Institution
International Institute of Information Technology, Hyderabad
Education•Hyderabad, India•
About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Authentication & Internet security. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).
Topics: Authentication, Internet security, Wireless sensor network, Machine translation, Deep learning
Papers published on a yearly basis
Papers
More filters
•
12 Jul 2012TL;DR: This work presents the qualitative analysis of the agreement statistics and identifies the possible reasons for the disagreement between the annotators, and shows the syntactic annotation of some constructions specific to Urdu like Ezafe and discusses the problem of word segmentation (tokenization).
Abstract: In this paper we describe a currently underway treebanking effort for Urdu-a South Asian language. The treebank is built from a newspaper corpus and uses a Karaka based grammatical framework inspired by Paninian grammatical theory. Thus far 3366 sentences (0.1M words) have been annotated with the linguistic information at morpho-syntactic (morphological, part-of-speech and chunk information) and syntactico-semantic (dependency) levels. This work also aims to evaluate the correctness or reliability of this manual annotated dependency treebank. Evaluation is done by measuring the inter-annotator agreement on a manually annotated data set of 196 sentences (5600 words) annotated by two annotators. We present the qualitative analysis of the agreement statistics and identify the possible reasons for the disagreement between the annotators. We also show the syntactic annotation of some constructions specific to Urdu like Ezafe and discuss the problem of word segmentation (tokenization).
18 citations
01 Jan 2010
TL;DR: A model of cognition is presented that explains how metaphor creates new insights into an object or a situation and is based on assuming that cognition invariably leads to a loss of information and that metaphor can recover some of this lost information.
Abstract: We consider some examples of creativity in a number of diverse cognitive domains like art, science, mathematics, product development, legal reasoning, etc. to articulate an operational account of creative cognition. We present a model of cognition that explains how metaphor creates new insights into an object or a situation. The model is based on assuming that cognition invariably leads to a loss of information and that metaphor can recover some of this lost information. In this model we also contrast the role of traditional analogy (mapping based on existing conceptualization) with the role of metaphor (destroying existing conceptualizations in order to create new conceptualizations).
18 citations
••
16 Dec 2017
TL;DR: In this paper, an EEG (Electroencephalogram)-based image annotation system was proposed to identify target images during a rapid serial visual presentation (RSVP) task.
Abstract: The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20–200 ms, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training.
18 citations
••
TL;DR: This study demonstrates that the dynamic framework best characterizes the variability in ASD, and finds that whole-brain flexibility correlates with static modularity only in TD.
Abstract: Resting-state functional connectivity (FC) analyses have shown atypical connectivity in autism spectrum disorder (ASD) as compared to typically developing (TD). However, this view emerges from investigating static FC overlooking the age, disease phenotype and their interaction in the whole brain transient connectivity patterns. Contrasting with most extant literature in the present study, we investigated precisely how age and disease phenotypes factors into dynamic changes in functional connectivity of TD and ASD using resting-state functional magnetic resonance imaging (rs-fMRI) data stratified into three cohorts: children (7-11 years) and adolescents (12-17 years), and adults (18+) for the analysis. The dynamic variability in the connection strength and the modular organization in terms of measures: flexibility, cohesion strength and disjointness were explored for each subject to characterize the differences between ASD and TD. In ASD, we observed significantly higher inter-subject dynamic variability in connection strength as compared to TD. This hypervariability relates to the symptom severity in ASD. We found that whole-brain flexibility correlates with static modularity only in TD. Further, we observed a coreperiphery organization in the resting-state, with Sensorimotor and Visual regions in the rigid core; and DMN and attention areas in the flexible periphery. TD also develops a more cohesive organization of sensorimotor areas. However, in ASD we found a strong positive correlation of symptom severity with the flexibility of rigid areas and with disjointness of sensorimotor areas. The regions of the brain showing the high predictive power of symptom severity were distributed across the cortex, with stronger bearings in the frontal, motor and occipital cortices. Our study demonstrates that the dynamic framework best characterizes the variability in ASD.
18 citations
••
26 Mar 2018TL;DR: In this paper, a semi-supervised method based on co-training was proposed to exploit a large pool of unlabeled tweets to augment the limited supervised training data, and as a result enhance the performance.
Abstract: Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care. Current ADR surveillance systems are often associated with a substantial time lag before such events are officially published. On the other hand, online social media such as Twitter contain information about ADR events in real-time, much before any official reporting. Current state-of-the-art methods in ADR mention extraction use Recurrent Neural Networks (RNN), which typically need large labeled corpora. Towards this end, we propose a semi-supervised method based on co-training which can exploit a large pool of unlabeled tweets to augment the limited supervised training data, and as a result enhance the performance. Experiments with \(\sim \)0.1M tweets show that the proposed approach outperforms the state-of-the-art methods for the ADR mention extraction task by \(\sim \)5% in terms of F1 score.
18 citations
Authors
Showing all 2066 results
Name | H-index | Papers | Citations |
---|---|---|---|
Ravi Shankar | 66 | 672 | 19326 |
Joakim Nivre | 61 | 295 | 17203 |
Aravind K. Joshi | 59 | 249 | 16417 |
Ashok Kumar Das | 56 | 278 | 9166 |
Malcolm F. White | 55 | 172 | 10762 |
B. Yegnanarayana | 54 | 340 | 12861 |
Ram Bilas Pachori | 48 | 182 | 8140 |
C. V. Jawahar | 45 | 479 | 9582 |
Saurabh Garg | 40 | 206 | 6738 |
Himanshu Thapliyal | 36 | 201 | 3992 |
Monika Sharma | 36 | 238 | 4412 |
Ponnurangam Kumaraguru | 33 | 269 | 6849 |
Abhijit Mitra | 33 | 240 | 7795 |
Ramanathan Sowdhamini | 33 | 256 | 4458 |
Helmut Schiessel | 32 | 117 | 3527 |