and upsampling techniques. For achieving the same, we utilized an attention guided encoder-decoder framework which does unsupervised learning for generating an attention map adaptively from the data to serve and direct the upsampling and downsampling operators. We also construct a fashion e-commerce focused dataset with high-quality alpha mattes to facilitate the training and evaluation for image matting.
Tasks	Image Matting, Semantic Segmentation
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03613v1
PDF	https://arxiv.org/pdf/2003.03613v1.pdf
PWC	https://paperswithcode.com/paper/alphanet-an-attention-guided-deep-network-for
Repo
Framework

Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration


Title	Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration
Authors	Jian Kang, Danfeng Hong, Jialin Liu, Gerald Baier, Naoto Yokoya, Begüm Demir
Abstract	Interferometric phase restoration has been investigated for decades and most of the state-of-the-art methods have achieved promising performances for InSAR phase restoration. These methods generally follow the nonlocal filtering processing chain aiming at circumventing the staircase effect and preserving the details of phase variations. In this paper, we propose an alternative approach for InSAR phase restoration, i.e. Complex Convolutional Sparse Coding (ComCSC) and its gradient regularized version. To our best knowledge, this is the first time that we solve the InSAR phase restoration problem in a deconvolutional fashion. The proposed methods can not only suppress interferometric phase noise, but also avoid the staircase effect and preserve the details. Furthermore, they provide an insight of the elementary phase components for the interferometric phases. The experimental results on synthetic and realistic high- and medium-resolution datasets from TerraSAR-X StripMap and Sentinel-1 interferometric wide swath mode, respectively, show that our method outperforms those previous state-of-the-art methods based on nonlocal InSAR filters, particularly the state-of-the-art method: InSAR-BM3D. The source code of this paper will be made publicly available for reproducible research inside the community.
Tasks
Published	2020-03-06
URL	https://arxiv.org/abs/2003.03440v1
PDF	https://arxiv.org/pdf/2003.03440v1.pdf
PWC	https://paperswithcode.com/paper/learning-convolutional-sparse-coding-on
Repo
Framework


Title	Symplectic Geometric Methods for Matrix Differential Equations Arising from Inertial Navigation Problems
Authors	Xin-Long Luo, Geng Sun
Abstract	This article explores some geometric and algebraic properties of the dynamical system which is represented by matrix differential equations arising from inertial navigation problems, such as the symplecticity and the orthogonality. Furthermore, it extends the applicable fields of symplectic geometric algorithms from the even dimensional Hamiltonian system to the odd dimensional dynamical system. Finally, some numerical experiments are presented and illustrate the theoretical results of this paper.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04315v1
PDF	https://arxiv.org/pdf/2002.04315v1.pdf
PWC	https://paperswithcode.com/paper/symplectic-geometric-methods-for-matrix
Repo
Framework

SPA: Verbal Interactions between Agents and Avatars in Shared Virtual Environments using Propositional Planning


Title	SPA: Verbal Interactions between Agents and Avatars in Shared Virtual Environments using Propositional Planning
Authors	Andrew Best, Sahil Narang, Dinesh Manocha
Abstract	We present a novel approach for generating plausible verbal interactions between virtual human-like agents and user avatars in shared virtual environments. Sense-Plan-Ask, or SPA, extends prior work in propositional planning and natural language processing to enable agents to plan with uncertain information, and leverage question and answer dialogue with other agents and avatars to obtain the needed information and complete their goals. The agents are additionally able to respond to questions from the avatars and other agents using natural-language enabling real-time multi-agent multi-avatar communication environments. Our algorithm can simulate tens of virtual agents at interactive rates interacting, moving, communicating, planning, and replanning. We find that our algorithm creates a small runtime cost and enables agents to complete their goals more effectively than agents without the ability to leverage natural-language communication. We demonstrate quantitative results on a set of simulated benchmarks and detail the results of a preliminary user-study conducted to evaluate the plausibility of the virtual interactions generated by SPA. Overall, we find that participants prefer SPA to prior techniques in 84% of responses including significant benefits in terms of the plausibility of natural-language interactions and the positive impact of those interactions.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03246v1
PDF	https://arxiv.org/pdf/2002.03246v1.pdf
PWC	https://paperswithcode.com/paper/spa-verbal-interactions-between-agents-and
Repo
Framework

Hyperspectral-Multispectral Image Fusion with Weighted LASSO


Title	Hyperspectral-Multispectral Image Fusion with Weighted LASSO
Authors	Nguyen Tran, Rupali Mankar, David Mayerich, Zhu Han
Abstract	Spectral imaging enables spatially-resolved identification of materials in remote sensing, biomedicine, and astronomy. However, acquisition times require balancing spectral and spatial resolution with signal-to-noise. Hyperspectral imaging provides superior material specificity, while multispectral images are faster to collect at greater fidelity. We propose an approach for fusing hyperspectral and multispectral images to provide high-quality hyperspectral output. The proposed optimization leverages the least absolute shrinkage and selection operator (LASSO) to perform variable selection and regularization. Computational time is reduced by applying the alternating direction method of multipliers (ADMM), as well as initializing the fusion image by estimating it using maximum a posteriori (MAP) based on Hardie’s method. We demonstrate that the proposed sparse fusion and reconstruction provides quantitatively superior results when compared to existing methods on publicly available images. Finally, we show how the proposed method can be practically applied in biomedical infrared spectroscopic microscopy.
Tasks
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06944v1
PDF	https://arxiv.org/pdf/2003.06944v1.pdf
PWC	https://paperswithcode.com/paper/hyperspectral-multispectral-image-fusion-with
Repo
Framework

Unsupervised machine learning of quantum phase transitions using diffusion maps


Title	Unsupervised machine learning of quantum phase transitions using diffusion maps
Authors	Alexander Lidiak, Zhexuan Gong
Abstract	Experimental quantum simulators have become large and complex enough that discovering new physics from the huge amount of measurement data can be quite challenging, especially when little theoretical understanding of the simulated model is available. Unsupervised machine learning methods are particularly promising in overcoming this challenge. For the specific task of learning quantum phase transitions, unsupervised machine learning methods have primarily been developed for phase transitions characterized by simple order parameters, typically linear in the measured observables. However, such methods often fail for more complicated phase transitions, such as those involving incommensurate phases, valence-bond solids, topological order, and many-body localization. We show that the diffusion map method, which performs nonlinear dimensionality reduction and spectral clustering of the measurement data, has significant potential for learning such complex phase transitions unsupervised. This method works for measurements of local observables in a single basis and is thus readily applicable to many experimental quantum simulators as a versatile tool for learning various quantum phases and phase transitions.
Tasks	Dimensionality Reduction
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07399v1
PDF	https://arxiv.org/pdf/2003.07399v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-machine-learning-of-quantum
Repo
Framework

Generative Multi-Stream Architecture For American Sign Language Recognition


Title	Generative Multi-Stream Architecture For American Sign Language Recognition
Authors	Dom Huh, Sai Gurrapu, Frederick Olson, Huzefa Rangwala, Parth Pathak, Jana Kosecka
Abstract	With advancements in deep model architectures, tasks in computer vision can reach optimal convergence provided proper data preprocessing and model parameter initialization. However, training on datasets with low feature-richness for complex applications limit and detriment optimal convergence below human performance. In past works, researchers have provided external sources of complementary data at the cost of supplementary hardware, which are fed in streams to counteract this limitation and boost performance. We propose a generative multi-stream architecture, eliminating the need for additional hardware with the intent to improve feature richness without risking impracticability. We also introduce the compact spatio-temporal residual block to the standard 3-dimensional convolutional model, C3D. Our rC3D model performs comparatively to the top C3D residual variant architecture, the pseudo-3D model, on the FASL-RGB dataset. Our methods have achieved 95.62% validation accuracy with a variance of 1.42% from training, outperforming past models by 0.45% in validation accuracy and 5.53% in variance.
Tasks	Sign Language Recognition
Published	2020-03-09
URL	https://arxiv.org/abs/2003.08743v1
PDF	https://arxiv.org/pdf/2003.08743v1.pdf
PWC	https://paperswithcode.com/paper/generative-multi-stream-architecture-for
Repo
Framework

Estimation of Orofacial Kinematics in Parkinson’s Disease: Comparison of 2D and 3D Markerless Systems for Motion Tracking


Title	Estimation of Orofacial Kinematics in Parkinson’s Disease: Comparison of 2D and 3D Markerless Systems for Motion Tracking
Authors	Diego L. Guarin, Aidan Dempster, Andrea Bandini, Yana Yunusova, Babak Taati
Abstract	Orofacial deficits are common in people with Parkinson’s disease (PD) and their evolution might represent an important biomarker of disease progression. We are developing an automated system for assessment of orofacial function in PD that can be used in-home or in-clinic and can provide useful and objective clinical information that informs disease management. Our current approach relies on color and depth cameras for the estimation of 3D facial movements. However, depth cameras are not commonly available, might be expensive, and require specialized software for control and data processing. The objective of this paper was to evaluate if depth cameras are needed to differentiate between healthy controls and PD patients based on features extracted from orofacial kinematics. Results indicate that 2D features, extracted from color cameras only, are as informative as 3D features, extracted from color and depth cameras, differentiating healthy controls from PD patients. These results pave the way for the development of a universal system for automatic and objective assessment of orofacial function in PD.
Tasks
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08048v1
PDF	https://arxiv.org/pdf/2003.08048v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-orofacial-kinematics-in
Repo
Framework