International Institute of Information Technology, Hyderabad

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).

Mining Rare Periodic-Frequent Patterns Using Multiple Minimum Supports.

Abstract: Recently, an approach has been proposed in the literature to extract frequent patterns which occur periodically. In this paper, we have proposed an approach to extract rare periodic-frequent patterns. Normally, the single minsup based frequent pattern mining approaches like Apriori and FP-growth suffer from “rare item problem”. That is, at high minsup, frequent patterns consisting of rare items will be missed, and at low minsup, number of frequent patterns explode. In the literature, efforts have been made to extract rare frequent patterns under “multiple minimum support framework”. It was observed that the periodic-frequent pattern mining approach also suffers from the “rare item problem”. In this paper, we have extended “multiple minimum support framework” to extract rare periodic-frequent patterns and developed a new algorithm to extract rare periodic-frequent patterns. Experiment results show that the proposed approach is efficient.

Residual neural networks for speech recognition

Abstract: Recent developments in deep learning methods have greatly influenced the performances of speech recognition systems. In a Hidden Markov model-Deep neural network (HMM-DNN) based speech recognition system, DNNs have been employed to model senones (context dependent states of HMM), where HMMs capture the temporal relations among senones. Due to the use of more deeper networks significant improvement in the performances has been observed and developing deep learning methods to train more deeper architectures has gained a lot of scientific interest. Optimizing a deeper network is more complex task than to optimize a less deeper network, but recently residual network have exhibited a capability to train a very deep neural network architectures and are not prone to vanishing/exploding gradient problems. In this work, the effectiveness of residual networks have been explored for of speech recognition. Along with the depth of the residual network, the criticality of width of the residual network has also been studied. It has been observed that at higher depth, width of the networks is also a crucial parameter for attaining significant improvements. A 14-hour subset of WSJ corpus is used for training the speech recognition systems, it has been observed that the residual networks have shown much ease in convergence even with a depth much higher than the deep neural network. In this work, using residual networks an absolute reduction of 0.4 in WER error rates (8% reduction in the relative error) is attained compared to the best performing deep neural network.

No more beating about the bush : A Step towards Idiom Handling for Indian Language NLP.

Abstract: One of the major challenges in the field of Natural Language Processing (NLP) is the handling of idioms; seemingly ordinary phrases which could be further conjugated or even spread across the sentence to fit the context. Since idioms are a part of natural language, the ability to tackle them brings us closer to creating efficient NLP tools. This paper presents a multilingual parallel idiom dataset for seven Indian languages in addition to English and demonstrates its usefulness for two NLP applications Machine Translation and Sentiment Analysis. We observe significant improvement for both the subtasks over baseline models trained without employing the idiom dataset.

An efficient algorithm for topic ranking and modeling topic evolution

Abstract: In this paper we introduce a novel and efficient approach to detect and rank topics in a large corpus of research papers. With rapidly growing size of academic literature, the problem of topic detection and topic ranking has become a challenging task. We present a unique approach that uses closed frequent keyword-set to form topics. We devise a modified time independent PageRank algorithm that assigns an authoritative score to each topic by considering the sub-graph in which the topic appears, producing a ranked list of topics. The use of citation network and the introduction of time invariance in the topic ranking algorithm reveal very interesting results. Our approach also provides a clustering technique for the research papers using topics as similarity measure. We extend our algorithms to study various aspects of topic evolution which gives interesting insight into trends in research areas over time. Our algorithms also detect hot topics and landmark topics over the years. We test our algorithms on the DBLP dataset and show that our algorithms are fast, effective and scalable.