John McCrae – författare

This book provides an in-depth discussion of the evolution of machine translation from rule-based systems to advanced deep learning models and Large Language Models (LLMs). This comprehensive guide covers traditional approaches, Statistical Machine Translation (SMT), and the transformative impact of neural networks and transformers. It explores the practical applications of LLMs like GPT, addressing evaluation metrics and ongoing research challenges. Ideal for researchers, practitioners, and students in NLP and AI, this book bridges theoretical foundations with real-world applications, offering valuable insights into the future of machine translation technology to understand the full spectrum of machine translation advancements, from foundational theories to the latest generative AI technologies.

For humans, understanding a natural language sentence or discourse is so effortless that we hardly ever think about it. For machines, however, the task of interpreting natural language, especially grasping meaning beyond the literal content, has proven extremely difficult and requires a large amount of background knowledge. This book focuses on the interpretation of natural language with respect to specific domain knowledge captured in ontologies. The main contribution is an approach that puts ontologies at the center of the interpretation process. This means that ontologies not only provide a formalization of domain knowledge necessary for interpretation but also support and guide the construction of meaning representations. We start with an introduction to ontologies and demonstrate how linguistic information can be attached to them by means of the ontology lexicon model lemon. These lexica then serve as basis for the automatic generation of grammars, which we use to compositionallyconstruct meaning representations that conform with the vocabulary of an underlying ontology. As a result, the level of representational granularity is not driven by language but by the semantic distinctions made in the underlying ontology and thus by distinctions that are relevant in the context of a particular domain. We highlight some of the challenges involved in the construction of ontology-based meaning representations, and show how ontologies can be exploited for ambiguity resolution and the interpretation of temporal expressions. Finally, we present a question answering system that combines all tools and techniques introduced throughout the book in a real-world application, and sketch how the presented approach can scale to larger, multi-domain scenarios in the context of the Semantic Web. Table of Contents: List of Figures / Preface / Acknowledgments / Introduction / Ontologies / Linguistic Formalisms / Ontology Lexica / Grammar Generation / Putting Everything Together / Ontological Reasoning for Ambiguity Resolution / Temporal Interpretation / Ontology-Based Interpretation for Question Answering / Conclusion / Bibliography / Authors' Biographies

This book constitutes the proceedings of the satellite events held at the XXX Semantic Web Conference, ESWC 2025, held in Portoroz, Slovenia, during June 1–2, 2025.The 31 Posters & Demos papers are presented together with 12 PhD Symposium papers and 7 Industry papers in this book were carefully reviewed and selected from 43 Posters& Demo papers, 15 PHD Symsposium papers and 14 Industry papers. The theme of  the conference was “Empowering Knowledge through Semantics: From Knowledge Graphs to Neurosemantics”. The satellite events are an important aspect of facilitating the main conference discussion as well as fundamental questions about how we acquire, represent, use, and interact with knowledge and semantics.The satellite events of ESWC 2025 include the poster and demo session, the PhD symposium, the industry track, project networking, and workshops and tutorials.