Results for "Shafiq Joty"

total 54took 0.07s
Joint Multitask Learning for Community Question Answering Using Task-Specific EmbeddingsSep 24 2018We address jointly two important tasks for Question Answering in community forums: given a new question, (i) find related existing questions, and (ii) find relevant answers to this new question. We further use an auxiliary task to complement the previous ... More
Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid ApproachMay 06 2018We propose a novel coherence model for written asynchronous conversations (e.g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks. We conduct our research in two steps. First, we propose improvements to ... More
VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual QuestionsMar 20 2018Aug 25 2018Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with ... More
Discourse Structure in Machine Translation EvaluationOct 04 2017In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance ... More
Adversarial Unsupervised Representation Learning for Activity Time-SeriesNov 14 2018Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions. Being able to proactively screen and monitor such chronic conditions would be a big step forward for overall health. The rapid increase ... More
Unpaired Image Captioning by Language PivotingMar 14 2018Jul 18 2018Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description. In general, the mapping function is learned from a training set of ... More
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative ModelsNov 17 2017Jun 13 2018Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike ... More
A Unified Linear-Time Framework for Sentence-Level Discourse ParsingMay 14 2019We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse segmenter to identify the elementary discourse units (EDU) in a text, and a discourse ... More
Unpaired Image Captioning via Scene Graph AlignmentsMar 26 2019Deep neural networks have achieved great success on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire in most real-world scenarios. In this paper, we propose ... More
NEURON: Query Optimization Meets Natural Language Processing For Augmenting Database EducationMay 15 2018Aug 21 2018Relational database management system (RDBMS) is a major undergraduate course taught in many universities worldwide as part of their computer science program. A core component of such course is the design and implementation of the query optimizer in a ... More
Applications of Online Deep Learning for Crisis Response Using Social Media InformationOct 04 2016Oct 05 2016During natural or man-made disasters, humanitarian response organizations look for useful information to support their decision-making processes. Social media platforms such as Twitter have been considered as a vital source of useful information for disaster ... More
Unpaired Image Captioning via Scene Graph AlignmentsMar 26 2019Apr 04 2019Most of the existing deep learning based image captioning methods are fully-supervised models, which require large-scale paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this ... More
Thread Reconstruction in Conversational Data using Neural Coherence ModelsJul 24 2017Jul 25 2017Discussion forums are an important source of information. They are often used to answer specific questions a user might have and to discover more about a topic of interest. Discussions in these forums may evolve in intricate ways, making it difficult ... More
Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural NetworksAug 12 2016The role of social media, in particular microblogging platforms such as Twitter, as a conduit for actionable and tactical information during disasters is increasingly acknowledged. However, time-critical analysis of big crisis data on social media streams ... More
Cross-Language Question Re-RankingOct 04 2017We study how to find relevant questions in community forums when the language of the new questions is different from that of the existing questions in the forum. In particular, we explore the Arabic-English language pair. We compare a kernel-based system ... More
Phrase-Based AttentionsSep 30 2018Most state-of-the-art neural machine translation systems, despite being different in architectural skeletons (e.g. recurrence, convolutional), share an indispensable feature: the Attention. However, most existing attention methods are token-based and ... More
Addressing Community Question Answering in English and ArabicOct 18 2016This paper studies the impact of different types of features applied to learning to re-rank questions in community Question Answering. We tested our models on two datasets released in SemEval-2016 Task 3 on "Community Question Answering". Task 3 targeted ... More
Domain Adaptation with Adversarial Training and Graph EmbeddingsMay 14 2018The success of deep neural networks (DNNs) is heavily dependent on the availability of labeled data. However, obtaining labeled data is a big challenge in many real-world problems. In such scenarios, a DNN model can leverage labeled and unlabeled data ... More
Graph Based Semi-supervised Learning with Convolution Neural Networks to Classify Crisis Related TweetsMay 02 2018During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts. However, the scarcity ... More
Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video PredictionJul 08 2018The explosion of video data on the internet requires effective and efficient technology to generate captions automatically for people who are not able to watch the videos. Despite the great progress of video captioning research, particularly on video ... More
Machine Translation Evaluation with Neural NetworksOct 05 2017We present a framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic ... More
Complex Question Answering: Unsupervised Learning Approaches and ExperimentsJan 15 2014Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topic-oriented, informative multi-document summarization where the goal is to produce a single text as a compressed version of a set ... More
DeepER -- Deep Entity ResolutionOct 02 2017Aug 05 2018Entity resolution (ER) is a key data integration problem. Despite the efforts in 70+ years in all aspects of ER, there is still a high demand for democratizing ER - humans are heavily involved in labeling data, performing feature engineering, tuning parameters, ... More
Topic Segmentation and Labeling in Asynchronous ConversationsFeb 04 2014Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications. We present two new corpora of email and blog conversations ... More
Dis-S2V: Discourse Informed Sen2VecOct 25 2016Vector representation of sentences is important for many text processing tasks that involve clustering, classifying, or ranking sentences. Recently, distributed representation of sentences learned by neural models from unlabeled data has been shown to ... More
Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task LearningDec 27 2017Physical activity and sleep play a major role in the prevention and management of many chronic conditions. It is not a trivial task to understand their impact on chronic conditions. Currently, data from electronic health records (EHRs), sleep lab studies, ... More
Reuse and Adaptation for Entity Resolution through Transfer LearningSep 28 2018Entity resolution (ER) is one of the fundamental problems in data integration, where machine learning (ML) based classifiers often provide the state-of-the-art results. Considerable human effort goes into feature engineering and training data creation. ... More
Models for Capturing Temporal Smoothness in Evolving Networks for Learning Latent Representation of NodesApr 16 2018In a dynamic network, the neighborhood of the vertices evolve across different temporal snapshots of the network. Accurate modeling of this temporal evolution can help solve complex tasks involving real-life social and interaction networks. However, existing ... More
A Structured Learning Approach with Neural Conditional Random Fields for Sleep StagingJul 23 2018Oct 28 2018Sleep plays a vital role in human health, both mental and physical. Sleep disorders like sleep apnea are increasing in prevalence, with the rapid increase in factors like obesity. Sleep apnea is most commonly treated with Continuous Positive Air Pressure ... More
A note on a characterization theorem for a certain class of domainsOct 02 2016We have introduced and studied in [3] the class of Globalized multiplicatively pinched-Dedekind domains (GMPD domains). This class of domains could be characterized by a certain factorization property of the non-invertible ideals, (see [3, Theorem 4]). ... More
Impact of Physical Activity on Sleep:A Deep Learning Based ExplorationJul 24 2016The importance of sleep is paramount for maintaining physical, emotional and mental wellbeing. Though the relationship between sleep and physical activity is known to be important, it is not yet fully understood. The explosion in popularity of actigraphy ... More
Analyzing Adversarial Attacks Against Deep Learning for Intrusion Detection in IoT NetworksMay 13 2019Adversarial attacks have been widely studied in the field of computer vision but their impact on network security applications remains an area of open research. As IoT, 5G and AI continue to converge to realize the promise of the fourth industrial revolution ... More
Modeling Morphology of Social Network CascadesFeb 10 2013Cascades represent an important phenomenon across various disciplines such as sociology, economy, psychology, political science, marketing, and epidemiology. An important property of cascades is their morphology, which encompasses the structure, shape, ... More
On a certain class of integral domains with finitely many overringsNov 24 2018An integral domain is called {\em Globalized multiplicatively pinched-Dedekind domain $($GMPD domain$)$} if every nonzero noninvertible ideal can be written as $JP_1\cdots P_k$ with $J$ invertible ideal and $P_1,...,P_k$ distinct ideals which are maximal ... More
On a certain class of integral domains with finitely many overringsNov 24 2018May 05 2019An integral domain is called {\em Globalized multiplicatively pinched-Dedekind domain $($GMPD domain$)$} if every nonzero noninvertible ideal can be written as $JP_1\cdots P_k$ with $J$ invertible ideal and $P_1,...,P_k$ distinct ideals which are maximal ... More
Disparity-Augmented Trajectories for Human Activity RecognitionMay 14 2019Numerous methods for human activity recognition have been proposed in the past two decades. Many of these methods are based on sparse representation, which describes the whole video content by a set of local features. Trajectories, being mid-level sparse ... More
Saliency detection for seismic applications using multi-dimensional spectral projections and directional comparisonsJan 30 2019In this paper, we propose a novel approach for saliency detection for seismic applications using 3D-FFT local spectra and multi-dimensional plane projections. We develop a projection scheme by dividing a 3D-FFT local spectrum of a data volume into three ... More
The role of visual saliency in the automation of seismic interpretationDec 31 2018In this paper, we propose a workflow based on SalSi for the detection and delineation of geological structures such as salt domes. SalSi is a seismic attribute designed based on the modeling of human visual system that detects the salient features and ... More
SalSi: A new seismic attribute for salt dome detectionJan 09 2019In this paper, we propose a saliency-based attribute, SalSi, to detect salt dome bodies within seismic volumes. SalSi is based on the saliency theory and modeling of the human vision system (HVS). In this work, we aim to highlight the parts of the seismic ... More
Automated flow for compressing convolution neural networks for efficient edge-computation with FPGADec 18 2017Deep convolutional neural networks (CNN) based solutions are the current state- of-the-art for computer vision tasks. Due to the large size of these models, they are typically run on clusters of CPUs or GPUs. However, power requirements and cost budgets ... More
On Topological Properties of Third type of Hex Derived NetworksApr 24 2019In chemical graph theory, a topological index is a numerical representation of a chemical network while a topological descriptor correlates certain physico-chemical characteristics of underlying chemical compounds besides its chemical representation. ... More
Subsurface structure analysis using computational interpretation and learning: A visual signal processing perspectiveDec 20 2018Understanding Earth's subsurface structures has been and continues to be an essential component of various applications such as environmental monitoring, carbon sequestration, and oil and gas exploration. By viewing the seismic volumes that are generated ... More
Preprint Touch-less Interactive Augmented Reality Game on Vision Based Wearable DeviceApr 23 2015Sep 07 2015This is the preprint version of our paper on Personal and Ubiquitous Computing. There is an increasing interest in creating pervasive games based on emerging interaction technologies. In order to develop touch-less, interactive and augmented reality games ... More
Order divisor graphs of finite groupsNov 14 2016Jul 22 2017The interplay between groups and graphs have been the most famous and productive area of algebraic graph theory. In this paper, we introduce and study the graphs whose vertex set is group G such that two distinct vertices a and b having different orders ... More
A First Look at Ad-block Detection: A New Arms Race on the WebMay 19 2016The rise of ad-blockers is viewed as an economic threat by online publishers, especially those who primarily rely on ad- vertising to support their services. To address this threat, publishers have started retaliating by employing ad-block detectors, ... More
Paying for Likes? Understanding Facebook Like Fraud Using HoneypotsSep 07 2014Oct 04 2014Facebook pages offer an easy way to reach out to a very large audience as they can easily be promoted using Facebook's advertising platform. Recently, the number of likes of a Facebook page has become a measure of its popularity and profitability, and ... More
Order divisor graphs of finite groupsNov 14 2016The interplay between groups and graphs have been the most famous and productive area of algebraic graph theory. In this paper, we introduce and study the graphs whose vertex set is group G such that two distinct vertices a and b having different orders ... More
AdGraph: A Machine Learning Approach to Automatic and Effective AdblockingMay 22 2018Filter lists are widely deployed by adblockers to block ads and other forms of undesirable content in web browsers. However, these filter lists are manually curated based on informal crowdsourced feedback, which brings with it a significant number of ... More
Structural band-gap tuning in g-C$_3$N$_4$Dec 10 2014g-C$_3$N$_4$ is a promising material for hydrogen production from water via photo-catalysis, if we can tune its band gap to desirable levels. Using a combined experimental and ab initio approach, we uncover an almost perfectly linear relationship between ... More
Characterizing Key Stakeholders in an Online Black-Hat MarketplaceMay 07 2015Apr 04 2017Over the past few years, many black-hat marketplaces have emerged that facilitate access to reputation manipulation services such as fake Facebook likes, fraudulent search engine optimization (SEO), or bogus Amazon reviews. In order to deploy effective ... More
Potential of a moving test charge in a dusty plasma in the presence of grain size distribution and grain charging dynamicsOct 22 2004It is well known that the form of grain size distribution strongly influences the linear dielectric response of a dusty plasma. In previous results [IEEE Trans. Plasma Sci. 29, 182 (2001)], it was shown that for a class of size distributions, there is ... More
Measuring, Characterizing, and Detecting Facebook Like FarmsJul 01 2017Jul 04 2017Social networks offer convenient ways to seamlessly reach out to large audiences. In particular, Facebook pages are increasingly used by businesses, brands, and organizations to connect with multitudes of users worldwide. As the number of likes of a page ... More
Combating Fraud in Online Social Networks: Detecting Stealthy Facebook Like FarmsJun 01 2015May 09 2016As businesses increasingly rely on social networking sites to engage with their customers, it is crucial to understand and counter reputation manipulation activities, including fraudulently boosting the number of Facebook page likes using like farms. ... More
Characterizing Seller-Driven Black-Hat MarketplacesMay 07 2015This paper investigates two seller-driven black-hat online marketplaces, SEOClerks and MyCheapJobs, aiming to shed light on the services they offer as well as sellers and customers they attract. We perform a measurement-based analysis based on complete ... More