Physical Sciences and Mathematics Commons^™

Argumentation For Knowledge Representation, Conflict Resolution, Defeasible Inference And Its Integration With Machine Learning, Luca Longo

Conference papers

Modern machine Learning is devoted to the construction of algorithms and computational procedures that can automatically improve with experience and learn from data. Defeasible argumentation has emerged as sub-topic of artificial intelligence aimed at formalising common-sense qualitative reasoning. The former is an inductive approach for inference while the latter is deductive, each one having advantages and limitations. A great challenge for theoretical and applied research in AI is their integration. The first aim of this chapter is to provide readers informally with the basic notions of defeasible and non-monotonic reasoning. It then describes argumentation theory, a paradigm for implementing defeasible …

Investigating The Impact Of Unsupervised Feature-Extraction From Multi-Wavelength Image Data For Photometric Classification Of Stars, Galaxies And Qsos, Annika Lindh

Conference papers

Accurate classification of astronomical objects currently relies on spectroscopic data. Acquiring this data is time-consuming and expensive compared to photometric data. Hence, improving the accuracy of photometric classification could lead to far better coverage and faster classification pipelines. This paper investigates the benefit of using unsupervised feature-extraction from multi-wavelength image data for photometric classification of stars, galaxies and QSOs. An unsupervised Deep Belief Network is used, giving the model a higher level of interpretability thanks to its generative nature and layer-wise training. A Random Forest classifier is used to measure the contribution of the novel features compared to a set …

Towards A Computational Model Of Frame Of Reference Alignment In Swedish Dialogue, Simon Dobnik, Christine Howes, Kim Demaret, John D. Kelleher

Conference papers

In this paper we examine how people negotiate, interpret and repair the frame of reference (FoR) in online text based dialogues discussing spatial scenes in Swedish. We describe work-in-progress in which participants are given different perspectives of the same scene and asked to locate several objects that are only shown on one of their pictures. This task requires participants to coordinate on FoR in order to identify the missing objects. This study has implications for situated dialogue systems.

Fundamentals Of Machine Learning For Neural Machine Translation, John D. Kelleher

Conference papers

This paper presents a short introduction to neural networks and how they are used for machine translation and concludes with some discussion on the current research challenges being addressed by neural machine translation (NMT) research. The primary goal of this paper is to give a no-tears introduction to NMT to readers that do not have a computer science or mathematical background. The secondary goal is to provide the reader with a deep enough understanding of NMT that they can appreciate the strengths of weaknesses of the technology. The paper starts with a brief introduction to standard feed-forward neural networks (what …

The Role Of Perception In Situated Spatial Reference, John D. Kelleher

Conference papers

This position paper set out the argument that an interesting avenue of exploration and study of universals and variation in spatial reference is to address this topic in termsa of the universals in human perception and attention and to explore how these universals impact on spatial reference across cultures and languages.

Towards A Deep Learning-Based Activity Discovery System, Eoin Rogers, John D. Kelleher, Robert J. Ross

Conference papers

Activity discovery is a challenging machine learning problem where we seek to uncover new or altered behavioural patterns in sensor data. In this paper we motivate and introduce a novel approach to activity discovery based on modern deep learning techniques. We hypothesise that our proposed approach can deal with interleaved datasets in a more intelligent manner than most existing AD methods. We also build upon prior work building hierarchies of activities that capture the inherent ag- gregate nature of complex activities and show how this could plausibly be adapted to work with the deep learning technique we present. Finally, we …

A Model For Attention-Driven Judgements In Type Theory With Records, Simon Dobnik, John D. Kelleher

Conference papers

This paper makes three contributions to the discussion on the applicability of Type Theory with Records (TTR) to embodied dialogue agents. First, it highlights the problem of type assignment or judgements in practical implementations which is resource intensive. Second, it presents a judgement control mechanism, which consists of grouping of types into clusters or states by their thematic relations and selection of types following two mechanisms inspired by the Load Theory of selective attention and cognitive control (Lavie et al., 2004), that addresses this problem. Third, it presents a computational framework, based on Bayesian inference, that offers a basis for …

Towards Reusable Personas For Everyday Design, Ciaran O'Leary, Fredrick Mtenzi, Claire Mcavinia

Conference papers

Personas are artificial character based representations of user goals, attitudes, motivations and abilities which enable designers to focus their design efforts on key, targeted users. The success of personas in design is due to their capacity to enable designers to empathize with users and understand user goals. Persona development is rooted in the rigorous collection and analysis of data specifically related to the design project being undertaken. New design projects thus require the development of new personas. Since redevelopment is not always achievable attention has turned towards reuse of personas and the underlying data. This paper reports on ongoing research …

Models Of Internal Waves In The Presence Of Currents, Alan Compelli, Rossen Ivanov

Conference papers

A fluid system consisting of two domains is examined. The system is considered as being bounded at the bottom and top by a flatbed and wave-free surface respectively. An internal wave propagating in one direction, driven by gravity, acts as a free common interface between the fluids. Various current profiles are considered. The Hamiltonian of the system is determined and expressed in terms of canonical wave-related variables. Limiting behaviour is examined and compared to that of other known models. The linearised equations as well as long-wave approximations are formulated. The presented models provide potential applications to modelling of internal geophysical …

Factorized Runge-Kutta-Chebyshev Methods, Stephen O'Sullivan

Conference papers

The second-order extended stability Factorized Runge-Kutta-Chebyshev (FRKC2) class of explicit schemes for the integration of large systems of PDEs with diffusive terms is presented. FRKC2 schemes are straightforward to implement through ordered sequences of forward Euler steps with complex stepsizes, and easily parallelised for large scale problems on distributed architectures.

Preserving 7 digits for accuracy at 16 digit precision, the schemes are theoretically capable of maintaining internal stability at acceleration factors in excess of 6000 with respect to standard explicit Runge-Kutta methods. The stability domains have approximately the same extents as those of RKC schemes, and are a third longer …

A Competitive Random Sequential Adsorption Model For Immunoassay Activity, Dana Mackey, Eilis Kelly, Robert Nooney

Conference papers

Immunoassays rely on highly specific reactions between antibodies and antigens and are used in biomedical diagnostics applications to detect biomarkers for a variety of diseases. Antibody immobilization to solid interfaces through random adsorption is a widely used technique but has the disadvantage of severely reducing the antigen binding activity and, consequently, the assay performance. This paper proposes a simple mathematical framework, based on the theory known as competitive random sequential adsorption (CRSA), for describing how the activity of immobilized antibodies depends on their orientation and packing density and generalizes a previous model by introducing the antibody aspect ratio as an …

Understanding The Everyday Designer In Organisations, Ciaran O'Leary, Fredrick Mtenzi, Claire Mcavinia

Conference papers

This paper builds upon the existing concept of an everyday designer as a non-expert designer who carries out design activities using available resources in a given environment. It does so by examining the design activities undertaken by non-expert, informal, designers in organisations who make use of the formal and informal technology already in use in organisations while designing to direct, influence, change or transform the practices of people in the organisation. These people represent a cohort of designers who are given little attention in the literature on information systems, despite their central role in the formation of practice and enactment …

Deep Level Lexical Features For Cross-Lingual Authorship Attribution, Marisa Llorens, Sarah Jane Delany

Conference papers

Crosslingual document classification aims to classify documents written in different languages that share a common genre, topic or author. Knowledge-based methods and others based on machine translation deliver state-of-the-art classification accuracy, however because of their reliance on external resources, poorly resourced languages present a challenge for these type of methods. In this paper, we propose a novel set of language independent features that capture language use from a document at a deep level, using features that are intrinsic to the document. These features are based on vocabulary richness measurements and are text length independent and self-contained, meaning that no external …

Using Topic Modelling Algorithms For Hierarchical Activity Discovery, Eoin Rogers, John D. Kelleher, Robert J. Ross

Conference papers

Activity discovery is the unsupervised process of discovering patterns in data produced from sensor networks that are monitoring the behaviour of human subjects. Improvements in activity discovery may simplify the training of activity recognition models by enabling the automated annotation of datasets and also the construction of systems that can detect and highlight deviations from normal behaviour. With this in mind, we propose an approach to activity discovery based on topic modelling techniques, and evaluate it on a dataset that mimics complex, interleaved sensor data in the real world. We also propose a means for discovering hierarchies of aggregated activities …

A Corpus Of Annotated Irish Traditional Dance Music Recordings: Design And Benchmark Evaluations, Pierre Beauguitte, Bryan Duggan, John D. Kelleher

Conference papers

An emerging trend in music information retrieval (MIR) is the use of supervised machine learning to train automatic music transcription models. A prerequisite of adopting a machine learning methodology is the availability of annotated corpora. However, different genres of music have different characteristics and modelling these characteristics is an important part of creating state of the art MIR systems. Consequently, although some music corpora are available the use of these corpora is tied to the specific music genre, instrument type and recording context the corpus covers. This paper introduces the first corpus of annotations of audio recordings of Irish traditional …

Mental Workload In Medicine: Foundations, Applications, Open Problems, Challenges And Future Perspectives, Luca Longo

Conference papers

Mental workload is a design concept borrowed from Ergonomics with a significant adoption in the aviation and automobile industries. Nowadays, the consideration of this construct is also taking place in many modern clinical working environments for designing interacting and complex systems that impose ever greater cognitive demand on operators and less physical load. Measuring mental workload is essential for improving the interaction human-system, enhancing performance, reducing the operator’s error and increasing safety. However, defining, measuring, assessing mental workload and understanding how this impinges on performance are still open problems. This secondary research is firstly aimed at introducing the construct of …

Harnessing The Power Of Text Mining For The Detection Of Abusive Content In Social Media, Hao Chen, Susan Mckeever, Sarah Jane Delany

Conference papers

Abstract The issues of cyberbullying and online harassment have gained considerable coverage in the last number of years. Social media providers need to be able to detect abusive content both accurately and efficiently in order to protect their users. Our aim is to investigate the application of core text mining techniques for the automatic detection of abusive content across a range of social media sources include blogs, forums, media-sharing, Q&A and chat - using datasets from Twitter, YouTube, MySpace, Kongregate, Formspring and Slashdot. Using supervised machine learning, we compare alternative text representations and dimension reduction approaches, including feature selection and …

Using Icicle Trees To Encode The Hierarchical Structure Of Source Code, Ivan Bacher, Brian Mac Namee, John D. Kelleher

Conference papers

This paper presents a study which evaluates the use of a tree visualisation (icicle tree) to encode the hierarchical structure of source code. The tree visualisation was combined with a source code editor in order to function as a compact overview to facilitate the process of comprehending the global structure of a source code document. Results from our study show that pro- viding an overview visualisation led to an increase in accuracy and a decrease in completion time when participants performed counting tasks. However, in locating tasks, the presence of the visualisation led to a decrease in participants’ performance.

Idiom Token Classification Using Sentential Distributed Semantics, Giancarlo Salton, Robert J. Ross, John D. Kelleher

Conference papers

Idiom token classification is the task of deciding for a set of potentially idiomatic phrases whether each occurrence of a phrase is a literal or idiomatic usage of the phrase. In this work we explore the use of Skip-Thought Vectors to create distributed representations that encode features that are predictive with respect to idiom token classification. We show that classifiers using these representations have competitive performance compared with the state of the art in idiom token classification. Importantly, however, our models use only the sentence containing the tar- get phrase as input and are thus less dependent on a potentially …

Sentiment Classification Using Negation As A Proxy For Negative Sentiment, Bruno Ohana, Brendan Tierney, Sarah Jane Delany

Conference papers

We explore the relationship between negated text and neg- ative sentiment in the task of sentiment classification. We propose a novel adjustment factor based on negation occur- rences as a proxy for negative sentiment that can be applied to lexicon-based classifiers equipped with a negation detec- tion pre-processing step. We performed an experiment on a multi-domain customer reviews dataset obtaining accuracy improvements over a baseline, and we further improved our results using out-of-domain data to calibrate the adjustment factor. We see future work possibilities in exploring nega- tion detection refinements, and expanding the experiment to a broader spectrum of opinionated …