Abstract

The rapid advancement of Transformer-based models has transformed natural language processing (NLP), yet their application to low-resource Indic languages remains underexplored, limiting equitable access to digital knowledge. This thesis investigates the encoding capabilities and robustness of multilingual Transformer models for Indic languages, culminating in practical NLP applications to enhance knowledge accessibility. By addressing linguistic diversity and digital inclusion, the study aligns with the urgent need to bridge information gaps for millions of Indic language speakers, particularly in India, where regional languages like Telugu face significant resource constraints. Our work begins by introducing INDICSENTEVAL, a novel dataset with approximately 47,000 sentences across six Indic languages—Hindi, Telugu, Marathi, Kannada, Urdu, and Malayalam. This dataset enables a comprehensive probing analysis of nine multilingual Transformer models (seven universal, two Indic-specific) across eight linguistic properties, including surface, syntactic, and semantic features. The findings reveal that while models encode English properties consistently, performance for Indic languages varies, with Indic-specific models outperforming universal ones. Extending this analysis, our study evaluates model robustness against 13 perturbations, such as word dropping and shuffling, finding that universal models exhibit greater resilience, particularly under noun and verb perturbations. These insights, detailed in Chapters 3 and 4, highlight model-specific strengths and weaknesses, informing robust NLP system design. Moreover, the development of IndicSentEval and the resulting insights into model behavior underscore the critical role of digitized linguistic data in enabling effective downstream NLP tasks for low-resource languages. Building on these findings, the thesis develops a practical application to enhance Telugu Wikipedia, addressing the knowledge access gap for 95.7 million Telugu speakers. Leveraging NLP techniques like translation, transliteration, and template generation, the study generates 8,929 high-quality moviedomain articles, adhering to Wikipedia’s standards for word count, images, and infoboxes. This contribution, detailed in Chapter 5, demonstrates the real-world impact of robust NLP systems, fostering digital inclusion for low-resource language communitie

Abstract

The proliferation of user-generated content on microblogging platforms like Twitter and via SMS has created a wealth of short-form, opinionated data. However, the noisy, concise, and context-dependent nature of this text presents significant challenges for traditional sentiment analysis techniques. This thesis addresses the task of sentiment polarity classification for short expressions by conducting a systematic, two-stage investigation into feature engineering, moving from surface-level patterns to deep syntactic analysis. The initial phase of our research investigates the effectiveness of three feature categories: (1) phraselevel prior polarity features derived from established resources like SentiWordNet and custom-built lexicons for emoticons and interjections; (2) Part-of-Speech (POS) tag pattern features; and (3) noisy data-specific features. Using a Naive Bayes classifier on the SemEval-2013 dataset, our initial experiments revealed that while these features provide a strong baseline, they have limitations. Specifically, while POS tag patterns offered a boost for subjectivity classification (distinguishing objective vs. subjective text), their impact on polarity classification (positive, negative, neutral) was minimal. This highlighted a key weakness: an inability to robustly model complex contextual phenomena like negation and modification, resulting in lower performance for negative expressions. To address these shortcomings, the second and primary phase of this thesis introduces a novel approach centered on Phrase Dependency Parsing. By extending traditional word-level dependency parsing to the phrase level, we combine the relational benefits of dependency graphs with the structural awareness of constituency trees. This method allows us to first define a precise contextual boundary for a given expression within its parent sentence. From this pruned, context-aware sub-tree, we extract a new set of powerful Syntactic Dependency Features, including a Phrase Path, a Sentiment Phrase Path, and a crucial Subject Negation feature. By integrating these syntactic features and employing a more powerful Support Vector Machine (SVM) classifier, our system’s performance improved dramatically. The average F1-score on the Twitter dataset jumped from 0.744 to 0.863. Most notably, the F-measure for the challenging negative class saw a substantial increase from 0.676 to 0.834. This result strongly validates our central hypothesis: a deep understanding of syntactic structure is essential for accurately classifying sentiment in short, noisy text. This work demonstrates that moving beyond surface-level features to incorporate linguisticallyinformed, dependency-based features is a critical step in overcoming the challenges of contextual polarity

Abstract

This thesis investigates two aspects of how humans engage with visual content: how it is described and how it is remembered. The first part focusses on Audio Descriptions (ADs), which convey essential on-screen information, allowing visually impaired audiences to follow videos. To be effective, ADs must form a coherent sequence that helps listeners visualise the unfolding scene, rather than describing isolated moments. However, most automatic methods generate each AD independently, often resulting in repetitive, incoherent descriptions. To address this, we propose a training-free method, CoherentAD, that first generates multiple candidate descriptions for each AD time interval, and then performs auto-regressive selection across the sequence to form a coherent and informative narrative. To evaluate AD sequences holistically, we introduce a sequence-level metric, StoryRecall, which measures how well the predicted ADs convey the ground truth narrative, alongside repetition metrics that capture the redundancy across consecutive AD outputs. Our method produces coherent AD sequences with enhanced narrative understanding, outperforming prior approaches that rely on independent generations. The second part investigates Video Memorability. Understanding what makes a video memorable has important applications in advertising and education technology. Towards this goal, we investigate spatio-temporal attention mechanisms underlying video memorability. Different from previous works that fuse multiple features, we adopt a simple CNN+Transformer architecture that enables analysis of spatio-temporal attention while matching state-of-the-art (SoTA) performance on video memorability prediction. We compare model attention against human gaze fixations collected through a small-scale eye-tracking study where humans perform the video memory task. We uncover the following insights: (i) Quantitative saliency metrics show that our model, trained only to predict a memorability score, exhibits similar spatial attention patterns to human gaze, especially for more memorable videos. (ii) The model assigns greater importance to initial frames in a video, mimicking human attention patterns. (iii) Panoptic segmentation reveals that both (model and humans) assign a greater share of attention to things and less attention to stuff as compared to their occurrence probability

Abstract

This thesis investigates how entities are shaped by the discourse in which they appear. Rather than being isolated mentions, entities take on meaning through their interactions with the surrounding context, both in terms of reference and interpretation: the identity of an entity can shift depending on how it is invoked, and the narrative framing around it can significantly influence how it is perceived by a reader. At its core, the research addresses these two complementary dimensions of entity analysis: the challenge of tracking entity references across text (coreference resolution) and the interpretive challenge of understanding how entities are characterized through their framing within the text (entity role classification). While these tasks represent distinct technical problems, they are unified by their contribution to richer discourse comprehension and their shared goal of moving NLP systems beyond surface-level language processing toward deeper semantic understanding. The first part of this research focuses on coreference resolution for South Asian languages, addressing a significant gap in current NLP research where these morphologically rich and syntactically diverse languages remain underrepresented. To overcome the lack of suitable evaluation resources, we develop mGAP, a novel dataset containing coreference annotations across 27 South Asian languages, created through a dedicated translation and alignment pipeline from English reference data. This dataset provided the foundation for investigating cross-lingual transfer learning strategies designed to address the low-resource nature of many of these languages. Through systematic experimentation, we examine which languages serve as effective source languages for training when target language data is scarce, offering insights into making use of linguistic similarities for enhanced cross-lingual adaptation. The second part shifts focus to entity framing in news media, where the research question evolves from identifying what an entity refers to, to understanding what narrative role that entity plays within the text. The framing of the text is pivotal in how a reader would perceive the entity being described. For this task, we developed a two-stage pipeline for classifying entities into roles such as protagonist, antagonist, and innocent, as well as more fine-grained narrative categories. The pipeline first employs entity-centric summarization to extract relevant contextual information surrounding target entities, followed by classification using a DeBERTa v3-based model enhanced with contrastive learning techniques. This approach addresses the significant challenge of determining how entities are portrayed based on surrounding textual cues, contributing further to computational methods for analyzing media bias and narrative construction.

Abstract

India is experiencing an innovation upswing in many fields such as: pharmaceuticals, agriculture, space technology and especially in the area of IT/computer science. The Indian IT industry has a lot to offer: lower human resource costs, large talent pool, favourable government policies, access to capital, and advanced infrastructure that makes India the cost-effective Silicon Valley of the world. It also hosts a significant number of world-class research institutions producing handsome volumes of deep-tech computer science research. However, it has been observed that much of this research is unable to productise and become usable for markets in the real world This has resulted in a high volume of research with potential to disrupt markets but fail to carry through the ‘lab to land’ journey for a research output. This thesis is a study to understand the translation process of a research as a marketable product and to identify factors that impede or enable this translation. The productisation window for any relevant computer science research work is largely time sensitive. [1] Recent explosion in AI adoption fueled with a digital infrastructure has made many deep-tech Computer Science research areas to get production ready very fast. It has an associated shelf life during which it should be explored and leveraged for any sort of translational or productisation activity. Therefore, as a community engaging closely with research problems bridging disconnections between research labs and industry/market requires critical and timely interventions. While there are many research translation models available as a concept or practice, many are ineffective in explaining a seamless / smooth transition of any research work into an industry-consumable technology or product. Based on tacit knowledge & existing models of translation it is apparent to observe that due to the nature of the research ecosystem, its processes and the associated stakeholders within it, identifying potential translation flow is far from trivial. In order to understand the entire journey of a potential research translation, this thesis proposes a productisation flow that considers all potential channels through which a research work in computer science can transition into a market relevant product or an industry consumable technology. This thesis will cover the productisation flow in detail in the later chapters. In this study, we focus on understanding this gap in productisation from the perspective of research scholars who actually work on these projects. After an extensive literature study, the thesis focuses on highlighting the gap in considering ‘researchers’ as an active stakeholder in this entire productisation process. As a result, this thesis proposes a productisation flow of deep-tech research from lab to market translations that highlights the participation of researchers across various translational channels and their stages. This qualifies the need to understand reasons why research flow from lab to land is enabled or inhibited wrt researchers.

Abstract

This study critically analyses portrayals of masculinity on Over The Top (OTT) platforms in India, which have seen a marked rise in viewership since the beginning of the COVID-19 pandemic. Netflix, currently the largest investor in original content in India, offers a range of curated material in 31 languages. Masculinity over the years in Indian cinema, particularly the Bollywood industry, has largely been portrayed through hegemonic notions of normativity. Through simple distinctions between good and bad, a clear contrast is set up between a hero and an anti-hero. R. W. Connell suggests a hierarchy of masculinities, in the middle of which lies Marginalised Masculinity. This study constructs this marginalised masculinity as working-class. We contend that at the intersection of class and socioeconomic status lies a violent expression of masculinity accepted by the neo-liberal audience of Netflix. The Netflix original productions considered for this study exempt the working-class man from ethical obligations, in his conquest to liberate himself from his class position. Aspirational capitalism makes it okay to be ethically dubious, spawning a troubling masculinity. We use a three-step coding method to substantiate qualitative discourse analysis of Jamtara - Sabka Number Aayega (2020, Soumendra Padhi), Class (2023, Ashim Ahluwalia), and The White Tiger (2021, Ramin Bahrani).

Abstract

The swift advancement of vehicular edge computing (VEC) has made task offloading to roadside units (RSUs) an essential solution for addressing the computational demands of modern vehicular applications. However, efficiently partitioning and scheduling tasks across RSUs in dynamic environments remains a significant challenge. Traditional static or heuristic-based scheduling methods often struggle to adapt to dynamic vehicular networks, which leads to reduced resource utilization, increased latency, and reduced task completion rates, particularly in high-density scenarios. In this thesis, we explore the benefits of partitioned scheduling for computation offloading from multiple vehicles to RSUs, focusing on two key strategies: Fully Partitioned Scheduling (FP-Sched) and Hybrid Partitioned Scheduling (HP-Sched). These strategies are designed to handle the challenges posed by vehicle flow constraints, edge resource limitations, and bandwidth schedulability. By leveraging realworld vehicular datasets and simulations, we demonstrate that the proposed algorithms significantly improve task completion rates and reduce latency compared to traditional approaches. To further increase the adaptability and schedulability of vehicular tasks, we introduce HAPTA (Horizontal, Adaptive Learning-based, Partitioned, Timeslot-based Algorithm), a novel framework that leverages the Upper Confidence Bound (UCB) algorithm. HAPTA dynamically selects RSUs with optimal resource availability while considering vehicular mobility, task deadlines, and stringent latency constraints. The framework supports horizontal task partitioning, enabling the splitting of tasks into subtasks for efficient resource utilization across multiple RSUs. Experimental evaluations demonstrate that HAPTA outperforms existing heuristic-based methods, achieving up to 96.5% task completion in high-density scenarios while maintaining a substantial speedup over optimal scheduling frameworks. With the growing adoption of Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communication technologies, the proposed framework provides a robust solution for distributed computation offloading in next-generation intelligent transportation systems. This work contributes to the advancement of VEC by offering a scalable, adaptive, and efficient approach to task scheduling, paving the way for seamless integration of autonomous and connected vehicles in smart urban environments.

Abstract

Understanding the complex relationship between brain Structural Connectivity (SC) and Functional Connectivity (FC) remains a central challenge in computational neuroscience. A popular class of approaches models this relationship by simulating diffusion processes on the structural connectome to approximate functional patterns. While prior works have explored such models using fixed or multi-scale Graph Diffusion Kernels, they typically lack spatial specificity, as they do not associate diffusion parameters with individual brain Regions of Interest (RoIs). This limits the biological interpretability and precision of the models. In this work, we introduce a novel framework based on Graph Diffusion Wavelets, which enable learning region-specific diffusion scales to more accurately capture the mapping from SC to FC. By leveraging the multi-scale and localized nature of diffusion wavelets, our method uncovers how spatial communication varies across brain regions. Evaluated on the Human Connectome Project (HCP) dataset, our model achieves a high average Pearson correlation coefficient of 0.833 between predicted and empirical FC, outperforming several existing state-of-the-art methods. Importantly, the proposed architecture is linear and computationally efficient, and it reveals that the distribution of diffusion scales follows a power-law, indicative of scale-free dynamics. This is consistent with known organizational principles of the brain. Notably, we find that the bilateral frontal pole exhibits the largest diffusion scales, suggesting its integrative role within large-scale Resting-State Networks (RSNs). These findings align with previous literature on the frontal pole’s role in high-level cognitive functions. Overall, our results highlight the potential of graph diffusion wavelets as both a predictive and interpretable tool for studying brain structure-function coupling. The thesis also includes application of spectral graph theoretic method to relate the structural features like curvature to physiological traits like age and sex. Finally, the thesis is concluded by summarizing and proposing research directions.

Abstract

As machine learning models are increasingly adopted in critical decision-making domains, ensuring their fairness has become a central concern—especially when these systems have the option to abstain from making a prediction. While abstain option classifiers reduce the risk of error by deferring uncertain decisions, they may inadvertently introduce new forms of unfairness, particularly when abstention rates differ across sensitive groups. This thesis investigates the fairness implications of abstain option classification and proposes methods to mitigate associated disparities. We present EQUISCALE, a unified framework for training fair cost-based abstain classifiers under group fairness constraints. Unlike prior work that focuses exclusively on coverage-based models and single fairness criteria, EQUISCALE introduces fairness-aware loss formulations that extend demographic parity (independence) and equalized odds (separation) to the abstention setting. The approach uses Lagrangian dual optimization to enforce fairness constraints during model training. EQUISCALE is the first method to incorporate multiple fairness criteria simultaneously in abstain classification and to apply the separation criterion in this context. We validate our approach through extensive experiments on five benchmark datasets, showing substantial reductions in fairness violations without compromising classification performance. This work advances the understanding of fair abstention and provides practical tools for deploying equitable machine learning systems in high-risk environments.

Abstract

The profound immersion offered by natural walking in Virtual Reality (VR) is frequently constrained by the limited physical space available to users, hindering the exploration of expansive virtual environments. While various locomotion techniques aim to address this ”room-scale constraint,” they often introduce compromises such as reduced presence, simulator sickness, or an inability to seamlessly revisit previously explored areas. This fundamental mismatch between virtual aspiration and physical reality necessitates innovative solutions that extend navigable space without sacrificing user comfort or experiential quality. This thesis first conceptualizes the Architecturally Consistent Maze Generation for Virtual Reality (ACMGVR) framework, a novel design for the procedural generation of potentially infinite, multipath maze environments. ACMGVR prioritizes strict local architectural consistency (e.g., right-angled corridors) and supports continuous, multi-directional natural walking, including backtracking. This framework explores dynamic spatial assessment techniques to intelligently reuse physical space, laying the theoretical groundwork for creating vast, explorable worlds within confined footprints. Building upon these principles, we developed, implemented, and empirically evaluated the Procedural Overlapping Maze System (POMS). POMS employs a collision-driven, node-based algorithm to dynamically generate architecturally consistent maze sections, facilitating continuous natural walking within a reused physical footprint. A rigorous user study (N=34) comparing POMS against a spatially equivalent static maze demonstrated that POMS successfully maintained user experience (UEQ) and presence (iPQ) at levels comparable to the static condition. More significantly, participants navigating POMS experienced markedly lower increases in key cybersickness symptoms—Oculomotor, Disorientation, and Total SSQ scores—a phenomenon termed ”The POMS Effect.” This research successfully developed an innovative conceptual framework for overlapping virtual environments, translated it into a functional system, and conducted rigorous empirical validation. The findings confirm that strategically designed, dynamically overlapping architectures can not only extend perceived navigable space for natural walking in VR but also substantially enhance user comfort by reducing cybersickness, without compromising core experiential qualities. This work thus offers a validated pathway towards creating more immersive, accessible, and sustainable virtual reality experiences.