Now showing items 1-20 of 1767

    • Low- and high-resource opinion summarization 

      Bražinskas, Arthur (The University of Edinburgh, 2023-01-25)
      Customer reviews play a vital role in the online purchasing decisions we make. The reviews express user opinions that are useful for setting realistic expectations and uncovering important details about products. However, ...
    • Learning the structure of clusters in graphs 

      Macgregor, Peter (The University of Edinburgh, 2023-01-25)
      Graph clustering is a fundamental problem in unsupervised learning, with numerous applications in computer science and in analysing real-world data. In many real-world applications, we find that the clusters have a significant ...
    • Data-efficient neural network training with dataset condensation 

      Zhao, Bo (The University of Edinburgh, 2023-01-24)
      The state of the art in many data driven fields including computer vision and natural language processing typically relies on training larger models on bigger data. It is reported by OpenAI that the computational cost to ...
    • FluiDB: adaptive storage layout using reversible relational operators 

      Perivolaropoulos, Christos (The University of Edinburgh, 2023-01-20)
      It is a popular practice to use materialized intermediate results to improve the perfor- mance of RDBMSes. Work in this area has focused either optimisers matching existing materialized results in the cache and selecting ...
    • Visual system identification: learning physical parameters and latent spaces from pixels 

      Jaques, Miguel (The University of Edinburgh, 2023-01-20)
      In this thesis, we develop machine learning systems that are able to leverage the knowledge of equations of motion (scene-specific or scene-agnostic) to perform object discovery, physical parameter estimation, position ...
    • Characterising the source of errors for metagenomic taxonomic classification 

      Crespi i Boixader, Alba (The University of Edinburgh, 2023-01-19)
      Characterising microbial communities enables a better understanding of their complexity and the contribution to the environment. Metagenomics has been a rapidly expanding field since the revolution of next generation ...
    • Structured parallelism discovery with hybrid static-dynamic analysis and evaluation technique 

      Vasiladiotis, Christos (The University of Edinburgh, 2023-01-17)
      Parallel computer architectures have dominated the computing landscape for the past two decades; a trend that is only expected to continue and intensify, with increasing specialization and heterogeneity. This creates huge ...
    • Temporality and modality in entailment graph induction 

      Bijl de Vroe, Sander Govert Cornelis (The University of Edinburgh, 2023-01-16)
      The ability to draw inferences is core to semantics and the field of Natural Language Processing. Answering a seemingly simple question like ‘Did Arsenal play Manchester yesterday’ from textual evidence that says ‘Arsenal ...
    • Structure-aware narrative summarization from multiple views 

      Papalampidi, Pinelopi (The University of Edinburgh, 2023-01-13)
      Narratives, such as movies and TV shows, provide a testbed for addressing a variety of challenges in the field of artificial intelligence. They are examples of complex stories where characters and events interact in many ...
    • Unbounded loops in quantum programs: categories and weak while loops 

      Andrés-Martínez, Pablo (The University of Edinburgh, 2023-01-13)
      Control flow of quantum programs is often divided into two different classes: classical and quantum. Quantum programs with classical control flow have their conditional branching determined by the classical outcome of ...
    • Meta-ontology fault detection 

      Casanova Jaquete, Juan (The University of Edinburgh, 2023-01-12)
      Ontology engineering is the field, within knowledge representation, concerned with using logic-based formalisms to represent knowledge, typically moderately sized knowledge bases called ontologies. How to best develop, use ...
    • Structured machine learning models for robustness against different factors of variability in robot control 

      Davchev, Todor Bozhinov (The University of Edinburgh, 2023-01-11)
      An important feature of human sensorimotor skill is our ability to learn to reuse them across different environmental contexts, in part due to our understanding of attributes of variability in these environments. This ...
    • Language integrated relational lenses 

      Horn, Rudi (The University of Edinburgh, 2023-01-10)
      Relational databases are ubiquitous. Such monolithic databases accumulate large amounts of data, yet applications typically only work on small portions of the data at a time. A subset of the database defined as a computation ...
    • Learning universal representations across tasks and domains 

      Li, Wei-Hong (The University of Edinburgh, 2022-12-16)
      A longstanding goal in computer vision research is to produce broad and general-purpose systems that work well on a broad range of vision problems and are capable of learning concepts only from few labelled samples. In ...
    • Document summarization with neural query modeling 

      Xu, Yumo (The University of Edinburgh, 2022-12-16)
      Document summarization is a natural language processing task that aims to produce a short summary that concisely delivers the most important information of a document or multiple documents. Over the last few decades, the ...
    • Network analysis of the post synaptic proteome and its implication for cognition 

      Robertson, Grant (The University of Edinburgh, 2022-12-15)
      The post synaptic proteome is a complex of more than 3,000 proteins that form modular molecular machines that are involved in signal transduction, information processing and learning in the central nervous system. Previous ...
    • Dr.Aid: a formal framework assisting compliance with data governance rules 

      Zhao, Rui (The University of Edinburgh, 2022-12-15)
      The data “Terms of Use” (ToU) widely exists, with different names, such as “Privacy Policy” or “Data Consent”, and everyone handling data will deal with them. They are, in general, a form of data-governance rules, which ...
    • Learning reliable representations when proxy objectives fail 

      Darlow, Luke Nicholas (The University of Edinburgh, 2022-12-14)
      Representation learning involves using an objective to learn a mapping from data space to a representation space. When the downstream task for which a mapping must be learned is unknown, or is too costly to cast as an ...
    • Few-shot learning in changing domains 

      Mason, Ian (The University of Edinburgh, 2022-12-12)
      This thesis will present a number of investigations into how machine learning systems, in particular artificial neural networks, function in changing domains. In the standard machine learning paradigm a model is evaluated ...
    • Generative factorization for object-centric representation learning 

      Li, Nanbo (The University of Edinburgh, 2022-12-12)
      Empowering machines to understand compositionality is considered by many (Lake et al., 2017; Lake and Baroni, 2018; Schölkopf et al., 2021) a promising path towards improved representational interpretability and ...