Engineering Commons^™

Combining Bert With Contextual Linguistic Features For Identification Of Propaganda Spans In News Articles, Arjumand Younus, Muhammad Atif Qureshi

Conference papers

Recent endeavours at detection of propaganda in news articles treat this as a fine-grained problem of detecting it within fragments; and hence, transformer based embeddings perform decently in such detection. We build our propaganda detection framework on top of a transformer model simultaneously enriching it with contextual linguistic information of surrounding part-of-speech tags and LIWC categories the word itself belongs to. The evaluation outcomes being encouraging indicate a huge potential for this line of reasoning in natural language processing of news text.

Modelling The Addition Of Limestone In Cement Using Hydcem, Niall Holmes, Denis Kelliher, Mark Tyrer

Conference papers

Hydration models can aid in the prediction, understanding and description of hydration behaviour over time as the move towards more sustainable cements continues.

HYDCEM is a new model to predict the phase assemblage, degree of hydration and heat release over time for cements undergoing hydration for any w/c ratio and curing temperatures up to 450C. HYDCEM, written in MATLAB, complements more sophisticated thermodynamic models by predicting these properties over time using user-friendly inputs within one code. A number of functions and methods based on up to date cement hydration behaviour from the literature are hard-wired into the code along with …

A Multi-Task Approach To Incremental Dialogue State Tracking, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Incrementality is a fundamental feature of language in real world use. To this point, however, the vast majority of work in automated dialogue processing has focused on language as turn based. In this paper we explore the challenge of incremental dialogue state tracking through the development and analysis of a multi-task approach to incremental dialogue state tracking. We present the design of our incremental dialogue state tracker in detail and provide evaluation against the well known Dialogue State Tracking Challenge 2 (DSTC2) dataset. In addition to a standard evaluation of the tracker, we also provide an analysis of the Incrementality …

Prediction Of Flood Hydrograph In Small River Catchments Using System Modelling Approach, Ahmed Nasr, Zeinab Bedri, Loreta Ramanauske

Conference papers

Floods remain to be one of the natural catastrophic disasters with serious adverse social and economic implications on individuals and communities all around the world. In Ireland, frequency of flood events have increased dramatically during the last forty years and is expected to continue to rise primarily due to changes in rainfall and temperature patterns as a result of the global climate change. Small river catchments are usually vulnerable to different types of flooding particularly those associated with “monster” rainfall events, which are characterised by short durations and high intensities. Therefore accurate prediction of flood hydrographs resulting from these rainfall …

Assessment Of The Accuracy Of Cable Sheath Fault Location Device And Enhancement Of Its Performance, Niall Kennedy, Joseph Kearney, Tom Looby, Ciaran O'Leary

Conference papers

As power system networks are being constantly upgraded and extended, there is a greater importance in the reliable transmission of electrical power and fault finding techniques, especially for cables installed underground. Damage to a cable’s protective sheath can damage a cables life span and also lead to disruption of system operation and loss of supply. This study includes research into the literature and techniques used to locate these faults accurately. Bridge resistance and volt drop measurement techniques are the main methods used by sheath fault location devices to locate faults accurately. This task is made more difficult because such devices …

Is It Worth It? Budget-Related Evaluation Metrics For Model Selection, Filip Klubicka, Giancarlo Salton, John D. Kelleher

Conference papers

Projects that set out to create a linguistic resource often do so by using a machine learning model that pre-annotates or filters the content that goes through to a human annotator, before going into the final version of the resource. However, available budgets are often limited, and the amount of data that is available exceeds the amount of annotation that can be done. Thus, in order to optimize the benefit from the invested human work, we argue that the decision on which predictive model one should employ depends not only on generalized evaluation metrics, such as accuracy and F-score, but …

Streaming Vr For Immersion: Quality Aspects Of Compressed Spatial Audio, Miroslaw Narbutt, Sean O’Leary, Andrew Allen, Jan Skoglund, Andrew Hines

Conference papers

Delivering a 360-degree soundscape that matches full sphere visuals is an essential aspect of immersive VR. Ambisonics is a full sphere surround sound technique that takes into account the azimuth and elevation of sound sources, portraying source location above and below as well as around the horizontal plane of the listener. In contrast to channel-based methods, ambisonics representation offers the advantage of being independent of a specific loudspeaker set-up. Streaming ambisonics over networks requires efficient encoding techniques that compress the raw audio content without compromising quality of experience (QoE). This work investigates the effect of audio channel compression via the …

A Hardware One-Time Pad Prototype Generator For Localising Cloud Security, Paul Tobin, Lee Tobin, Michael Mckeever, Jonathan Blackledge

Conference papers

In this paper, we examine a system for encrypting data before storing in the Cloud. Adopting this system gives excellent security to stored data and complete control for accessing data by the client at different locations. The motivation for developing this personal encryption came about because of poor Cloud security and doubts over the safety of public encryption algorithms which might contain backdoors. However, side-channel attacks and other unwanted third-party interventions in Cloud security, probably contribute more to the poor security record history. These factors led to the development of a prototype for personalising security locally which defeats cryptanalysis. The …

A Framework For Post-Stroke Quality Of Life Prediction Using Structured Prediction, Andrew Hines, John D. Kelleher

Conference papers

This paper presents a conceptual model that relates Quality of Life to the established Quality of Experience formation process. It uses concepts developed by the Quality of Experience community to propose an adapted framework for developing predictive models for Quality of Life. A mapping of common factors that can be applied to health related quality of life is proposed and practical challenges for modelling and applications are presented and discussed. The process of identifying and categorising factors and features is illustrated using stroke patient treatment as an example use case.

On The Development Of A One-Time Pad Generator For Personalising Cloud Security, Paul Tobin, Lee Tobin, Michael Mckeever, Jonathan Blackledge

Conference papers

Cloud computing security issues are being reported in newspapers, television, and on the Internet, on a daily basis. Furthermore, in 2013, Edward Snowden alleged backdoors were placed in a number of encryption systems by the National Security Agency causing confidence in public encryption to drop even further. Our solution allows the end-user to add a layer of unbreakable security by encrypting the data locally with a random number generator prior to uploading data to the Cloud. The prototype one-time pad generator is impervious to cryptanalysis because it generates unbreakable random binary sequences from chaos sources initiated from a natural noise. …

Solar Photovoltaic System Control Topology Investigation For Power Source Mismatch, Lynette O'Callaghan

Conference papers

An investigation into solar photovoltaic (PV) system control topology selection, when partial shade is anticipated in the solar array, is presented. As available area is maximised in Building Integrated PV (BIPV) systems, shading is an inevitable consequence. The presence of partial shading in a PV array leads to multiple power peaks in the power-voltage curve, due to bypass diode sections being triggered, and an increase in module mismatch losses in the array. A building energy design software, Integrated Environmental Solutions, is used to determine the shadowed area on PV modules throughout the year, incorporating the PV system location and geometrical …

Referring Expression Generation Challenge 2008 Dit System Description, John D. Kelleher, Brian Mac Namee

Conference papers

This section describes the two systems developed at DIT for the attribute selection track of the REG 2008 challenge. Both of theses systems use an incremental greedy search to generate descriptions, similar to the incremental algorithm described in (Dale and Reiter, 1995). The output of these incremental algorithms are, to a large extent, determined by the order in which the algorithm tests the target object’s attributes for inclusion in the description. Indeed, the major difference between the two systems described in this section is the mechanism used to order the attributes for inclusion.

Physics-Based Table-Top Mixed Reality Games, Qingqing Dong, Zhongyi Sun, Brian Mac Namee

Conference papers

Mixed reality applications use techniques from computer vision, augmented reality and virtual reality to allow real and virtual objects interact physically together on a user’s computer screen. This paper will describe two mixed reality applications which allow the user to play games that appear to take place on top of their physical desk. The games described are a desktop racing game and a desktop based game of ten pin bowling. In the desktop racing game virtual cars, controlled by the user, interact with both virtual objects (such as trees, walls and lampposts) and real ones (such as ramps and blocks). …

Autopilot: Simulating Changing Concepts In Real Data, Patrick Lindstrom, Sarah Jane Delany, Brian Mac Namee

Conference papers

An increasingly important area in supervised incremental learning is learning in the presence of changing concepts. Research into concept drift is hampered by the lack of availability of controllable `real life' datasets. In this paper we propose an approach for generating real life data over which we have control of the concept and can generate data exhibiting different types of concept drift. The approach uses a 3-D driving game to produce a data stream of instances describing how to drive around a track. The classification problem is learning the driving technique of the driver, which can be affected by changes …

Structural Descriptions In Human-Assisted Robot Visual Learning, Geert-Jan Kruijff, John D. Kelleher, Gregor Berginc, Ales Leonardis

Conference papers

The paper presents an approach to using structural descriptions, obtained through a human-robot tutoring dialogue, as labels for the visual ob ject models a robot learns. The paper shows how structural descriptions can relate models for different aspects of one and the same object, and how relating descriptions for visual models and discourse referents enables incremental updating of model descriptions through dialogue (either robot- or human-initiated). The approach has been implemented in an integrated architecture for human-assisted robot visual learning.

Information Fusion For Visual Reference Resolution In Dynamic Situated Dialogue., Geert-Jan Kruijff, John D. Kelleher, Nick Hawes

Conference papers

Human-Robot Interaction (HRI) invariably involves dialogue about objects in the environment in which the agents are situated. The paper focuses on the issue of resolving discourse references to such visual objects. The paper addresses the problem using strategies for intra-modal fusion (identifying that different occurrences concern the same object), and inter-modal fusion, (relating object references across different modalities). Core to these strategies are sensori-motoric coordination, and ontology-based mediation between content in different modalities. The approach has been fully implemented, and is illustrated with several working examples

Spatial Prepositions In Context: The Semantics Of Near In The Presence Of Distractor Objects., Fintan Costello, John D. Kelleher

Conference papers

The paper examines how people’s judgements of proximity between two objects are influenced by the presence of a third object. In an experiment participants were presented with images containing three shapes in different relative positions, and asked to rate the acceptability of a locative expression such as ‘the circle is near the triangle’ as descriptions of those images. The results showed an interaction between the relative positions of objects and the linguistic roles that those objects play in the locative expression: proximity was a decreasing function of the distance between the object in the head position in the expression and …