Home      Discussions      About
Join us

@cse.iitkgp.ernet.in

Aug 17, 2016
By marsili
Digital Libraries
Computers and Society

Anomalies in the peer-review system: A case study of the journal of H…

Peer-review system has long been relied upon for bringing quality research to the notice of the scientific community and also preventing flawed resea…
May 09, 2017
Digital Libraries

Understanding the Impact of Early Citers on Long-Term Scientific Impa…

This paper explores an interesting new dimension to the challenging problem of predicting long-term scientific impact (LTSI) usually measured by the …
Sep 06, 2018
By amrith
Computation and Language

Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romani…

We propose a post-OCR text correction approach for digitising texts in Romanised Sanskrit. Owing to the lack of resources our approach uses OCR model…
Apr 10, 2019
Computer Vision

Efficient Retrieval of Logos Using Rough Set Reducts

Searching for similar logos in the registered logo database is a very important and tedious task at the trademark office. Speed and accuracy are two …
Jan 15, 2009
Computation and Language
Data Analysis
Statistics and Probability

Are there any linguistic inferences that can be drawn from the results obtained through the study of the spectral plot and the eigenvectors of PhoNet? In fact, one can correlate several phonological theories to the aforementioned observations, which…

Discovering Global Patterns in Linguistic Networks through Spectral …

Recent research has shown that language and the socio-cognitive phenomena associated with it can be aptly modeled and visualized through networks of …
Sep 10, 2017
Computation and Language

AppTechMiner: Mining Applications and Techniques from Scientific Ar…

This paper presents AppTechMiner, a rule-based information extraction framework that automatically constructs a knowledge base of all application are…
Feb 15, 2018
By bidisha
Machine Learning

Designing Random Graph Models Using Variational Autoencoders With A…

Deep generative models have been praised for their ability to learn smooth latent representation of images, text, and audio, which can then be used t…
Jun 13, 2019
By bidisha
Computation and Language

Improved Sentiment Detection via Label Transfer from Monolingual to …

Multilingual writers and speakers often alternate between two languages in a single discourse, a practice called "code-switching". Existing sentiment…
Jun 21, 2019
By niloy
Computation and Language

We proposed VACS, a novel variational autoencoder to synthesize unlimited volumes of language-tagged code-switched text starting with modest real code-switched and abundant monolingual text. We showed that VACS generates text of various lengths and …

A Deep Generative Model for Code-Switched Text

Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies. Accurate language mo…
Aug 08, 2018
Social and Information Networks
Physics and Society

On Rich Clubs of Path-Based Centralities in Networks

Many scale-free networks exhibit a rich club structure, where high degree vertices form tightly interconnected subgraphs. In this paper, we explore t…
Nov 07, 2011
Information Retrieval

An IR-based Evaluation Framework for Web Search Query Segmentation

This paper presents the first evaluation framework for Web search query segmentation based directly on IR performance. In the past, segmentation stra…
Apr 24, 2012
By niloy
Social and Information Networks
Physics and Society

A Tunable Mechanism for Identifying Trusted Nodes in Large Scale Di…

In this paper, we propose a simple randomized protocol for identifying trusted nodes based on personalized trust in large scale distributed networks.…
Nov 11, 2018
Computer Vision

HSD-CNN: Hierarchically self decomposing CNN architecture using class…

Conventional Convolutional neural networks (CNN) are trained on large domain datasets, and are hence typically over-represented and inefficient in li…
Oct 01, 2016
By niranj
Combinatorics

Induced bisecting families for hypergraphs

Two $n$-dimensional vectors $A$ and $B$, $A,B \in \mathbb{R}^n$, are said to be \emph{trivially orthogonal} if in every coordinate $i \in [n]$, at le…
Sep 05, 2016
Networking and Internet Architecture

SDFog: A Software Defined Computing Architecture for QoS Aware Servic…

Cloud computing revolutionized the information technology (IT) industry by offering dynamic and infinite scaling, on-demand resources and utility-ori…
Mar 24, 2011
By akdas
Cryptography and Security

An Identity Based Key Management Scheme in Wireless Sensor Networks

Pairwise key establishment is one of the fundamental security services in sensor networks which enables sensor nodes in a sensor network to communica…
Sep 21, 2016
Digital Libraries
Information Retrieval

OCR++: A Robust Framework For Information Extraction from Scholarly …

This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata…
May 02, 2017
By marsili
Digital Libraries

Influence of Reviewer Interaction Network on Long-term Citations: A C…

A `peer-review system' in the context of judging research contributions, is one of the prime steps undertaken to ensure the quality of the submission…
Mar 07, 2017
Machine Learning
Data Structures and Algorithms
Social and Information Networks

Cheshire: An Online Algorithm for Activity Maximization in Social N…

User engagement in social networks depends critically on the number of online actions their users take in the network. Can we design an algorithm tha…
Aug 30, 2012
By tanmoy
Computation and Language
Information Retrieval

Authorship Identification in Bengali Literature: a Comparative Analys…

Stylometry is the study of the unique linguistic styles and writing behaviors of individuals. It belongs to the core task of text categorization like…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description