Search

Large language models have limited context capacity, hindering reasoning over long conversations. We propose the Hierarchical Aggregate Tree memory structure to recursively aggregate relevant dialogue context through conditional tree traversals. HAT encapsulates information from children nodes, enabling broad coverage with depth control. We formulate finding best context as optimal tree traversal. Experiments show HAT improves dialog coherence and summary quality over baseline contexts, demonstrating the techniques effectiveness for multi turn reasoning without exponential parameter growth. This memory augmentation enables more consistent, grounded longform conversations from LLMs, Comment: 6 pages, 2 figures

This paper provides an overview of the historical progression of distributed optimization techniques, tracing their development from early duality-based methods pioneered by Dantzig, Wolfe, and Benders in the 1960s to the emergence of the Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN) algorithm. The initial focus on Lagrangian relaxation for convex problems and decomposition strategies led to the refinement of methods like the Alternating Direction Method of Multipliers (ADMM). The resurgence of interest in distributed optimization in the late 2000s, particularly in machine learning and imaging, demonstrated ADMM's practical efficacy and its unifying potential. This overview also highlights the emergence of the proximal center method and its applications in diverse domains. Furthermore, the paper underscores the distinctive features of ALADIN, which offers convergence guarantees for non-convex scenarios without introducing auxiliary variables, differentiating it from traditional augmentation techniques. In essence, this work encapsulates the historical trajectory of distributed optimization and underscores the promising prospects of ALADIN in addressing non-convex optimization challenges., Comment: 23 pages

In 2020, covid-19 virus had reached more than 200 countries. Till December 20th 2021, 221 nations in the world had collectively reported 275M confirmed cases of covid-19 & total death toll of 5.37M. Many countries which include United States, India, Brazil, United Kingdom, Russia etc were badly affected by covid-19 pandemic due to the large population. The total confirmed cases reported in this country are 51.7M, 34.7M, 22.2M, 11.3M, 10.2M respectively till December 20, 2021. This pandemic can be controlled with the help of precautionary steps by government & civilians of the country. The early prediction of covid-19 cases helps to track the transmission dynamics & alert the government to take the necessary precautions. Recurrent Deep learning algorithms is a data driven model which plays a key role to capture the patterns present in time series data. In many literatures, the Recurrent Neural Network (RNN) based model are proposed for the efficient prediction of COVID-19 cases for different provinces. The study in the literature doesnt involve the interpretation of the model behavior & robustness. In this study, The LSTM model is proposed for the efficient prediction of active cases in each provinces of India. The active cases dataset for each province in India is taken from John Hopkins publicly available dataset for the duration from 10th June, 2020 to 4th August, 2021. The proposed LSTM model is trained on one state i.e., Maharashtra and tested for rest of the provinces in India. The concept of Explainable AI is involved in this study for the better interpretation & understanding of the model behavior. The proposed model is used to forecast the active cases in India from 16th December, 2021 to 5th March, 2022. It is notated that there will be a emergence of third wave on January, 2022 in India., Comment: 12 pages

Human communication is inherently multimodal and asynchronous. Analyzing human emotions and sentiment is an emerging field of artificial intelligence. We are witnessing an increasing amount of multimodal content in local languages on social media about products and other topics. However, there are not many multimodal resources available for under-resourced Dravidian languages. Our study aims to create a multimodal sentiment analysis dataset for the under-resourced Tamil and Malayalam languages. First, we downloaded product or movies review videos from YouTube for Tamil and Malayalam. Next, we created captions for the videos with the help of annotators. Then we labelled the videos for sentiment, and verified the inter-annotator agreement using Fleiss's Kappa. This is the first multimodal sentiment analysis dataset for Tamil and Malayalam by volunteer annotators., Comment: 31

In this paper, we have applied the logistic growth regression model and genetic algorithm to predict the number of coronavirus infected cases that can be expected in upcoming days in India and also estimated the final size and its peak time of the coronavirus epidemic in India.

Offensive behaviour has become pervasive in the Internet community. Individuals take the advantage of anonymity in the cyber world and indulge in offensive communications which they may not consider in the real life. Governments, online communities, companies etc are investing into prevention of offensive behaviour content in social media. One of the most effective solution for tacking this enigmatic problem is the use of computational techniques to identify offensive content and take action. The current work focuses on detecting offensive language in English tweets. The dataset used for the experiment is obtained from SemEval-2019 Task 6 on Identifying and Categorizing Offensive Language in Social Media (OffensEval). The dataset contains 14,460 annotated English tweets. The present paper provides a comparative analysis and Random kitchen sink (RKS) based approach for offensive language detection. We explore the effectiveness of Google sentence encoder, Fasttext, Dynamic mode decomposition (DMD) based features and Random kitchen sink (RKS) method for offensive language detection. From the experiments and evaluation we observed that RKS with fastetxt achieved competing results. The evaluation measures used are accuracy, precision, recall, f1-score.

Dimensionality reduction is an important step in processing the hyperspectral images (HSI) to overcome the curse of dimensionality problem. Linear dimensionality reduction methods such as Independent component analysis (ICA) and Linear discriminant analysis (LDA) are commonly employed to reduce the dimensionality of HSI. These methods fail to capture non-linear dependency in the HSI data, as data lies in the nonlinear manifold. To handle this, nonlinear transformation techniques based on kernel methods were introduced for dimensionality reduction of HSI. However, the kernel methods involve cubic computational complexity while computing the kernel matrix, and thus its potential cannot be explored when the number of pixels (samples) are large. In literature a fewer number of pixels are randomly selected to partial to overcome this issue, however this sub-optimal strategy might neglect important information in the HSI. In this paper, we propose randomized solutions to the ICA and LDA dimensionality reduction methods using Random Fourier features, and we label them as RFFICA and RFFLDA. Our proposed method overcomes the scalability issue and to handle the non-linearities present in the data more efficiently. Experiments conducted with two real-world hyperspectral datasets demonstrates that our proposed randomized methods outperform the conventional kernel ICA and kernel LDA in terms overall, per-class accuracies and computational time., Comment: Submitted IEEE JSTARS

A color image contains luminance and chrominance components representing the intensity and color information respectively. The objective of the work presented in this paper is to show the significance of incorporating the chrominance information for the task of scene classification. An improved color-to-grayscale image conversion algorithm by effectively incorporating the chrominance information is proposed using color-to-gay structure similarity index (C2G-SSIM) and singular value decomposition (SVD) to improve the perceptual quality of the converted grayscale images. The experimental result analysis based on the image quality assessment for image decolorization called C2G-SSIM and success rate (Cadik and COLOR250 datasets) shows that the proposed image decolorization technique performs better than 8 existing benchmark algorithms for image decolorization. In the second part of the paper, the effectiveness of incorporating the chrominance component in scene classification task is demonstrated using the deep belief network (DBN) based image classification system developed using dense scale invariant feature transform (SIFT) as features. The levels of chrominance information incorporated by the proposed image decolorization technique is confirmed by the improvement in the overall scene classification accuracy . Also, the overall scene classification performance is improved by the combination of models obtained using the proposed and the conventional decolorization methods., Comment: This article is accepted in SPIE J.of Electronic Imaging with title: Significance of perceptually relevant image decolorization for scene classification

Tree adjoining grammars (TAGs) provide an ample tool to capture syntax of many Indian languages. Tamil represents a special challenge to computational formalisms as it has extensive agglutinative morphology and a comparatively difficult argument structure. Modelling Tamil syntax and morphology using TAG is an interesting problem which has not been in focus even though TAGs are over 4 decades old, since its inception. Our research with Tamil TAGs have shown us that we can not only represent syntax of the language, but to an extent mine out semantics through dependency resolution of the sentence. But in order to demonstrate this phenomenal property, we need to parse Tamil language sentences using TAGs we have built and through parsing obtain a derivation we could use to resolve dependencies, thus proving the semantic property. We use an in-house developed pseudo lexical TAG chart parser; algorithm given by Schabes and Joshi (1988), for generating derivations of sentences. We do not use any statistics to rank out ambiguous derivations but rather use all of them to understand the mentioned semantic relation with in TAGs for Tamil. We shall also present a brief parser analysis for the completeness of our discussions., Comment: 9 pages. arXiv admin note: text overlap with arXiv:1604.01235

Visual Saliency is the capability of vision system to select distinctive parts of scene and reduce the amount of visual data that need to be processed. The presentpaper introduces (1) a novel approach to detect salient regions by considering color and luminance based saliency scores using Dynamic Mode Decomposition (DMD), (2) a new interpretation to use DMD approach in static image processing. This approach integrates two data analysis methods: (1) Fourier Transform, (2) Principle Component Analysis.The key idea of our work is to create a color based saliency map. This is based on the observation thatsalient part of an image usually have distinct colors compared to the remaining portion of the image. We have exploited the power of different color spaces to model the complex and nonlinear behavior of human visual system to generate a color based saliency map. To further improve the effect of final saliency map, weutilized luminance information exploiting the fact that human eye is more sensitive towards brightness than color.The experimental results shows that our method based on DMD theory is effective in comparison with previous state-of-art saliency estimation approaches. The approach presented in this paperis evaluated using ROC curve, F-measure rate, Precision-Recall rate, AUC score etc., Comment: 8 pages

Tree adjoining grammar (TAG) is specifically suited for morph rich and agglutinated languages like Tamil due to its psycho linguistic features and parse time dependency and morph resolution. Though TAG and LTAG formalisms have been known for about 3 decades, efforts on designing TAG Syntax for Tamil have not been entirely successful due to the complexity of its specification and the rich morphology of Tamil language. In this paper we present a minimalistic TAG for Tamil without much morphological considerations and also introduce a parser implementation with some obvious variations from the XTAG system, Comment: International Symposium for Dravidian Languages (iDravidian), co-located with ICON2014, Goa University, Dec 2014

Machine Translation is one of the major oldest and the most active research area in Natural Language Processing. Currently, Statistical Machine Translation (SMT) dominates the Machine Translation research. Statistical Machine Translation is an approach to Machine Translation which uses models to learn translation patterns directly from data, and generalize them to translate a new unseen text. The SMT approach is largely language independent, i.e. the models can be applied to any language pair. Statistical Machine Translation (SMT) attempts to generate translations using statistical methods based on bilingual text corpora. Where such corpora are available, excellent results can be attained translating similar texts, but such corpora are still not available for many language pairs. Statistical Machine Translation systems, in general, have difficulty in handling the morphology on the source or the target side especially for morphologically rich languages. Errors in morphology or syntax in the target language can have severe consequences on meaning of the sentence. They change the grammatical function of words or the understanding of the sentence through the incorrect tense information in verb. Baseline SMT also known as Phrase Based Statistical Machine Translation (PBSMT) system does not use any linguistic information and it only operates on surface word form. Recent researches shown that adding linguistic information helps to improve the accuracy of the translation with less amount of bilingual corpora. Adding linguistic information can be done using the Factored Statistical Machine Translation system through pre-processing steps. This paper investigates about how English side pre-processing is used to improve the accuracy of English-Tamil SMT system., Comment: Proc. of Int. Conf. on Advances in Computer Science, AETACS - 2013

We provide a simplified form of Primal Augmented Lagrange Multiplier algorithm. We intend to fill the gap in the steps involved in the mathematical derivations of the algorithm so that an insight into the algorithm is made. The experiment is focused to show the reconstruction done using this algorithm.

The art of recovering an image from damage in an undetectable form is known as inpainting. The manual work of inpainting is most often a very time consuming process. Due to digitalization of this technique, it is automatic and faster. In this paper, after the user selects the regions to be reconstructed, the algorithm automatically reconstruct the lost regions with the help of the information surrounding them. The existing methods perform very well when the region to be reconstructed is very small, but fails in proper reconstruction as the area increases. This paper describes a Hierarchical method by which the area to be inpainted is reduced in multiple levels and Total Variation(TV) method is used to inpaint in each level. This algorithm gives better performance when compared with other existing algorithms such as nearest neighbor interpolation, Inpainting through Blurring and Sobolev Inpainting., Comment: 7 pages, 7 figures; International Journal of Computer Science, Engineering and Applications (IJCSEA), Voulume 2, Number 3, June 2012, ISSN : 2230 - 9616 [Online] ; 2231 - 0088 [Print]

We present an algorithm using transformation groups and their irreducible representations to generate an orthogonal basis for a signal in the vector space of the signal. It is shown that multiresolution analysis can be done with amplitudes using a transformation group. G-lets is thus not a single transform, but a group of linear transformations related by group theory. The algorithm also specifies that a multiresolution and multiscale analysis for each resolution is possible in terms of frequencies. Separation of low and high frequency components of each amplitude resolution is facilitated by G-lets. Using conjugacy classes of the transformation group, more than one set of basis may be generated, giving a different perspective of the signal through each basis. Applications for this algorithm include edge detection, feature extraction, denoising, face recognition, compression, and more. We analyze this algorithm using dihedral groups as an example. We demonstrate the results with an ECG signal and the standard `Lena' image., Comment: 20 pages, 8 figures