Knowledge Graphs represent real-world entities and the relationships between them. Multilingual Knowledge Graph Construction (mKGC) refers to the task of automatically constructing or predicting missing entities and links for knowledge graphs in a multilingual setting. In this work, we reformulate the mKGC task as a Question Answering (QA) task and introduce mRAKL: a Retrieval-Augmented Generation (RAG) based system to perform mKGC. We achieve this by using the head entity and linking relation in a question, and having our model predict the tail entity as an answer. Our experiments focus primarily on two low-resourced languages: Tigrinya and Amharic. We experiment with using higher-resourced languages Arabic and English for cross-lingual transfer. With a BM25 retriever, we find that the RAG-based approach improves performance over a no-context setting. Further, our ablation studies show that with an idealized retrieval system, mRAKL improves accuracy by 4.92 and 8.79 percentage points for Tigrinya and Amharic, respectively.

Explainable Artificial Intelligence (AI) focuses on helping humans understand the working of AI systems or their decisions and has been a cornerstone of AI for decades. Recent research in explainability has focused on explaining the workings of AI models or model explainability. There have also been several position statements and review papers detailing the needs of end-users for user-centered explainability but fewer implementations. Hence, this thesis seeks to bridge some gaps between model and user-centered explainability. We create an explanation ontology (EO) to represent literature-derived explanation types via their supporting components. We implement a knowledge-augmented question-answering (QA) pipeline to support contextual explanations in a clinical setting. Finally, we are implementing a system to combine explanations from different AI methods and data modalities. Within the EO, we can represent fifteen different explanation types, and we have tested these representations in six exemplar use cases. We find that knowledge augmentations improve the performance of base large language models in the contextualized QA, and the performance is variable across disease groups. In the same setting, clinicians also indicated that they prefer to see actionability as one of the main foci in explanations. In our explanations combination method, we plan to use similarity metrics to determine the similarity of explanations in a chronic disease detection setting. Overall, through this thesis, we design methods that can support knowledge-enabled explanations across different use cases, accounting for the methods in today's AI era that can generate the supporting components of these explanations and domain knowledge sources that can enhance them.

Over the past decade, network operations teams have had to deal with a number of issues in their networks--from increased complexity to more distributed environments. With AIOps, you can start optimizing your networks now and prepare for the future. AIOps lets you manage your network like never before. According to Gartner, AIOps combines big data and machine learning to automate IT operations processes such as event correlation, anomaly detection, and causality determination to name a few. It can be defined as the application of machine learning (ML) and data science to IT operations problems.

Someone once said "if you can't measure something, you can't understand it." Another version of this belief says: "If you can't measure it, it doesn't exist." This is a false way of thinking -- a fallacy -- in fact it is sometimes called the McNamara fallacy. This mindset can have dire consequences in national affairs as well as in personal medical treatment (such as the application of "progression-free survival" metrics in cancer patients, where the reduction in tumors is lauded as a victory while the corresponding reduction in quality of life is ignored). Similarly, in the world of data science and analytics, we are often drawn into this same way of thinking.

Over the past several years, technology has rapidly changed what enterprise analytics can do. Analytical approaches that incorporate predictive models have begun to displace merely descriptive approaches. Descriptive analytics, which continue to be valuable for many users, have evolved as well, making greater use of visual analytics and moving toward a self-service model in which nontechnical users can often develop their own analyses. In general, analytics are quickly becoming both easier to use and more powerful. Despite this progress, it's still difficult to use data and analytics to understand and predict many of the important phenomena in organizations. Predictive models require a substantial amount of past data and a reasonable amount of expertise to create and use, which limits how and when they can be deployed.