Abstract

In remote sensing, multi-sensor data fusion aims at combining strengths of different data sources in a manner such that the resultant fused product preserves the best of the participating sources. From among all the levels at which fusion is done, namely pixel level, feature level and decision/information level, pixel level data fusion is the most elementary form of fusion. The real advantage with pixel level fusion is that it has the actual raw input data at its disposal which could be transferred to the output in a form closest to the input. Hence, pixel level algorithms need to aim at preserving the input properties rather than just improving the overall visual quality. Most of the existing methods are aimed at visual quality improvement and perform fusion using the global distributions, which results in loss of uniqueness of certain objects features. Such objects are either completely lost or their responses are milder in the output. These kind of local distributions can be preserved using a localized method of fusion. Other limitations of fusion methods include distortion of overall spectral distribution of the input data source and their applicability on the type of data being fused. There is a Gaussian Linear Stretch Image (GLSI) technique [1] for images fusion to handle spectral distortion. It is a moving window-based distribution matching and details are transferred in a linear manner. We have enhanced this algorithm to effectively handle two major challenges it faced. One is the detection and matching of class distributions which are inverted in the low and high resolution images and the other being the fusion of pixels belong to class distributions with significantly low sample space. We call it the Enhanced Gaussian Linear Stretch Image (e-GLSI) algorithm. The proposed e-GLSI algorithm is also a window based technique which aims at improving spatial resolution of multispectral bands using higher resolution panchromatic band. e-GLSI fuses the two inputs by transferring the spatial details of the panchromatic band into each multispectral band independently at local window level, hence prevents suppression of local unique features and preserves the spectral distribution of each band as well. In this approach, the local window statistics are used to establish linear relationships between corresponding windows from two different spatial resolution bands. Cases of distribution inversions and unimodal splits are handled using well defined metrics before fusing two distributions together. The algorithm then enhances each band independently without using any derived or aggregated knowledge, thus making this technique suitable to fuse any combination of input images. Results show that the statistical profile of the e-GLSI output bands matches the original multispectral image bands’ statistical profile better than other widely used approaches. In order to evaluate this matching quantitatively, standard deviation of the relative difference in fused pixel value and original multispectral pixel value per band has been computed. e-GLSI output gives a standard deviation of 0.18, 0.12 and 0.26 for red, blue and green bands respectively. Thus showing that it’s able to preserve the spectral characteristics from input images. In Spite of being able to preserve the spectral characteristics of the input images, there are some artifacts introduced in the e-GLSI fusion output. One of them is objects getting split across the moving window of the technique, which introduces a window boundary or sharp edge in some of the objects. A way to handle this could be the use of a variable sized window depending on the area of the image being processed. But this in itself is a challenge as it would require surrounding information and certain heuristics in order to decide the window size at a location in an image. In order to tackle this challenge, we used objects as windows in our approach. We propose an object based fusion algorithm based on GLSI, which we call the Object based GLSI (o-GLSI). Processing blocks for this approach are are the objects segmented from the Pan image. Since pixels being fused are part of a single object, we transfer details in a Gaussian manner in case of o-GLSI. The quantitative evaluation of o-GLSI fusion results clearly show that o-GLSI standard deviation of 0.32, 0.49 and 0.82 for relative difference in fused pixel and ground truth multispectral pixel for red, blue and green bands respectively is successful in keeping the fusion output spectrally closer to the input. Universal Image Quality Index (UIQI) [2] values of 0.9 for each band with respect to the ground truth proves that the quality of image fused by o-GLSI is very good. Since classification is one of the prominent applications for fused images, a superior accuracy rate supports the effectiveness of the fusion algorithm involved. As another measure to evaluate the utility of the fused images, k-means classification accuracy has been co

Abstract

Empathy entails the ability to understand (perspective-taking) and share the affective experiences of others, both processes considered the bedrock of all social interactions and critical for survival. Most empathy related neuroscience studies employ simple paradigms like pain-infliction or static images with emotional context and analysis focuses on either perspective-taking processing or affective experience overlooking the complex interaction among the processes. The initial studies informed how one understands pieces of the whole system with an assumption that when information from the pieces is fit the whole picture can be realized but this methodology has led to constrained theories on empathy process. To address the short-comings in understanding empathy, the focus of affective neuroscience research has shifted to studying this phenomenon as part of naturalistic social cognition. Hence with the goal to mimic real-life situations that evoke empathy, naturalistic or ecologically-valid paradigms are recent inclusions building upon the foundation provided by the earlier simple models. This study focuses specifically on narratives and empathy response. The aim of this study is to explore the neural correlates of narrative empathy using multi-modal visual movie narrative. Towards this, two functional magnetic resonance imaging (fMRI) studies were conducted using a total of 5 commercial full-length short film and movie clips. The first experiment had 3 movie clips (5-8minute long) from a diverse genre (animation, Hollywood and Indian Hindi movie) and the goal of this exploratory investigation was to identify the networks of empathy – cognitive (mentalizing), emotional and motor (affective experiences) and analyzing the dynamic nature of the neural activations as a function of the self-reported level of empathy experienced. The data-driven independent component analysis (ICA) method applied to isolate the underlying brain networks revealed: a) the ability of the fictional narratives induces emotional contagion and the potential to elicit empathy response b) activation of significant, distinct but overlapping empathy networks and c) the dynamic cross-correlation analysis between the task default-mode network (DMN) and individual empathy networks revealed that emotional empathy response displayed lower correlation while cognitive empathy higher correlation with DMN, suggesting the possible role of self-reflection or attention to an internal narrative triggered by external stimuli (Andrews-Hanna et al., 2012; Gusnard et al., 2001). This is a potentially significant finding for understanding the difference in cognitive and emotional empathy in clinical conditions like autism and psychopathy. Developing on the findings from the first study, a second fMRI study was designed to understand specifically the role of context in empathy response. Toward this, two diverse full-length short movies (8 minutes each) with real-life actors of ethnicity dissimilar to the participants were selected as stimuli. Functional imaging data was collected from two sets of extremely short clips (13-20seconds) with neutral and emotional scenes extracted from the full-length movie followed by the whole movie. Using a general linear model approach for data analysis, the contrasts estimated from each condition (activation for the short clips of neutral and emotional scenes versus the same clips in the full-length movie) were compared and the analysis showed that empathy sub-processes (emotional, cognitive and motor) were statistically significant when context is presented. The results also reveal the complex differential empathy processes in real-life social interactions, where responses are a function of context. Overall, the neural correlates of narrative empathy presented in this thesis, the first of the kind, suggest that a complex construct such as empathy should be best studied in with ecologically valid stimuli. The impact of the results, in studying empathy deficiency and interventions using narratives to enhance empathy, needs to be explored in the future.

Abstract

The rst problem is on anonymous communication, specically the so called "Anonymous Leader". A leader is one who has some special function such as decision making, etc. An anonymous leader is a leader who is anonymous, i.e.. no body knows who he is. The problem asks how a leader can perform its special function without revealing itself. We note that communication is the primary constraint to being anonymous. The anonymous leader must be able to send and receive messages without revealing its identitiy. Morever, other nodes/players must not be able to pretend to be the anonymous leader. There are many possible applications of this anonymous leader setting and here we will also describe one such application. Formally, we give denition of anonymous leader and give protocols with proof that enable anonymous communication while satisfying the dual requirements the leader must not be revealed, and other nodes/players should not be able to pretend to be the leader. Interestingly, this is the rst such formalisation in the literature to date; while anonymous communication itself is common, restricting it to only one anonymous node/party has not been attempted before The second problem is on broadcast, specifically ”Simultaneous Broadcast”. There are situations where the broadcasted message is required to reach nodes at the same time. This is especially true in auction bidding and gambling. Admitedly, it is possible to ensure that the time difference between reciepients is small enough to ensure that perfect simultanity is not required. Nevertheless this problem is interesting in its own right, especially considering the difficulty and the lack of any theory in the literature. Here, we try to solve the problem using ”time lock puzzles”. Time lock puzzles enable us to lock messages in such a way that a fixed amount of time is required to be invested to unlock the message. This can be used to setup synchrony in message receipt. However, the constraints and limitations are considerable, forcing this solution to be ultimately purely a first attempt at the problem. Formally, we give definition and protocol for simultaneous broadcast using time lock puzzles.

Abstract

Simultaneous Localization and Mapping (SLAM) refers to the problem of mapping an unknown environment that the robot is operating in and localizing itself in the unknown environment at the same time. Out of the various methods of performing SLAM, using a single monocular camera as the sole sensory input is highly preferred due to its simplicity and low power consumption. Range sensors such as laser range finders, depth cameras etc require much more power to operate and performing SLAM with them is more computationally intensive as compared to SLAM with a single camera. However, when compared to trajectory planning methods using depth-based SLAM, Monocular SLAM in loop does need additional considerations. One main reason being that for a robust optimization of the map and robot trajectory, using Bundle Adjustment (BA) in the case of most monocular SLAM methods, the SLAM system needs to scan the area for a reasonable duration to gather more information about the area to improve the map and pose estimates. Additionally, due to the way monocular SLAM methods work, they do not tolerate large camera rotations between successive views and tend to breakdown. Other reasons for Monocular SLAM failure include ambiguities in decomposition of the Essential Matrix, feature-sparse scenes and more layers of non linear optimization apart from BA. Learning a complex task such as low-level robot manoeuvres while preventing failure of monocular SLAM is a challenging problem for both robots and humans. The data-driven identification of basic motion strategies in preventing monocular SLAM failure is a largely unexplored problem. In this thesis, a computational model is devised for representing and inferring strategies for the problem, formulated as a Markov Decision Process (MDP), where the reward function models the goal of the task as well as information about the strategy. Reinforcement Learning (RL) is used with an intuitive, handcrafted reward function to generates fail safe trajectories wherein the SLAM generated outputs (scene structure and camera motion) do not deviate largely from their true values. This model is expanded on by treating it as an expert and try to learn an underlying true reward function for the given task at hand using Inverse Reinforcement Learning (IRL). Quintessentially, the framework successfully learns the otherwise complex relation between motor actions and perceptual inputs and uses this knowledge to generate trajectories that do not cause failure of SLAM. It also learns how a few chosen parameters affect the task at hand. This complex relation is almost intractable to capture in an obvious mathematical formulation. The framework allows one to identify the way in which a few chosen parameters affect the quality of monocular SLAM estimates. The estimated reward function was able to capture expert demonstration information and the inherent expert strategy and it was possible to give an intuitive explanation to the obtained reward structure. Drastic improvements in the quality of the SLAM map and trajectory are systematically shown in simulations. Better performance is demonstrated over other methods based on maximizing scene overlap, supervised learning based methods and over state-of-the-art methods described in literature that select the next view from a candidate set of views based on the best score calculated according to SLAM quality measures. The proposed method scales effectively across various SLAM frameworks in real world experiments as well as in simulations with a mobile robot.

Abstract

Sentiment analysis has emerged as a field, that has attracted a significant amount of attention over the last decade. This is the area of study to analyze people reviews, songs and attitudes from different types of data and classify whether it is a positive, negative or neutral. Recent advancement of social media which is an enormous ever-growing source has led people to share their views through various modalities such as audio, text and video. This source of information is important to automatically make out the sentiment embedded in the different types of data such as reviews and songs. In this thesis, an improved multimodal approach to detect the sentiment of product reviews and songs based on their multi-modality natures (audio and text) is proposed. The basic goal is to classify the input data as either positive or negative sentiment. Database used in this study are Spanish product reviews, Hindi product reviews and Telugu songs. Most of the existing systems for audio or speech based sentiment analysis use the conventional audio features which are extracted from entire signal, but they are not domain specific features to extract the sentiment. In this work, instead of extracting the features from entire signal, a specific regions of an audio signal have been identified and experiments are performed on these regions by extracting the relevant features. For songs data, experiments are performed over each song, and its beginning and ending regions. For all these cases, Gaussian Mixture Models (GMM) and Support Vector Machine (SVM) classifiers are built using the prosody, temporal, spectral, tempo and chroma features. Experimental results shown that the ate of detecting the sentiment of a song is high at beginning of a song compared to its ending region and over the entire duration of the song. This is because, the instruments and vocals which convey the sentiment for beginning part of the song may or may not sustain throughout the song. For the reviews data, we could not perform these experiments because in such cases the sentiment may not be present at beginning or ending regions of an utterance. So for the reviews data, the stressed and normal regions are identified using the strength of excitation. From the stressed regions, Mel Frequency Cepstral Coefficients (MFCC) features are extracted and GMM classifier is built. Further, experiments are performed by extracting the prosody (energy, pitch and duration) and relative prosody features from both the regions and from the entire audio signal and a GMM classifier is built. From the results, it is observed that, the performance at specific regions is better as compared to the entire signal. It is also observed that, relative prosody features extracted from both the regions has high accuracy of detecting the sentiment compared to the prosody and MFCC features. This is because, the natural variations present in the prosody features are reduced using the relative prosody features. Recently, neural networks have achieved good success on sentiment classification. In this work also different deep learning architectures like Deep Neural Network (DNN) and Deep Neural Network Attention Mechanism (DNNAM) are explored. Here stressed regions concept fail because of less training data. DNN performance depends on the amount of training data. The more the training data, the more accurate it is. So here the experiments are performed by combination of frames which result in better performance because each frame will not carry the sentiment. MFCC features considered are 13-dimensional, 65-dimensional and 130-dimensional feature vectors. From the studies, it is observed that DNNAM classifier gives better results compared to DNN, because the DNN approach is a frame based one where as the DNNAM approach is a utterance level classification there by efficiently making use of the context. For text based sentiment analysis, transcriptions are carried out manually from the audio signal. For song classification, SVM and Naive-Bayes classifiers are built using the textual features which are computed by Doc2Vec vectors. As in the audio, here also experiments are performed at the beginning, the ending and over the entire song. The studies shown that beginning of a song has high accuracy in detecting the sentiment compared to the ending region and over the entire song. As similar experiments could not be carried out with the reviews data, entire document is taken as an input to extract the sentiment. Support Vector Machine (SVM) and Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) classifiers are used to develop a sentiment model with the textual features computed by Doc2Vec and Word2Vec. From the experimental studies, it is observed that LSTM-RNN outperforms the SVM because LSTM-RNN is able to memorize long temporal context. Finally, we combine both the modalities such as audio and text to extract the sentiment. Both the modalities are hypothesized based on

Abstract

Technological advancements have made human beings dependent on machines in unprecedented ways. High precision in many tasks and a vast, tractable memory confirms their presence as an integral part of human lifestyle. Human-machine interaction, then, is the evident next step in developing smarter systems and consequently, a research topic of foremost importance. Effective communication is achieved by means of natural language and hence, language becomes an obvious necessity for human-machine communication too. The vast majority of languages spoken in a multi-ethnic society mandates the necessity of development of multilingual systems. India is one such region which is inhabited by highly diverse multicultural societies and a multitude of ethnic groups living as a nation. An effective Spoken Dialog System (SDS) developed for Indian scenario has to keep in mind the shared characteristics of languages spoken across India. This motivates the dire need to develop multilingual human-machine interfaces which can exploit this commonality. Portability and ever-increasing computing capacity have rendered mobile phones to be the most common form of communication agents. But in absence of network connectivity, they lose a lot of power residing in cloud platforms and have to rely on local resources which are limited and scarce in nature. This problem is ubiquitous because there are several locations and situations when network is not available but basic communication is crucial for information retrieval. One such situation is Healthcare for preventable diseases in rural areas. This thesis is focused to alleviate some of the problems which arise when humans move to interact with hand-held conversational machine agents in a multilingual setting such as India. With the advent of social media, code-mixing became a popular phenomena in spoken language. This work progresses to develop a spoken dialog system for the domain of Healthcare and focuses on problems of 1. recognizing the language of communication within speech segments through large-scale spoken language modeling and 2. spotting keywords in speech signal by creating a robust representation of articulatory gestures in speech. The proposed approaches are based on recurrent and convolutional architectures of neural networks and have been experimentally shown to outperform the state-of-the-art on standard datasets.

Abstract

Ring laser gyroscopes (RLG) are optical inertial rotation sensors used to measure the rate and direction of rotation. With the help of accelerometers, they provide accurate information about the position and orientation of an object. Their sensitivity depends upon the intended application: military navigation requires gyros with sensitivity of 0.01-0.1 deg/h while automobiles and handheld application need sensitivity of 1-10 deg/h. As the sensitivity of gyro is directly proportional to its size, the high performance military applications are dominated by the bulky He-Ne RLG. Over the past few decades, strong theoretical research backed up by advanced fabrication technologies have improved the performance of He-Ne RLG significantly. In the era of on-chip integrated optical devices, large size and high power requirement of He-Ne RLG limits its applications. This is where Semiconductor RLG (SRLG) provides a viable alternative. SRLG is a compact, low cost and low power inertial rotation sensor working on the principle of Sagnac effect. It offers the promise of fabricating the complete gyro system on a single Photonic Integrated Circuit (PIC). Many implementations of bulk-optic and integrated SRLG have been proposed, but their reported performance has been highly inferior to He-Ne RLG. While bulk-optic SRLG has shown sensitivity of 10 3 deg/h, the reported sensitivity of integrated SRLG has been 10 8 deg/h, which is unacceptable even for low performance applications like automobiles. While the poor performance of integrated SRLG has been attributed to phenomena like mode coupling and gain competition, a detailed performance analysis has not yet been reported. Hence, critical performance limiting parameters could not be identified and feasible practical solutions to enhance the performance could not be proposed. This has inhibited the development of SRLG technology towards high performance applications. In this thesis, SRLG has been mathematically modeled using rate equations of counter-traveling electric fields inside the gain medium and the resonant cavity. The Sagnac beat signal obtained by simulating the model is verified by rotating the experimental setup of the gyro. The sensitivity, which is found to be limited by locking of the counter-traveling fields, is enhanced by proposing few novel designs and biasing techniques. Although these techniques improve the sensitivity of SRLG, the overall performance is still very poor compared to the military navigation standards. In order to identify the critical performance limiting parameters and phenomena, every metric of SRLG such as quantum limit, angle random walk, scale factor stability, null shift and lock-in threshold have been thoroughly modeled in terms of material, geometry and environmental parameters. Moreover, effects of nonlinearities such as spatial hole burning, mode coupling, gain saturation etc. on the SRLG sensitivity have been evaluated. The critical performance affecting parameters are identified and optimized to achieve best possible performance. For integrated SRLG, lock-in due to non-linear backscattering inside the semiconductor gain medium is found to limit the sensitivity to 10 8 deg/h. Use of external coupled-cavity semiconductor ring lasers and stimulated Brillouin scattering (SBS) based ring lasers as gyroscopes are proposed for high performance military applications.

Abstract

A legal judgment is a document which provides an explanation of the court order concerning a legal case. The legal data is being digitized and is being made available in digital format for access by legal practitioners and the general public. Also, the legal data is continuously growing with the judgments being delivered. In common law based legal systems, legal practitioners refer to the previous judgments of the court to prepare the new judgment. Extracting relevant legal judgments for a given input judgment is useful to legal practitioners. The inherent complexity of a legal judgment requires effective and efficient ways to extract relevant legal judgments for a given input judgment. Legal judgments contain text and citation information which can be exploited for finding relevant legal judgments for a given input judgment. In the literature, efforts have been made to exploit the text and citation information for finding similarity between the pairs of judgments. In this thesis, we show the potential of citation information in the judgments, in finding similar judgments through cluster analysis and for ranked retrieval of relevant legal judgments. Firstly, we analyzed how the citation information could be helpful in finding similar legal judgments. Link information has been exploited extensively in the web domain for search and retrieval systems. Similarly, citation information in the legal judgments can be exploited for building efficient search systems in the legal domain. We developed a clustering approach to cluster judgments having only citation information. We have conducted experiments on real world legal judgment dataset delivered by Supreme Court of India. The clustering results indicate that the citation information is helpful in finding clusters of judgments. As the naturally available citations are sparse, we also exploit the notion of paragraph links to increase the number of citations in the judgments and reported the corresponding clustering results. Further, we have made an effort to show the potential of citation information in the ranked retrieval of relevant legal judgments for a given judgment. Efforts are being made to build efficient search systems that extract legal judgments for a given input query by extending the traditional information retrieval approaches. Intricate legal concepts are discussed at a granular level in the legal judgment documents. In addition to citation information, we exploit the paragraph-level information of the judgments for ranked retrieval of relevant legal judgments for a given input judgment. Instead of considering the entire text document for comparison, we find the aggregate relevance between judgments by computing the relevance at paragraphs of the judgments based on the Okapi retrieval model. User evaluation study on the real world legal judgment dataset shows that the citation based approach improves the performance by combining with Okapi retrieval model. Overall, we conclude that citation information available in the legal judgments can be exploited for finding similarity among legal judgments.

Abstract

Recently representation learning has been receiving much attention from both industrial and academic communities. Thanks to the advent of powerful GPUs and advanced techniques like dropout and rectified linear units, the interest in neural networks has been revived. The current state-of-the-art solution for the applications in the field of Natural Language Processing (NLP) and Information Retrieval (IR) is powered by neural network based representation learning models. In this thesis, we focus on the unsupervised representation learning models which are cheap to build (as they rely on unlabeled data) but very effective for many downstream applications. We explore two main challenges in building an unsupervised representation learning model for NLP and IR problems. Context serves as the source of knowledge for estimating the representation of data. For example, in Word2Vec, the context is the set of words surrounding a given word in a sentence. The first challenge we focus is the context insufficiency problem. For instance, consider the models used in practise to generate representations for tweets. We observe that tweets do not exist in isolation, and hence the performance of the models which work only with the content of the tweet (as context) is found to be sub-optimal. To handle this issue, we propose a better model which also captures the interactions between the tweet and its adjacent tweet (as context) in the users’ timeline. Along similar lines, we explore two more use cases where we smartly incorporate novel contexts that captures complex interactions such as scientific author and his/her paper interaction in an author collaboration network (‘Author2Vec’) and sentences interaction in a document (‘Doc2Sent2Vec’), that turned out to be advantageous in computing accurate author and document representations respectively. We conclude that if we smartly leverage the available contexts, the performance of the model improves significantly. Though the representation learning models perform well in practise, little is known about the core properties of the data encoded within the representations. Understanding these core properties would empower us in making generalizable conclusions about the quality of the representations. Hence, the second challenge we focus is the human interpretability problem with these automatically learned representations. For instance, researchers in Twitter analytics are getting interesting results by applying different representation learning models for several valuable tasks such as sentiment analysis, semantic textual similarity computation, microblog retrieval, hashtag identification and so on. In order to understand the core properties encoded in a tweet representation, we evaluate the representations to estimate the extent to which it can model each of those properties such as tweet length, presence of words, hash-tags, mentions, capitalization and so on. This is done with the help of multiple classifiers which take the representation as input. Essentially, each classifier evaluates one of the syntactic or social properties which are arguably salient for a tweet. The result is an application independent, fine-grained analysis of tweet representations generated by different representation learning models. This thesis is one of the initial work to overcome the above-mentioned challenges by proposing novel methods to improve the contexts and interpret the representations. In the growing body of representation learning research, the set of models and framework proposed in this thesis could act as the basic building blocks in the future works attempting to advance the science of building smarter NLP/IR systems.

Abstract

In the era of globalization, vast amount of information is available on World Wide Web. This information is available in various natural languages. In order to access this information, the speakers of different languages have to rely on translation or learn the other language. Learning multiple languages is not feasible for everyone, hence the need of translation arises. In such a scenario, machine translation emerges as an important discipline in the field of computational linguistics that can give access to the vast information within a short time and at low cost. Translating natural languages automatically is one of the most complex and comprehensive applications of computational linguistics [63], and the dream of a perfect fullscale machine translation system still remains an intellectually challenging task. Several approaches, such as rule based, statistical and hybrid, have been tried out to build linguistic tools. All these approaches have their own merits as well as demerits. Pān.inian Grammar, universally admired for its insightful analysis of Sanskrit [74], offers a perspective to language analysis. The main focus of Pān.inian Grammar is to explain how, where and how much information a language encodes that helps in capturing information dynamics in a language [3]. In order to use Pān.inian theory to analyse other languages, it is necessary to model these languages in terms of Pān.inian primitives. We have selected the primary basic notions such as nominal inflections (sup), verbal inflections (tiṅ), basic grammatical constructions (pada), compound constructions (samasta-pada), etc., to analyse the syntax and semantics of natural language sentences. In our research, we have used these concepts to analyse English from Pān.inian perspective and then map English structures into Hindi for handling three major linguistic tasks for English-Hindi machine translation as follows: 1. Finding Out the Meaningful Linguistic Units That Can Participate in a Sentence: This step theoretically accounts for English sentence in terms of Pān.inian primitives such as sup, tiṅ, pada and samasta-pada. Here we find out the syntactic and semantic units called padas and samasta-padas and the grammatical markings that connect these units, the padas and samasta-padas with the other meaningful units in a sentence. Such analysis looks at the words in a sentence as a combination of content words and grammatical markings [125]. Thus, this type of syntactic analysis helps in capturing the flow of information and gives us the shallow parse of the sentences. It is also helpful in various other linguistic tasks such as dependency parsing, word ordering and case marking. 2. Mapping Dependency Parsers’ Output into a Uniform Notation: Parsers play an important role in analyzing the exact meaning of a sentence. The parse tree produced by the parsers formally represents syntactic and semantic information among the words in a sentence. In a machine translation system, various modules like Gender Number Person (GNP) agreement, Word Sense Disambiguation (WSD), reordering of the source language sentence according to target language sentence, etc. are some of the important tasks which require dependency parse as input [89]. Several dependency parsers are available for English viz. Stanford Parser, Link Grammar Parser, CLEAR Dependency Parser, Minipar, Malt and many more [119, 47, 36, 85]. However, no two dependency parse output formats match with each other. These parsers differ on the names of the dependency labels, their representation style and the number of dependency labels [17]. Since the parsers are based on different approaches, and each approach has its own limitations, the parsers produce different degrees of output quality for different syntactic constructions. In order to obtain maximum benefit out of these parsers, one has to combine the strengths of the parsers [24]. Hence arises the need of a common representation schema. Also, the use of computers as an information processing device requires a sophisticated theory for processing the information in a language. Bringing the parsers’ output into one uniform notation provides the system an ability to plug-in any of these parsers without modifying other translation modules, thereby avoiding large amount of manual work that is costly as well as time consuming. 3. Framing Transfer Grammar Rules: Word ordering plays an important role in the translation process between languages. Using the concept of pada and samasta-pada, the source language sentence is manipulated into target language sentence for natural translation. Since the notion of pada overtly identifies the grammatical markers and their respective content words as syntactic units of a sentence, we get a little more freedom for word ordering as an advantage due to the relatively free word order nature of the target language Hindi [23]. The concept of pada also helps in generating direct