arXiv subjects

Mayank Singh

Publications and source records attributed to Mayank Singh.

At least 109 records · Page 6Linked to original sources

arXiv2020

A study of charm quark dynamics in quark-gluon plasma with 3+1 D viscous hydrodynamics

The drag and diffusion coefficients are studied within the framework of Fokker-Planck dynamics for the case of a charm quark propagating in an expanding quark-gluon plasma. The space-time evolution of the nuclear matter created in the relativistic heavy-ion collision is modelled using MUSIC, a 3+1 D relativistic viscous hydrodynamic approach. The effect of viscous corrections to the heavy quark transport coefficients is explored by considering scattering processes with thermal quarks and gluons in the medium. It is observed that the momentum diffusion of the heavy quarks is sensitive to the shear and bulk viscosity to entropy ratios. The collisional energy loss of the charm quark in the viscous quark-gluon plasma is analyzed.

hep-ph↗

arXiv2020

Gandhipedia: A one-stop AI-enabled portal for browsing Gandhian literature, life-events and his social network

We introduce an AI-enabled portal that presents an excellent visualization of Mahatma Gandhi's life events by constructing temporal and spatial social networks from the Gandhian literature. Applying an ensemble of methods drawn from NLTK, Polyglot and Spacy we extract the key persons and places that find mentions in Gandhi's written works. We visualize these entities and connections between them based on co-mentions within the same time frame as networks in an interactive web portal. The nodes in the network, when clicked, fire search queries about the entity and all the information about the entity presented in the corresponding book from which the network is constructed, are retrieved and presented back on the portal. Overall, this system can be used as a digital and user-friendly resource to study Gandhian literature.

cs.IR↗

arXiv2020

SEAL: Scientific Keyphrase Extraction and Classification

Automatic scientific keyphrase extraction is a challenging problem facilitating several downstream scholarly tasks like search, recommendation, and ranking. In this paper, we introduce SEAL, a scholarly tool for automatic keyphrase extraction and classification. The keyphrase extraction module comprises two-stage neural architecture composed of Bidirectional Long Short-Term Memory cells augmented with Conditional Random Fields. The classification module comprises of a Random Forest classifier. We extensively experiment to showcase the robustness of the system. We evaluate multiple state-of-the-art baselines and show a significant improvement. The current system is hosted at http://lingo.iitgn.ac.in:5000/.

cs.IR↗

arXiv2020

On the Benefits of Models with Perceptually-Aligned Gradients

Adversarial robust models have been shown to learn more robust and interpretable features than standard trained models. As shown in [\cite{tsipras2018robustness}], such robust models inherit useful interpretable properties where the gradient aligns perceptually well with images, and adding a large targeted adversarial perturbation leads to an image resembling the target class. We perform experiments to show that interpretable and perceptually aligned gradients are present even in models that do not show high robustness to adversarial attacks. Specifically, we perform adversarial training with attack for different max-perturbation bound. Adversarial training with low max-perturbation bound results in models that have interpretable features with only slight drop in performance over clean samples. In this paper, we leverage models with interpretable perceptually-aligned features and show that adversarial training with low max-perturbation bound can improve the performance of models for zero-shot and weakly supervised localization tasks.

cs.CV↗

arXiv2020

Innovation and Revenue: Deep Diving into the Temporal Rank-shifts of Fortune 500 Companies

Research and innovation is important agenda for any company to remain competitive in the market. The relationship between innovation and revenue is a key metric for companies to decide on the amount to be invested for future research. Two important parameters to evaluate innovation are the quantity and quality of scientific papers and patents. Our work studies the relationship between innovation and patenting activities for several Fortune 500 companies over a period of time. We perform a comprehensive study of the patent citation dataset available in the Reed Technology Index collected from the US Patent Office. We observe several interesting relations between parameters like the number of (i) patent applications, (ii) patent grants, (iii) patent citations and Fortune 500 ranks of companies. We also study the trends of these parameters varying over the years and derive causal explanations for these with qualitative and intuitive reasoning. To facilitate reproducible research, we make all the processed patent dataset publicly available at https://github.com/mayank4490/Innovation-and-revenue.

cs.DL↗

arXiv2020

PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus for Machine Translation

Code-mixing is the phenomenon of using more than one language in a sentence. It is a very frequently observed pattern of communication on social media platforms. Flexibility to use multiple languages in one text message might help to communicate efficiently with the target audience. But, it adds to the challenge of processing and understanding natural language to a much larger extent. This paper presents a parallel corpus of the 13,738 code-mixed English-Hindi sentences and their corresponding translation in English. The translations of sentences are done manually by the annotators. We are releasing the parallel corpus to facilitate future research opportunities in code-mixed machine translation. The annotated corpus is available at https://doi.org/10.5281/zenodo.3605597.

cs.CL↗

arXiv2020

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution. Since the goal of few-shot learning is closely linked to robust representation learning, we study Manifold Mixup in this problem setting. Self-supervised learning is another technique that learns semantically meaningful features, using only the inherent structure of the data. This work investigates the role of learning relevant feature manifold for few-shot tasks using self-supervision and regularization techniques. We observe that regularizing the feature manifold, enriched via self-supervised techniques, with Manifold Mixup significantly improves few-shot learning performance. We show that our proposed method S2M2 beats the current state-of-the-art accuracy on standard few-shot learning datasets like CIFAR-FS, CUB, mini-ImageNet and tiered-ImageNet by 3-8 %. Through extensive experimentation, we show that the features learned using our approach generalize to complex few-shot evaluation tasks, cross-domain scenarios and are robust against slight changes to data distribution.

cs.LG↗

arXiv2019

Analysis of Reference and Citation Copying in Evolving Bibliographic Networks

Extensive literature demonstrates how the copying of references (links) can lead to the emergence of various structural properties (e.g., power-law degree distribution and bipartite cores) in bibliographic and other similar directed networks. However, it is also well known that the copying process is incapable of mimicking the number of directed triangles in such networks; neither does it have the power to explain the obsolescence of older papers. In this paper, we propose RefOrCite, a new model that allows for copying of both the references from (i.e., out-neighbors of) as well as the citations to (i.e., in-neighbors of) an existing node. In contrast, the standard copying model (CP) only copies references. While retaining its spirit, RefOrCite differs from the Forest Fire (FF) model in ways that makes RefOrCite amenable to mean-field analysis for degree distribution, triangle count, and densification. Empirically, RefOrCite gives the best overall agreement with observed degree distribution, triangle count, diameter, h-index, and the growth of citations to newer papers.

cs.SI↗

arXiv2019

A Method for Computing Class-wise Universal Adversarial Perturbations

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods that use iterative optimization for computing a universal perturbation, the proposed method employs a perturbation that is a linear function of weights of the neural network and hence can be computed much faster. The method does not require any training data and has no hyper-parameters. The attack obtains 34% to 51% fooling rate on state-of-the-art deep neural networks on ImageNet and transfers across models. We also study the characteristics of the decision boundaries learned by standard and adversarially trained models to understand the universal adversarial perturbations.

cs.LG↗

arXiv2019

Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification

The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing approaches focus on learning a common representation by leveraging both source and target data during training. In this paper, we introduce a two-stage training procedure that leverages weakly supervised datasets for developing simple lift-and-shift-based predictive models without being exposed to the target domain during the training phase. Experimental results show that transfer with weak supervision from a source domain to various target domains provides performance very close to that obtained via supervised training on the target domain itself.

cs.LG↗

arXiv2019

The rise and rise of interdisciplinary research: Understanding the interaction dynamics of three major fields -- Physics, Mathematics & Computer Science

The distinction between sciences is becoming increasingly more artificial -- an approach from one area can be easily applied to the other. More exciting research nowadays is happening perhaps at the interfaces of disciplines like Physics, Mathematics and Computer Science. How do these interfaces emerge and interact? For instance, is there a specific pattern in which these fields cite each other? In this article, we investigate a collection of more than 1.2 million papers from three different scientific disciplines -- Physics, Mathematics, and Computer Science. We show how over a timescale the citation patterns from the core science fields (Physics, Mathematics) to the applied and fast-growing field of Computer Science have drastically increased. Further, we observe how certain subfields in these disciplines are shrinking while others are becoming tremendously popular. For instance, an intriguing observation is that citations from Mathematics to the subfield of machine learning in Computer Science in recent times are exponentially increasing.

cs.DL↗

arXiv2019

BioGen: Automated Biography Generation

A biography of a person is the detailed description of several life events including his education, work, relationships, and death. Wikipedia, the free web-based encyclopedia, consists of millions of manually curated biographies of eminent politicians, film and sports personalities, etc. However, manual curation efforts, even though efficient, suffers from significant delays. In this work, we propose an automatic biography generation framework BioGen. BioGen generates a short collection of biographical sentences clustered into multiple events of life. Evaluation results show that biographies generated by BioGen are significantly closer to manually written biographies in Wikipedia. A working model of this framework is available at nlpbiogen.herokuapp.com/home/.

cs.DL↗

arXiv2019

Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to use the methodology of adversarial training. We analyze the adversarially trained robust models to study their vulnerability against adversarial attacks at the level of the latent layers. Our analysis reveals that contrary to the input layer which is robust to adversarial attack, the latent layer of these robust models are highly susceptible to adversarial perturbations of small magnitude. Leveraging this information, we introduce a new technique Latent Adversarial Training (LAT) which comprises of fine-tuning the adversarially trained models to ensure the robustness at the feature layers. We also propose Latent Attack (LA), a novel algorithm for construction of adversarial examples. LAT results in minor improvement in test accuracy and leads to a state-of-the-art adversarial accuracy against the universal first-order adversarial PGD attack which is shown for the MNIST, CIFAR-10, CIFAR-100 datasets.

cs.LG↗

arXiv2019

The Evolving Ecosystem of Predatory Journals: A Case Study in Indian Perspective

Digital advancement in scholarly repositories has led to the emergence of a large number of open access predatory publishers that charge high article processing fees from authors but fail to provide necessary editorial and publishing services. Identifying and blacklisting such publishers has remained a research challenge due to the highly volatile scholarly publishing ecosystem. This paper presents a data-driven approach to study how potential predatory publishers are evolving and bypassing several regularity constraints. We empirically show the close resemblance of predatory publishers against reputed publishing groups. In addition to verifying standard constraints, we also propose distinctive signals gathered from network-centric properties to understand this evolving ecosystem better.

cs.DL↗

arXiv2019

Automated Early Leaderboard Generation From Comparative Tables

A leaderboard is a tabular presentation of performance scores of the best competing techniques that address a specific scientific problem. Manually maintained leaderboards take time to emerge, which induces a latency in performance discovery and meaningful comparison. This can delay dissemination of best practices to non-experts and practitioners. Regarding papers as proxies for techniques, we present a new system to automatically discover and maintain leaderboards in the form of partial orders between papers, based on performance reported therein. In principle, a leaderboard depends on the task, data set, other experimental settings, and the choice of performance metrics. Often there are also tradeoffs between different metrics. Thus, leaderboard discovery is not just a matter of accurately extracting performance numbers and comparing them. In fact, the levels of noise and uncertainty around performance comparisons are so large that reliable traditional extraction is infeasible. We mitigate these challenges by using relatively cleaner, structured parts of the papers, e.g., performance tables. We propose a novel performance improvement graph with papers as nodes, where edges encode noisy performance comparison information extracted from tables. Every individual performance edge is extracted from a table with citations to other papers. These extractions resemble (noisy) outcomes of 'matches' in an incomplete tournament. We propose several approaches to rank papers from these noisy 'match' outcomes. We show that our ranking scheme can reproduce various manually curated leaderboards very well. Using widely-used lists of state-of-the-art papers in 27 areas of Computer Science, we demonstrate that our system produces very reliable rankings.

cs.DL↗

arXiv2018

Hydrodynamic Fluctuations in Relativistic Heavy-Ion Collisions

We present a novel approach to the treatment of thermal fluctuations in the (3+1)-D viscous hydrodynamic simulation MUSIC. The phenomenological impact of thermal fluctuations on hadronic observables is investigated using the IP-Glasma + hydrodynamics + hadronic cascade hybrid approach. The anisotropic flow observed in heavy-ion collision experiments is mostly attributed to the hydrodynamic response to the event-by-event collision geometry and to the sub-nucleon quantum fluctuations. However, hydrodynamic fluctuations are present during the dynamical evolution of the Quark Gluon Plasma (QGP) and are quantified by the fluctuation-dissipation theorem. They can leave their imprint on final-state observables. By analyzing the thermal noise mode-by-mode, we provide a consistent scheme of treating these fluctuations as the source terms for hydrodynamic fields. These source terms are then evolved together with hydrodynamic equations of motion. Such a treatment captures the non-perturbative nature of the evolution for these thermal fluctuations.

nucl-th↗

arXiv2018

CL Scholar: The ACL Anthology Knowledge Graph Miner

We present CL Scholar, the ACL Anthology knowledge graph miner to facilitate high-quality search and exploration of current research progress in the computational linguistics community. In contrast to previous works, periodically crawling, indexing and processing of new incoming articles is completely automated in the current system. CL Scholar utilizes both textual and network information for knowledge graph construction. As an additional novel initiative, CL Scholar supports more than 1200 scholarly natural language queries along with standard keyword-based search on constructed knowledge graph. It answers binary, statistical and list based natural language queries. The current system is deployed at http://cnerg.iitkgp.ac.in/aclakg. We also provide REST API support along with bulk download facility. Our code and data are available at https://github.com/CLScholar.

cs.DL↗

arXiv2018

Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space

Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks. On the other hand, the existence of adversarial examples have raised suspicions regarding the generalization capabilities of neural networks. In this work, we focus on the weight matrix learnt by the neural networks and hypothesize that ill conditioned weight matrix is one of the contributing factors in neural network's susceptibility towards adversarial examples. For ensuring that the learnt weight matrix's condition number remains sufficiently low, we suggest using orthogonal regularizer. We show that this indeed helps in increasing the adversarial accuracy on MNIST and F-MNIST datasets.

cs.LG↗