Informatics, School of: Recent submissions

Now showing items 1-20 of 1562

    • On understanding character-level models for representing morphology 

      Vania, Clara (The University of Edinburgh, 2020-01-20)
      Morphology is the study of how words are composed of smaller units of meaning (morphemes). It allows humans to create, memorize, and understand words in their language. To process and understand human languages, we expect ...

    • Understanding and generating language with abstract meaning representation 

      Damonte, Marco (The University of Edinburgh, 2020-01-08)
      Abstract Meaning Representation (AMR) is a semantic representation for natural language that encompasses annotations related to traditional tasks such as Named Entity Recognition (NER), Semantic Role Labeling (SRL), word ...

    • Design and evaluation of contracts for gradual typing 

      Williams, Jack (The University of Edinburgh, 2019-11-25)
      Gradual typing aims to improve the correctness of dynamically typed programs by incrementally adding type information. Sound gradual typing performs static type checking and inserts run-time checks when a type cannot be ...

    • Automatic performance optimisation of parallel programs for GPUs via rewrite rules 

      Remmelg, Toomas (The University of Edinburgh, 2019-12-11)
      Graphics Processing Units (GPUs) are now commonplace in computing systems and are the most successful parallel accelerators. Their performance is orders of magnitude higher than traditional Central Processing Units (CPUs) ...

    • Towards efficient support for massive Internet of Things over cellular networks 

      Tsoukaneri, Galini (The University of Edinburgh, 2019-12-12)
      The usage of Internet of Things (IoT) devices over cellular networks is seeing tremendous growth in recent years, and that growth in only expected to increase in the near future. While existing 4G and 5G cellular networks ...

    • 3D data fusion by depth refinement and pose recovery 

      Pu, Can (The University of Edinburgh, 2019-11-23)
      Refining depth maps from different sources to obtain a refined depth map, and aligning the rigid point clouds from different views, are two core techniques. Existing depth fusion algorithms do not provide a general ...

    • Test time cost sensitivity in machine learning 

      Gray, Gavin Douglas Buchanan (The University of Edinburgh, 2019-11-23)
      The use of deep neural networks has enabled machines to classify images, translate between languages and compete with humans in games. These achievements have been enabled by the large and expensive computational resources ...

    • Prosody generation for text-to-speech synthesis 

      Ronanki, Srikanth (The University of Edinburgh, 2019-09-30)
      The absence of convincing intonation makes current parametric speech synthesis systems sound dull and lifeless, even when trained on expressive speech data. Typically, these systems use regression techniques to predict ...

    • Social media in health and care co-production 

      Daneshvar Farzanegan, Sayed Hadi (The University of Edinburgh, 2019-11-23)
      The future of health and care services in the EU faces the three challenges of the aging population, fiscal restriction, and social inclusion. Co-production offers ways to manage informal care resources to enable them ...

    • Neural density estimation and likelihood-free inference 

      Papamakarios, Georgios (The University of Edinburgh, 2019-11-23)
      I consider two problems in machine learning and statistics: the problem of estimating the joint probability density of a collection of random variables, known as density estimation, and the problem of inferring model ...

    • Semantics and provenance of configuration programming language μPuppet 

      Fu, Weili (The University of Edinburgh, 2019-11-23)
      Nowadays computing infrastructures have grown bigger in scale and more complex. Automated configuration management tools have taken the place of traditional approaches of configuration tasks, such as manual configuration ...

    • Machine learning for inductive theorem proving 

      Jiang, Yaqing (The University of Edinburgh, 2019-11-23)
      Over the past few years, machine learning has been successfully combined with automated theorem provers (ATPs) to prove conjectures from various proof assistants. However, such approaches do not usually focus on inductive ...

    • Usability evaluation of spoken humanoid embodied conversational agents in mobile serious games 

      Korre, Danai (The University of Edinburgh, 2019-11-23)
      The use of embodied conversational agents (ECAs) and spoken dialogue systems in serious games offers theoretical advantages such as a more natural interaction with an agent displaying characteristics like personality, ...

    • Wide-coverage statistical parsing with minimalist grammars 

      Torr, John Philip (The University of Edinburgh, 2019-11-23)
      Syntactic parsing is the process of automatically assigning a structure to a string of words, and is arguably a necessary prerequisite for obtaining a detailed and precise representation of sentence meaning. For many NLP ...

    • Moving beyond parallel data for neutral machine translation 

      Currey, Anna (The University of Edinburgh, 2019-11-23)
      The goal of neural machine translation (NMT) is to build an end-to-end system that automatically translates sentences from the source language to the target language. Neural machine translation has become the dominant ...

    • Machine learning and privacy preserving algorithms for spatial and temporal sensing 

      Ghosh, Abhirup (The University of Edinburgh, 2019-11-23)
      Sensing physical and social environments are ubiquitous in modern mobile phones, IoT devices, and infrastructure-based settings. Information engraved in such data, especially the time and location attributes have ...

    • Methodology to sustain common information spaces for research collaborations 

      Trani, Luca (The University of Edinburgh, 2019-11-23)
      Information and knowledge sharing collaborations are essential for scientific research and innovation. They provide opportunities to pool expertise and resources. They are required to draw on today’s wealth of data to ...

    • Learning to make decisions with unforeseen possibilities 

      Innes, Craig (The University of Edinburgh, 2019-11-23)
      Methods for learning optimal policies often assume that the way the domain is conceptualised— the possible states and relevant actions that are needed to solve one’s decision problem—is known in advance and does not ...

    • Deep generative modelling for amortised variational inference 

      Srivastava, Akash (The University of Edinburgh, 2019-11-23)
      Probabilistic and statistical modelling are the fundamental frameworks that underlie a large proportion of the modern machine learning (ML) techniques. These frameworks allow for the practitioners to develop tailor-made ...

    • Phenomenological modelling: statistical abstraction methods for Markov chains 

      Michaelides, Michalis (The University of Edinburgh, 2019-11-23)
      Continuous-time Markov chains have long served as exemplary low-level models for an array of systems, be they natural processes like chemical reactions and population fluctuations in ecosystems, or artificial processes ...