Physical Sciences and Mathematics Commons^™

Exploring Online Novelty Detection Using First Story Detection Models, Fei Wang, Robert J. Ross, John D. Kelleher

Conference papers

Online novelty detection is an important technology in understanding and exploiting streaming data. One application of online novelty detection is First Story Detection (FSD) which attempts to find the very first story about a new topic, e.g. the first news report discussing the “Beast from the East” hitting Ireland. Although hundreds of FSD models have been developed, the vast majority of these only aim at improving the performance of the detection for some specific dataset, and very few focus on the insight of novelty itself. We believe that online novelty detection, framed as an unsupervised learning problem, always requires a …

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 …

From Rankings To Ratings: Rank Scoring Via Active Learning, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee

Conference papers

In this paper we present RaScAL, an active learning approach to predicting real-valued scores for items given access to an oracle and knowledge of the overall item-ranking. In an experiment on six different datasets, we find that RaScAL consistently outperforms the state-of-the-art. The RaScAL algorithm represents one step within a proposed overall system of preference elicitations of scores via pairwise comparisons.

Scoped: Evaluating A Composite Visualisation Of The Scope Chain Hierarchy Within Source Code, Ivan Bacher, Brian Mac Namee, John D. Kelleher

Conference papers

This paper presents two studies that evaluate the effectiveness of a software visualisation tool which uses a com- posite visualisation to encode the scope chain and information related to the scope chain within source code. The first study evaluates the effectiveness of adding the composite visualisation to a source code editor to help programmers understand scope relationships within source code. The second study evaluates the effectiveness of each individual component within the composite visualisation. The composite visualisation is composed of a packed circle tree diagram (overview component) and a list view (detail view component). The packed circle tree functions as …

The Code Mini-Map Visualisation: Encoding Conceptual Structures Within Source Code, Ivan Bacher, Brian Mac Namee, John D. Kelleher

Conference papers

Modern source code editors typically include a code mini-map visualisation, which provides programmers with an overview of the currently open source code document. This paper proposes to add a layering mechanism to the code mini- map visualisation in order to provide programmers with visual answers to questions related to conceptual structures that are not manifested directly in the code. Details regarding the design and implementation of this scope information layer, which displays additional encodings that correspond to the scope chain and information related to the scope chain within a source code document, is presented. The scope information layer can be …

Entity-Grounded Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher

Conference papers

An urgent limitation in current Image Captioning models is their tendency to produce generic captions that avoid the interesting detail which makes each image unique. To address this limitation, we propose an approach that enforces a stronger alignment between image regions and specific segments of text. The model architecture is composed of a visual region proposer, a region-order planner and a region-guided caption generator. The region-guided caption generator incorporates a novel information gate which allows visual and textual input of different frequencies and dimensionalities in a Recurrent Neural Network.

Perception & Perspective: An Analysis Of Discourse And Situational Factors In Reference Frame Selection, Robert J. Ross, Kavita E. Thomas

Conference papers

To integrate perception into dialogue, it is necessary to bind spatial language descriptions to reference frame use. To this end, we present an analysis of discourse and situational factors that may influence reference frame choice in dialogues. We show that factors including spatial orientation, task, self and other alignment, and dyad have an influence on reference frame use. We further show that a computational model to estimate reference frame based on these features provides results greater than both random and greedy reference frame selection strategies.

An Investigation Into The Effects Of Multiple Kernel Combinations On Solutions Spaces In Support Vector Machines, Paul Kelly, Luca Longo

Conference papers

The use of Multiple Kernel Learning (MKL) for Support Vector Machines (SVM) in Machine Learning tasks is a growing field of study. MKL kernels expand on traditional base kernels that are used to improve performance on non-linearly separable datasets. Multiple kernels use combinations of those base kernels to develop novel kernel shapes that allow for more diversity in the generated solution spaces. Customising these kernels to the dataset is still mostly a process of trial and error. Guidelines around what combinations to implement are lacking and usually they requires domain specific knowledge and understanding of the data. Through a brute …

Evaluating Sequence Discovery Systems In An Abstraction-Aware Manner, Eoin Rogers, Robert J. Ross, John D. Kelleher

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 evaluating activity discovery systems. Pre-annotated ground truths, often used to evaluate the performance of such systems on existing datasets, may exist at different levels of abstraction to the output of the output produced by the system. We propose a method for detecting and dealing with this situation, allowing for useful ground truth comparisons. This work has applications for activity discovery, and also for related fields. For example, it …

Towards A Conceptual Framework For The Development Of Immersive Experiences To Negotiate Meaning And Identify In Irish Language Learning, Naoise Collins, Brian Vaughan, Keith Gardiner, Charlie Cullen

Conference papers

The onset of virtual reality systems allows for new immersive content which provides users with a sense of presence in their virtual environment. This paper provides the conceptual framework for a larger study examining how designed virtual reality experiences can be utilised to transform Irish language meaning making and a user's personal Irish language identity.

Investigation Of Wavenumber Calibration For Raman Spectroscopy Using A Polymer Reference, Dongyue Liu, Hugh Byrne, Luke O'Neill, Bryan M. Hennelly

Conference papers

Raman spectroscopy is an optical technique that can be used to evaluate the biomolecular composition of tissue and cell samples in a real-time and non-invasive manner. Subtle differences between datasets of spectra obtained from related cell groups can be identified using multivariate statistical algorithms. Such techniques are highly sensitive to small errors, however, and, therefore, the classification sensitivity of Raman spectroscopy can be significantly impacted by miscalibration of the optical system due to small misalignments of the optical elements and/or variation in ambient temperature. Wavenumber calibration is often achieved by recording the spectrum from a wavenumber reference standard, such as …

Interoperable Ocean Observing Using Archetypes: A Use-Case Based Evaluation, Paul Stacey, Damon Berry

Conference papers

This paper presents a use-case based evaluation of the impact of two-level modeling on the automatic federation of ocean observational data. The goal of the work is to increase the interoperability and data quality of aggregated ocean observations to support convenient discovery and consumption by applications. An assessment of the interoperability of served data flows from publicly available ocean observing spatial data infrastructures was performed. Barriers to consumption of existing standards-compliant ocean-observing data streams were examined, including the impact of adherence to agreed data standards. Historical data flows were mapped to a set of archetypes and a backward integration experiment …

A Proposal To Embed The In Dubio Pro Reo Principle Into Abstract Argumentation Semantics Based On Topological Ordering And Undecidedness Propagation, Pierpaolo Dondio, Luca Longo

Conference papers

Abstract. In this paper we discuss how the in dubio pro reo principle and the corresponding standard of proof beyond reasonable doubt can be modelled in abstract argumentation. The in dubio pro reo principle protects arguments against attacks from doubtful arguments. We identify doubtful arguments with a subset of undecided arguments, called active undecided arguments, consisting of cyclic arguments responsible for generating the undecided situation. We obtain the standard of proof beyond reasonable doubt by imposing that attacks from doubtful undecided arguments are not enough to change the acceptability status of an attacked argument (the reo). The resulting semantics, called …

Validation Of Tagging Suggestion Models For A Hotel Ticketing Corpus, Bojan Bozic, Andre Rios, Sarah Jane Delany

Conference papers

This paper investigates methods for the prediction of tags on a textual corpus that describes hotel staff inputs in a ticketing system. The aim is to improve the tagging process and find the most suitable method for suggesting tags for a new text entry. The paper consists of two parts: (i) exploration of existing sample data, which includes statistical analysis and visualisation of the data to provide an overview, and (ii) evaluation of tag prediction approaches. We have included different approaches from different research fields in order to cover a broad spectrum of possible solutions. As a result, we have …

Non-Linear Machine Learning With Active Sampling For Mox Drift Compensation, Tamara Matthews, Muhammad Iqbal, Horacio Gonzalez-Velez

Conference papers

Abstract—Metal oxide (MOX) gas detectors based on SnO2 provide low-cost solutions for real-time sensing of complex gas mixtures for indoor ambient monitoring. With high sensitivity under ideal conditions, MOX detectors may have poor longterm response accuracy due to environmental factors (humidity and temperature) along with sensor aging, leading to calibration drifts. Finding a simple and efficient solution to correct such calibration drifts has been the subject of numerous studies but remains an open problem. In this work, we present an efficient approach to MOX calibration using active and transfer sampling techniques coupled with non-linear machine learning algorithms, namely neural networks, …

Information Hiding Using Convolutional Encoding, Jonathan Blackledge, Paul Tobin, J. Myeza, C. M. Adolfo

Conference papers

We consider two functions f1(r) and f2(r), for r 2 Rn and the problem of ‘Diffusing’ these functions together, followed by the application of an encryption process we call ‘Stochastic Diffusion’ and then hiding the output of this process in to one or other of the same functions. The coupling of these two processes (i.e., data diffusion and stochastic diffusion) is considered using a form of conditioning that generates a wellposed and data consistent inverse solution for the purpose of decrypting the output. After presenting the basic encryption method and (encrypted) information hiding model, coupled with a mathematical analysis (within …

Presenting A Hybrid Processing Mining Framework For Automated Simulation Model Generation, Susan Mckeever, Mohammad Messabah

Conference papers

Recent advances in information technology systems have enabled organizations to store tremendous amounts of business process data. Process mining offers a range of algorithms and methods to analyze and extract metadata for these processes. This paper presents a novel approach to the hybridization of process mining techniques with business process modelling and simulation methods. We present a generic automated end-to-end simulation framework that produces unbiased simulation models using system event logs. A conceptual model and various meta-data are derived from the logs and used to generate the simulation model. We demonstrate the efficacy of our framework using a business process …

Exploring The Functional And Geometric Bias Of Spatial Relations Using Neural Language Models, Simon Dobnik, Mehdi Ghanimifard, John D. Kelleher

Conference papers

The challenge for computational models of spatial descriptions for situated dialogue systems is the integration of information from different modalities. The semantics of spatial descriptions are grounded in at least two sources of information: (i) a geometric representation of space and (ii) the functional interaction of related objects that. We train several neural language models on descriptions of scenes from a dataset of image captions and examine whether the functional or geometric bias of spatial descriptions reported in the literature is reflected in the estimated perplexity of these models. The results of these experiments have implications for the creation of …

Generating Diverse And Meaningful Captions: Unsupervised Specificity Optimization For Image Captioning, Annika Lindh, Robert J. Ross, Abhijit Mahalunkar, Giancarlo Salton, John D. Kelleher

Conference papers

Image Captioning is a task that requires models to acquire a multi-modal understanding of the world and to express this understanding in natural language text. While the state-of-the-art for this task has rapidly improved in terms of n-gram metrics, these models tend to output the same generic captions for similar images. In this work, we address this limitation and train a model that generates more diverse and specific captions through an unsupervised training approach that incorporates a learning signal from an Image Retrieval model. We summarize previous results and improve the state-of-the-art on caption diversity and novelty.

We make our …

Using Regular Languages To Explore The Representational Capacity Of Recurrent Neural Architectures, Abhijit Mahalunkar, John D. Kelleher

Conference papers

The presence of Long Distance Dependencies (LDDs) in sequential data poses significant challenges for computational models. Various recurrent neural architectures have been designed to mitigate this issue. In order to test these state-of-the-art architectures, there is growing need for rich benchmarking datasets. However, one of the drawbacks of existing datasets is the lack of experimental control with regards to the presence and/or degree of LDDs. This lack of control limits the analysis of model performance in relation to the specific challenge posed by LDDs. One way to address this is to use synthetic data having the properties of subregular languages. …

Rhythm Inference From Audio Recordings Of Irish Traditional Music, Pierre Beauguitte, Bryan Duggan, John D. Kelleher

Conference papers

A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of this musical genre. Low-level spectral features and autocorrelation are used to obtain a low-dimensional representation, on which logistic regression models are trained. Two experiments are conducted to predict rhythmic information at different levels of precision. The method is tested on a collec- ion of session recordings, and high accuracy scores are reported.

A new method is proposed to infer rhythmic information from audio recordings of Irish traditional tunes. The method relies on he repetitive nature of …

The Terror Network Industrial Complex: A Measurement And Analysis Of Terrorist Networks And War Stocks, James Usher, Pierpaolo Dondio

Conference papers

This paper presents a measurement study and analysis of the structure of multiple Islamic terrorist networks to determine if similar characteristics exist between those networks. We examine data gathered from four terrorist groups: Al-Qaeda, ISIS, Lashkar-e-Taiba (LeT) and Jemaah Islamiyah (JI) consisting of six terror networks. Our study contains 471 terrorists’ nodes and 2078 links. Each terror network is compared in terms efficiency, communication and composition of network metrics. The paper examines the effects these terrorist attacks had on US aerospace and defence stocks (herein War stocks). We found that the Islamic terror groups increase recruitment during the planned attacks, …

An Investigation Of The Impact Of A Social Constructivist Teaching Approach, Based On Trigger Questions, Through Measures Of Mental Workload And Efficiency, Federico Gobbo, Luca Longo, Declan O'Sullivan, Giuliano Orru

Conference papers

Social constructivism is grounded on the construction of information with a focus on collaborative learning through social interactions. However, it tends to ignore the human mental architecture, pillar of cognitivism. A characteristic of cognitivism is that instructional designs built upon it are generally explicit, contrarily to constructivism. This position paper proposes a novel learning task that is aimed at combining both the approaches through the use of trigger questions in a collaborative activity executed after a traditional delivery of instructions. To evaluate this new task, a metric of efficiency based upon a measure of mental workload and a measure of …

A Comparison Of Classical Versus Deep Learning Techniques For Abusive Content Detection On Social Media Sites, Hao Che, Susan Mckeever, Sarah Jane Delany

Conference papers

The automated detection of abusive content on social media websites faces a variety of challenges including imbalanced training sets, the identification of an appropriate feature representation and the selection of optimal classifiers. Classifiers such as support vector machines (SVM), combined with bag of words or ngram feature representation, have traditionally dominated in text classification for decades. With the recent emergence of deep learning and word embeddings, an increasing number of researchers have started to focus on deep neural networks. In this paper, our aim is to explore cutting-edge techniques in automated abusive content detection. We use two deep learning approaches: …

Sensory Seduction And Narrative Pull, Nina Lyons, Matt Smith, Hugh Mccabe

Conference papers

User experience design is a process that has been defined, developed and refined over the last few decades. It is a process of shaping a user's movements through a website or mobile application. It is user-focussed, prioritising utility, ease-of-use and efficiency. It is widely used and has helped advance the way in which users interact with websites and mobile applications, making it far less frustrating. User experience design is a key element in how the internet and mobile technology have become ubiquitous in our daily lives. Given this success, it would seem that continuing to use this process for new …