Abstract

Metabolism is an integral part of cellular physiology, with the liver as the central organ for a wide range of metabolic functions and homeostasis. The liver, unlike other organs, has a remarkable capacity to regenerate after partial loss of its mass, thus maintaining a constant liver-to-body weight ratio to preserve homeostasis. In an injury-free liver, the turnover of regeneration is very slow, but in the presence of an injury or perturbation, the regenerative response is triggered as a reparative strategy. Perturbations interfering with liver functions and disturbing the homeostatic state have serious repercussions leading to metabolic disorders like hepatic steatosis, non-alcoholic fatty liver disease (NAFLD), non-alcoholic steatohepatitis (NASH) and hepatocellular carcinoma (HCC). Ageing is one risk factor that increases the susceptibility to these diseases. The regenerative ability of the liver has been used to treat these diseases in the form of liver transplantation and partial liver resection, but recurrence of the disease is often observed after a few years. Understanding the molecular network that controls liver function and its regenerative ability in health and disease is crucial for developing clinical applications. The emergence of high throughput omics technologies provides a scope to develop a systems-level understanding of the disease. In this direction, we attempt to understand the pathophysiology of the liver by adopting systems biology approach for omics data interpretation. Tissue homeostasis and regeneration depend on the reversible transitions between quiescence (G0) and cell proliferation. During regeneration, the liver needs to maintain the essential metabolic tasks along with the fulfilment of metabolic requirements for hepatocyte growth and division. To understand the regulatory mechanisms involved in balancing the liver function and proliferation demand after injury or resection, we analyzed RNA sequencing temporal data of liver regeneration after two-thirds partial hepatectomy (PH) using network inference and mathematical modelling approaches. The reconstruction of the dynamic regulatory network revealed the overall temporal coordination of metabolism, RNA splicing and cell cycle during liver regeneration. A temporal shift in the gene expression pattern corresponding to increased hepatocyte proliferation and decreased hepatocyte function is observed with HNF4A as a key transcriptional activator. Based on these key observations, we developed a mathematical model of the HNF4A regulatory circuit, which showed the emergence of different states corresponding to compensatory metabolism, proliferation, and epithelial-to-mesenchymal transition. We showed that a mutually exclusive behaviour emerges due to the bistable inactivation of HNF4A, which controls the initiation and termination of liver regeneration and different population-level behaviour. Through our approach of modelling a regulatory circuit from high-throughput gene expression data, we proposed a mechanistic explanation of different states observed in single-cell RNA sequencing data of liver regeneration. The functional impairment of the liver with ageing reduces its regenerative capability and predisposes it to NAFLD and HCC. Mapping the molecular network of the liver encompassing these physiological (ageing) and pathological conditions may help to understand the crosstalk of ageing with different liver diseases. We performed networklevel analyses by integrating mouse transcriptomic data with protein-protein interaction (PPI) network. A sample-wise analysis using network entropy measure was performed, which showed an increasing trend with ageing and helped to identify ageing genes based on local entropy changes. To gain further insights, we also integrated the differentially expressed genes (DEGs) between young and different age groups with the PPI network and identified core modules and nodes associated with ageing. Finally, we computed the network proximity of the ageing network with different networks of liver diseases and regeneration to quantify the effect of ageing. Our analysis revealed the complex interplay of immune, cancer signalling, and metabolic genes in the ageing liver. We found significant network proximities between ageing and NAFLD, HCC, liver damage conditions, and the early phase of liver regeneration with common nodes, including NLRP12, TRP53, GSK3B, CTNNB1, MAT1 and FASN. A common theme involving pathways in cancers connects ageing, regeneration and liver diseases. Overall, our study maps the network-level changes of ageing and their interconnections with the physiology and pathology of the liver. While the regulated process of liver regeneration is crucial for damage-induced repair, its dysregulation may lead to HCC, the most common type of liver cancer. Understanding the molecular pathogenesis of HCC sequentially from precancerous state to cancer

Abstract

Cognitive and psychological studies on human reading indicate that the effort required to read and understand text increases with sentence complexity (Klein and Kurkowski, 1974). Modern natural language processing (NLP) applications face similar challenges. Processing complex sentences with high accuracy remains difficult in computational linguistics, necessitating automatic sentence simplification techniques (Chandrasekar et al., 1996). Sentence complexity can be classified into �lexical complexity� and �syntactic complexity�. Lexical complexity can be managed by utilizing resources like lexicons, dictionaries, and thesauruses to replace infrequent words with common ones. To address syntactic complexity, analyzing sentence structure and applying simplification operations is essential. There are many applications of sentence simplification in NLP. Machine translation systems struggle with long, complex sentences, especially when dealing with divergent language pairs. For parsing, (McDonald and Nivre, 2007) showed that syntactic parsing of long sentences and identifying long-distance dependencies remain challenging. Simplifying sentences can aid parsing and machine translation by breaking down sentences into smaller parts. In automatic summarization, simplification can improve accuracy by extracting smaller units of information. In this work, we studied and analyzed existing sentence simplification methods for Hindi. We developed new approaches, both rule-based and statistical, to design a better system that overcomes the limitations of existing systems while improving quality and readability. As an application, we examined the effects of sentence simplification on Hindi to English machine translation systems.

Abstract

Recommender systems play a crucial role in guiding users towards items they are likely to appreciate (13). Traditional collaborative filtering (CF) methods have been widely used (1), but they often face challenges such as data sparsity and cold start problems (10). This research explores the integration of category-specific algorithms with traditional CF to enhance the performance of recommender systems. By considering item categories, we aim to create hybrid models that leverage the strengths of both approaches, resulting in more accurate and personalized recommendations. Our study is grounded in the extensive evaluation of different models, including user-based CF (2), category-based CF (CCF), and a hybrid model combining both approaches (3). We utilized the MovieLens 1M dataset, which contains over a million ratings from thousands of users, to validate our models. The performance of these models was assessed using precision, recall, and F1-score metrics, which are standard measures in recommender system research. The results indicate that incorporating category-specific information significantly improves the performance of recommender systems. The CCF model outperformed the traditional CF model, demonstrating the value of considering item categories. Furthermore, the hybrid model, which combines CF and CCF, achieved the highest performance, illustrating the effectiveness of leveraging the strengths of both methods. This research contributes to the field of recommender systems by providing a novel approach that enhances recommendation accuracy and personalization. The findings suggest that integrating categoryspecific algorithms with traditional CF methods can lead to significant improvements in recommendation performance, offering valuable insights for future research and practical applications in various domains such as e-commerce, streaming services, and social media platforms.

Abstract

Accidental fires in public and large buildings pose significant risks, demanding effective evacuation strategies to ensure the safety of occupants and minimize property loss. This study aims to address the challenges associated with building evacuations by integrating spatial, temporal, and path planning approaches specifically for 2D building plans. By incorporating a geospatial framework, the study enables the evaluation of dynamic changes in the building environment and their impact on evacuation outcomes. The current studies do not show how the cascading effect of the person in the queue and space constraints, static or dynamic, affect the evacuation times and can exacerbate the disaster. Also, the presence of multiple exits, if any, can change the outcomes. This research studies how spatial arrangement and floor plans play an important part in evacuation strategies and advocates for their integration into building planning and design processes. The study delves into the impact of obstacles on evacuation processes, by introducing a subspace model that significantly improves computation time in various geometric spaces. The findings emphasize the hindrance of obstacles, either static or dynamic, on evacuation efficiency and propose efficient path generation to mitigate increased evacuation times. The primary objective of this study is to evaluate dynamic changes in the building environment during evacuations and assess their impact on evacuation outcomes. It also addresses the challenges associated with building evacuations during accidental fires in public and large buildings. The focus is on ensuring occupant safety and minimizing property loss by developing effective evacuation strategies. The technical approach adopted in this study involves the integration of spatial, temporal, and path planning methodologies for 2D building plans within a geospatial framework. The study employs a computational approach that combines occupancy-based path planning. This allows for a complete evaluation of dynamic changes in the building environment, highlighting the interactions between individuals and their chosen paths toward their respective exits. Notably, the study focuses on time-dependent path planning to recognize the evolving nature of emergencies, incorporating dynamic elements to enhance the accuracy of evaluating the building environment in emergency scenarios. The study explores the effectiveness of integrating floor plans into path generation and people flow analysis, recognizing the influence of spatial arrangement on evacuation strategies. The proposed method employs a graph-based path generation approach using the subspace model for an effective methodology for evacuating occupants by adapting to changing paths based on a 2D structural plan. The path planning accounts for not just current position to the main exit, but incorporates other conditions like crowding and lag on some path segments, time delays in utilizing alternate exits like windows, and finally reaching to the Evacuation point. The study shows that in comparison to the base scenario, the adverse situation resulted in a more than 12x increase in evacuation time for the 89 building occupants. This underscores the impact of changed dynamics and emphasizes the necessity for well-planned alternative exits with sufficient capacity. The study gives the influence of main exit capacity and alternate exit access time on overall evacuation time, calling for comprehensive evaluation and appropriate definition of capacities for doors and windows. The subspaces offer a clear line of sight to the exit and are integral to the evacuation path. In scenarios with obstacles, the approach, where the main door served as the primary exit, resulted in only a marginal increase of 215 seconds for 70 occupants compared to clear spaces. However, when obstacles led to disconnection of the network, alternate exits like windows were used, causing an almost 4x rise in evacuation time to 996 seconds in Case 2. In cases with critical node blockage, the last person took around 1295 seconds to exit, a 6x increase compared to the base scenario with obstacles. This gives the need for strategic planning of alternate exits to reduce delays and optimize people flow rates. The study called for further work to seamlessly integrate the proposed method with static and dynamic components of indoor spaces, emphasizing the development of an occupant-friendly information dissemination model. The use of an agent-based model facilitated dynamic decision-making and adaptation to changing graph networks. The study's technical approach thus encompasses a holistic evaluation of evacuation strategies, considering spatial path planning aspects, with practical implications for building design and emergency planning. In conclusion, this study significantly advances the field of evacuation planning and modeling by addressing the complexities as

Abstract

Unmanned Aerial Vehicles (UAVs), commonly known as drones, have revolutionized various sectors including surveillance, agriculture, and disaster management due to their versatility and maneuverability. Hexacopter UAVs, equipped with six rotors, offer enhanced stability and payload capacity compared to their quadcopter counterparts. However, their operational effectiveness is contingent upon reliable fault detection and isolation mechanisms. In the dynamic operational contexts of hexacopter UAVs, potential faults such as motor failures, sensor malfunctions, or communication disruptions can lead to catastrophic consequences including loss of control, collisions, or data loss. Detecting and isolating these faults accurately and swiftly is imperative to ensure safe and efficient UAV operations. Our objective is to improve the reliability and accuracy of fault detection and isolation for a single motor failure in hexacopter UAVs. Commencing with a foundational exposition on hexacopter UAV dynamics, prevalent fault conditions, and classical machine learning classifiers, the research subsequently introduces LSTM networks and conducts a review of pertinent literature in fault detection and isolation, laying the groundwork for the proposed methodology. The principal contribution of this thesis revolves around the formulation of a fault detection and isolation paradigm that combines LSTM networks for latent temporal feature extraction with ensemble classifiers, notably Random Forests, aimed at enhancing fault detection efficacy. By harnessing the temporal intricacies inherent in UAV data using LSTM networks, the proposed model exhibits robust performance under measurement noise in fault detection and isolation tasks. The evaluation of the proposed approach encompasses comprehensive analyses conducted on synthetic and real-world datasets, encompassing examinations of noise resilience, fault detection and isolation timing, and the deployment on resource-constrained platforms such as the Raspberry Pi. Comparative assessments are conducted with benchmark models from both classical and deep learning domains, wherein our proposed approach demonstrates superior performance with an accuracy of 96.8% for stimulated datasets and 83.2% for real-world datasets. Furthermore, noise analysis highlights the resilience of our proposed method across varying noise intensities, underscoring its adaptability and robustness. The analysis conducted on synthetic data serves as a crucial validation step, instilling confidence in the model�s efficacy for real-world applications where data collection is inherently challenging. Subsequent experiments investigate fault detection and inference times, yielding insights into the temporal efficiency of the proposed approach. On an onboard microcontroller like the Raspberry Pi, the average inference time for our model is measured at 6.512 milliseconds, with additional statistical analyses providing further insights into performance metrics such as minimum and maximum algorithm run time and delay in prediction, alongside standard deviation. In conclusion, the thesis summarizes key findings and contributions, emphasizing the efficacy of the proposed approach in enhancing fault detection and isolation in hexacopter UAVs. Furthermore, it outlines potential avenues for future research, thereby underscoring the practical applicability of advanced machine learning techniques within real-world UAV systems. In essence, this thesis presents a novel fault detection and isolation framework that integrates LSTM networks with ensemble classifiers, thereby advancing fault detection and isolation capabilities in hexacopter UAVs operating in real-world scenarios

Abstract

The relentless growth of scholarly publications, exemplified by the annual publication rate exceeding 5 million articles, has posed a formidable challenge for researchers seeking efficient literature review methodologies. Systematic Literature Reviews (SLRs), crucial for understanding existing knowledge and identifying research gaps, are hindered by the manual extraction of information, contributing to extended timelines and potential obsolescence. This thesis addresses the urgent need for improved literature review methodologies by focusing on two challenges: Cited Text Span Retrieval (CTSR) and Named Entity Recognition (NER). CTSR involves identifying cited text spans, facilitating the tracing of information origin, while NER identifies and categorizes entities within the text. In this thesis, we introduce CitRet, a hybrid model for CTSR, leveraging semantic and syntactic characteristics of scientific documents and outperforming existing methods on the CLSciSumm shared tasks. Using only 1040 documents for finetuning, CitRet achieves a remarkable over 15% improvement in the F1 score evaluation. Further, we explore Complex NER for English, a non-trivial task of identifying rare and semantically ambiguous entities. Utilizing pre-trained language models, our models consistently outperform the baseline, with the best model advancing the baseline F1-score by over 9%. Expanding our scope to complex NER for low-resource languages, we leverage pre-trained language models for Chinese and Spanish. Employing Whole Word Masking (WWM) to enhance the Masked Language Modeling objective, our models, incorporating CRF, BiLSTMs, and Linear Classifiers, outperform the baseline by a significant margin. The best-performing model attains a competitive position on the evaluation leaderboard for the blind test set. This work aims to catalyze further research in the challenging domain of ambiguous, low-resource, complex NER. By addressing CTSR and NER, our thesis contributes significantly to the broader goal of enhancing systematic literature reviews (SLRs). Integration of these tasks provides a structured and comprehensive approach to navigating the vast scientific publication landscape, easing the burden on researchers and promoting a more efficient dissemination of knowledge.

Abstract

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect. Such manipulated data can cause adverse effects like vulnerability to backdoored samples, systematic biases, and in general, reduced accuracy on certain input domains. Machine Unlearning, traditionally studied for handling user data-deletion requests to provide privacy, can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving perfect unlearning is computationally expensive; consequently, prior works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms. In this thesis, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods (EU-k and CF-k) which outperform several popular inexact unlearning methods. We demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms. Next, we study the practical constraint that model developers may not know all manipulated training samples. Often, only a small, representative subset of the affected data is flagged. We formalize �Corrective Machine Unlearning� as the problem of mitigating the impact of data affected by unknown manipulations on a trained model, possibly knowing only a subset of impacted samples. We demonstrate that the problem of corrective unlearning has significantly different requirements from traditional privacyoriented unlearning. We find most existing unlearning methods, including the gold-standard retrainingfrom-scratch, require most of the manipulated data to be identified for effective corrective unlearning. However, one approach, SSD, achieves limited success in unlearning adverse effects with just a small portion of the manipulated samples, showing the tractability of this setting. We hope our work spurs research towards developing better methods for corrective unlearning. Finally, we demonstrate the use of unlearning in reducing the risk of Large Language Models assisting malicious use in the creation of bioweapons and cyberattacks. Adaptations of existing state-of-the-art unlearning techniques fail on this task, probably due to complexities introduced by not having access to training data that leads to such capabilities. We discuss Contrastive Unlearning Tuning (CUT), a Representation Engineering based unlearning method that steers models towards novice behaviour on potentially harmful dual-use knowledge, while retaining general model capabilities. We design a probing evaluation which shows CUT succeeds in removing this knowledge even from the internal layer representations of LLMs. Overall, this thesis attempts to extend the frontiers of unlearning from user-privacy applications to debiasing, denoising, removing backdoors, and removing harmful dual-use capabilities. We highlight the shortcomings of privacy-oriented unlearning methods and formulations in achieving these goals. We hope our work offers practitioners a new strategy to handle challenges arising from web-scale training, and post-training line of defense towards ensuring AI Safety.

Abstract

Knowledge graphs (KG), which are structures representing information corresponding to entities/topics and their inter-connections, have been playing a crucial role in leveraging information on the web for several downstream tasks such as text-generation, classification, etc. Hence, it becomes vital to construct and maintain such knowledge graphs. There are some previous efforts in populating such KGs and generating relevant entity/node embeddings for this task. However, these methods typically do not focus on analyzing entity-specific content exclusively, but rely on transformational techniques on a fixed collection of documents with certain entities. We define an approach to populate such KGs by utilizing entity-specific content on the web, for generating category-specific entity embeddings. We empirically prove our approach�s effectiveness, by utilizing it for a downstream task of Notability detection, associated with one of the most popular and important Knowledge Graphs - the Wikipedia platform. Wikipedia is a highly essential platform because of its informative, dynamic, and easily accessible nature. The rate of new content being uploaded to it is very high, which makes it essential to moderate this uploaded content. To ensure that only important and relevant content is uploaded to Wikipedia, its editors define a specific set of "Notability" guidelines. These guidelines indicate whether a particular title warrants its own Wikipedia article. So far notability is enforced by humans, which makes scalability an issue, and there has been no significant work on automating notability detection across diverse categories. We work on this problem of creating an automated system to detect the notability of different types of articles/pages, for a vast set of categories. It is not a trivial task to define a fixed procedure for determining the Notability of Wikipedia pages, as there are different types of pages in Wikipedia, in the way they correlate with the various categories in which they exist. For a given Wikipedia category, articles/pages that are simple category instances co-exist with pages that are associated with the category in a non-trivial manner. It is essential to distinguish Wikipedia pages based on this fundamental difference, to gauge the notability of the page accordingly, as the parameters to look for performing this Notability test vary in each case. We divide this problem into two components, based on the nature of an article�s title. We define two types of article titles - Simple titles and Complex titles. Simple titles correspond to simple category instances/named entities for a given category. For example, "Virat Kohli" is a simple title of the category "Cricket Players". Complex titles correspond to article titles that have complex dependencies with their category. For example, an article titled "Wake Island" might be present in the "Birds" category, because of its association with the category, but not because it represents an instance of a bird. This distinction helps us define the categories to analyze for generating category-specific embeddings. Articles with simple titles are further divided into two classes, the "Abstract" class and the "Generic" class, based on whether they represent abstract concepts (such as Temperature / Pressure) or not, respectively, as the process for notability detection is to be followed differently in each case. We construct a dataset with notable and non-notable samples, for 9 categories belonging to the Generic class and 5 categories belonging to the Abstract class. On the other hand, for articles with complex titles, another dataset is constructed for the 9 categories of the Generic class, as defining complex titles for conceptual entities in the Abstract class is non-trivial. We further design a generalizable mechanism to differentiate between simple and complex titles. Initially, we specifically worked on designing a notability detection system for articles with simple titles. This system is based on web-based entity features and their text-based salience encodings. We further incorporate neural networks and BERT encodings (transformer encoder) to perform binary classification. For validating our system�s performance in this task, we utilize accuracy metrics, correlation analysis, ablation study, and prediction confidence on popular Wikipedia pages. Our system outperforms machine learning-based classifier approaches and existing handcrafted entity salience detection algorithms. Further, we define a system to detect notability specifically for articles with complex titles. This system is primarily defined on the basis of web-based features and the salience of a title in its web-based documents� text. We train a Graph neural network (GNN) that generates attention-enhanced encodings for classification, with syntactic and semantic document graphs as inputs. We evaluated this system similar to the above syst

Abstract

The aging of the brain is a complex process shaped by a combination of genetic factors and environmental influences, exhibiting variations from one population to another. This thesis in- vestigates normative population-specific structural changes in the brain and explores variations in aging-related changes across different populations. The study gathers data from diverse groups, constructs individual models, and compares them through a thoughtfully designed framework. This thesis proposes as a comprehensive pipeline covering data collection, modeling, and the creation of an analysis framework. Finally, it offers an illustrative cross-population analysis, shedding light on the comparative aspects of brain aging. In our study, the Indian population is considered as the reference, and an effort is made to ad- dress gaps within this population through the creation of a population-specific database, an atlas, and an aging model to facilitate the study. Due to the challenges in data collection, we adopted a cross-sectional approach. A cross-sectional brain image database is meticulously curated for In- dian population. A sub-cortical structural atlas is created for the young population, enabling us to establish reference structural segmentation map for the Indian population. Age-specific, gender balanced, and high-resolution scans collected to create the first Indian brain aging model. Choosing cross-sectional data collection made sense because data from other populations were also mostly collected in a cross-sectional manner. Using the in-house database for Indian population and pub- licly available datasets for other populations, our inter-population analysis compares aging trends across Indian, Caucasian, Chinese, and Japanese populations. Developing an aging model from cross-sectional data presents challenges in distinguishing between cross-sectional variations and normative trends. In response, we proposed a method specifically tailored for cross-sectional data. We present a unique metric within our comprehensive aging comparison framework to differentiate between temporal and global anatomical variations across populations. This thesis has detailed a comprehensive process to compare the aspects of healthy aging across these diverse groups, ultimately concluding with a pilot study across four different populations. This framework can be readily adapted to study various research problems, exploring changes associated with different populations while considering factors beyond ethnicity, such as lifestyle, education, socio-economic factors, etc. Similar analysis frameworks and studies with multiple modalities and larger sample sizes will contribute to deriving more conclusive results.

Abstract

Factual inconsistencies in text, which include a range of errors from minor inaccuracies to substantial distortions, present a significant challenge in the realm of information dissemination. These inconsistencies, whether unintentional or the result of deliberate misinformation, can lead to a skewed understanding and flawed decision-making. In the context of the vast and complex landscape of digital data, the limitation of traditional verification methods becomes evident, highlighting the need for more advanced solutions. In this thesis, we present and explore three critical problems in this domain, each addressing a unique aspect of content credibility and factual consistency. The first problem we tackled in this thesis is the detection of hostility in online content, specifically focusing on Hindi tweets. Our approach categorizes these tweets into distinct hostile classes: hateful, offensive, defamatory, or fake. We employed pretrained Transformer-based models, particularly IndicBERT, which is adept at processing Hindi text due to its training on a vast corpus of Indian languages. The architecture of our model effectively utilizes information from emojis and hashtags, in addition to the natural language text. A significant enhancement in performance was achieved through Task Adaptive Pretraining (TAPT), leading to increases of 1.35% and 1.40% in binary hostility detection, and improvements of 4.06% and 1.05% in macro and weighted F1 metrics, respectively, for fine-grained classifications. Notably, our system, under the team name �iREL IIIT�, achieved first place in the �Hostile Post Detection in Hindi� shared task at the CONSTRAINT-2021 workshop. The second problem addressed in this thesis delves into the realm of automated fact extraction and verification, a pressing challenge in the digital landscape rife with misinformation. Central to our approach is the innovative Fact Extraction and Verification (FEVER) project, which assesses the veracity of claims against a comprehensive body of evidence from Wikipedia. Our contributions include the development of a specialized retrieval model tailored for the FEVER dataset, a strategic approach to sentence selection for optimal evidence gathering, and an exploration of advanced natural language inference (NLI) models, particularly state-of-the-art transformer models. By integrating these components, we not only refine the process of recognizing textual entailment but also significantly enhance the accuracy and efficiency of automated fact-checking. In tackling the third problem of this thesis, we address the critical issue of detecting and explaining factual inconsistencies in text, a significant challenge in the era of advanced Transformer-based natural language generation models. These models, while adept in tasks like summarization and translation, often struggle with producing hallucinatory and inconsistent content. Our approach introduces the novel Factual Inconsistency Classification with Explanations (FICLE) method. This technique involves a detailed analysis of sentence pairs to identify inconsistency types and provide comprehensive explanations, including inconsistent fact triples, context spans, and entity types. Central to our approach is the creation of the FICLE dataset, extensively annotated to cover a range of inconsistency types and their explanations. Utilizing this dataset, we developed a pipeline comprising four neural models, each designed to focus on specific facets of inconsistency detection and explanation. These models utilize various Transformer-based NLU and NLG architectures, with DeBERTa showing notable effectiveness across most sub-tasks. Our results underscore the effectiveness of this approach, demonstrating high performance in inconsistency type classification and entity-type prediction, with weighted F1 scores of around 87% and 86%, respectively, for these tasks. The detection of context spans, while more challenging, achieved an Intersection over Union (IoU) of approximately 65%, indicating the nuanced complexity of this aspect. The contributions of this research are multi-fold: proposing a new problem in factual inconsistency detection, creating a novel dataset, and establishing a baseline pipeline with high performance in inconsistency-type classification and entity-type prediction.