Artificial Intelligence and Robotics Commons^™

Synthetic, Yet Natural: Properties Of Wordnet Random Walk Corpora And The Impact Of Rare Words On Embedding Performance, Filip Klubicka, Alfredo Maldonado, Abhijit Mahalunkar, John D. Kelleher

Conference papers

Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use this corpus to train embeddings. However, the effect of the shape of the knowledge graph on the generated pseudo-corpora, and on the resulting word embeddings, has not been studied. To explore this, we use English WordNet, constrained to the taxonomic (tree-like) portion of the graph, as a case study. We investigate the properties of the generated pseudo-corpora, and their impact on the resulting embeddings. We find …

Audio Mixing Using Image Neural Style Transfer Networks, Susan Mckeever, Xuehao Liu, Sarah Jane Delany

Conference papers

Image style transfer networks are used to blend images, producing images that are a mix of source images. The process is based on controlled extraction of style and content aspects of images, using pre-trained Convolutional Neural Networks (CNNs). Our interest lies in adopting these image style transfer networks for the purpose of transforming sounds. Audio signals can be presented as grey-scale images of audio spectrograms. The purpose of our work is to investigate whether audio spectrogram inputs can be used with image neural transfer networks to produce new sounds. Using musical instrument sounds as source sounds, we apply and compare …

The Use Of Deep Learning Distributed Representations In The Identification Of Abusive Text, Susan Mckeever, Hao Chen, Sarah Jane Delany

Conference papers

The selection of optimal feature representations is a critical step in the use of machine learning in text classification. Traditional features (e.g. bag of words and n-grams) have dominated for decades, but in the past five years, the use of learned distributed representations has become increasingly common. In this paper, we summarise and present a categorisation of the stateof-the-art distributed representation techniques, including word and sentence embedding models. We carry out an empirical analysis of the performance of the various feature representations using the scenario of detecting abusive comments. We compare classification accuracies across a range of off-the-shelf embedding models …

Multi-Spectral Visual Crop Assessment Under Limited Data Constraints, Patricia O'Byrne, Patrick Jackman, Damon Berry, Hector-Hugo Franco-Penya, Michael French, Robert J. Ross

Conference papers

In an era of climate change and global population growth, deep learning based multi-spectral imaging has the potential to significantly assist in production management across a wide range of agricultural and food production domains. A key challenge however in applying state-of-the-art methods is that they, unlike classical hand crafted methods, are usually thought of as being only useful when significant amounts of data are available. In this paper we investigate this hypothesis by examining the performance of state-of-the-art deep learning methods when applied to a restricted data set that is not easily bootstrapped through pre-trained image processing networks. We demonstrate …

On The Inability Of Markov Models To Capture Criticality In Human Mobility, Vaibhav Klukarni, Abhijit Mahalunkar, Benoit Garbinato, John Kelleher

Conference papers

We examine the non-Markovian nature of human mobility by exposing the inability of Markov models to capture criticality in human mobility. In particular, the assumed Markovian nature of mobility was used to establish an upper bound on the predictability of human mobility, based on the temporal entropy. Since its inception, this bound has been widely used for validating the performance of mobility prediction models. We show that the variants of recurrent neural network architectures can achieve significantly higher prediction accuracy surpassing this upper bound. The central objective of our work is to show that human-mobility dynamics exhibit criticality characteristics which …

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.

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 …

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 …

On Demonstrating The Impact Of Defeasible Reasoning Via A Multi-Layer Argument-Based Framework (Doctoral Consortium), Lucas Middeldorf Rizzo

Conference papers

Promising results have indicated Argumentation Theory as a solid research area for implementing defeasible reasoning in practice. However, applications are usually domain dependent, not incorporating all the layers and steps required in an argumentation process, thus limit- ing their applicability in different areas. This PhD project is focused on the development of a multi-layer defeasible argument-based framework which is in turn used across different applications in the fields of decision making and knowledge representation and reasoning. The inference produced is compared against the inference of different quantitative theories of reasoning under uncertainty such as expert systems and fuzzy logic. The …

Rating By Ranking: An Improved Scale For Judgement-Based Labels, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee

Conference papers

Labels representing value judgements are commonly elicited using an interval scale of absolute values. Data collected in such a manner is not always reliable. Psychologists have long recognized a number of biases to which many human raters are prone, and which result in disagreement among raters as to the true gold standard rating of any particular object. We hypothesize that the issues arising from rater bias may be mitigated by treating the data received as an ordered set of preferences rather than a collection of absolute values. We experiment on real-world and artificially generated data, finding that treating label ratings …

An Analysis Of The Application Of Simplified Silhouette To The Evaluation Of K-Means Clustering Validity, Fei Wang, Hector-Hugo Franco-Penya, John D. Kelleher, John Pugh, Robert J. Ross

Conference papers

Silhouette is one of the most popular and effective internal measures for the evaluation of clustering validity. Simplified Silhouette is a computationally simplified version of Silhouette. However, to date Simplified Silhouette has not been systematically analysed in a specific clustering algorithm. This paper analyses the application of Simplified Silhouette to the evaluation of k-means clustering validity and compares it with the k-means Cost Function and the original Silhouette from both theoretical and empirical perspectives. The theoretical analysis shows that Simplified Silhouette has a mathematical relationship with both the k-means Cost Function and the original Silhouette, while empirically, we show that …

Estimation Of Train Driver Workload: Extracting Taskload Measures From On-Train-Data-Recorders, Nora Balfe, Katie Crowley, Brendan Smith, Luca Longo

Conference papers

This paper presents a method to extract train driver taskload from downloads of on-train-data-recorders (OTDR). OTDR are in widespread use for the purposes of condition monitoring of trains, but they may also have applications in operations monitoring and management. Evaluation of train driver workload is one such application. The paper describes the type of data held in OTDR recordings and how they can be transformed into driver actions throughout a journey. Example data from 16 commuter journeys are presented, which highlights the increased taskload during arrival at stations. Finally, the possibilities and limitations of the data are discussed.

Tackling The Interleaving Problem In Activity Discovery, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

Activity discovery (AD) is the unsupervised process of discovering activities in data produced from streaming sensor networks that are recording the actions of human subjects. One major challenge for AD systems is interleaving, the tendency for people to carry out multiple activities at a time a parallel. Following on from our previous work, we continue to investigate AD in interleaved datasets, with a view towards progressing the state-of-the-art for AD.

Presenting A Labelled Dataset For Real-Time Detection Of Abusive User Posts, Hao Chen, Susan Mckeever, Sarah Jane Delany

Conference papers

Social media sites facilitate users in posting their own personal comments online. Most support free format user posting, with close to real-time publishing speeds. However, online posts generated by a public user audience carry the risk of containing inappropriate, potentially abusive content. To detect such content, the straightforward approach is to filter against blacklists of profane terms. However, this lexicon filtering approach is prone to problems around word variations and lack of context. Although recent methods inspired by machine learning have boosted detection accuracies, the lack of gold standard labelled datasets limits the development of this approach. In this work, …

Representing And Inferring Mental Workload Via Defeasible Reasoning: A Comparison With The Nasa Task Load Index And The Workload Profile, Lucas Middeldorf Rizzo, Luca Longo

Conference papers

The NASA Task Load Index (NASA − TLX) and the Workload Profile (WP) are likely the most employed instruments for subjective mental workload (MWL) measurement. Numerous areas have made use of these methods for assessing human performance and thusly improving the design of systems and tasks. Unfortunately, MWL is still a vague concept, with different definitions and no universal measure. This research investigates the use of defeasible reasoning to represent and assess MWL. Reasoning is defeasible when a conclusion, supported by a set of premises, can be retracted in the light of new information. In this empirical study, this type …

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 …

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 …

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 …

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 …

Reformulation Strategies Of Repeated References In The Context Of Robot Perception Errors In Situated Dialogue, Niels Schütte, John D. Kelleher, Brian Mac Namee

Conference papers

We performed an experiment in which human participants interacted through a natural language dialogue interface with a simulated robot to fulfil a series of object manipulation tasks. We introduced errors into the robot’s perception, and observed the resulting problems in the dialogues and their resolutions. We then introduced different methods for the user to request information about the robot’s understanding of the environment. In this work, we describe the effects that the robot’s perceptual errors and the information request options available to the participant had on the reformulation of the referring expressions the participants used when resolving a unsuccessful reference.

A Defeasible Reasoning Framework For Human Mental Workload Representation And Assessment, Luca Longo

Conference papers

Human mental workload (MWL) has gained importance in the last few decades as an important design concept. It is a multifaceted complex construct mainly applied in cognitive sciences and has been defined in many different ways. Although measuring MWL has potential advantages in interaction and interface design, its formalisation as an operational and computational construct has not sufficiently been addressed. This research contributes to the body of knowledge by providing an extensible framework built upon defeasible reasoning, and implemented with argumentation theory (AT), in which MWL can be better defined, measured, analysed, explained and applied in different human–computer interactive contexts. …

Multi-Valued Argumentation Frameworks, Pierpaolo Dondio

Conference papers

In this paper we explore how the seminal Dung’s abstract argumentation framework can be extended to handle arguments containing gradual concepts. We allow arguments to have a degree of truth associated with them and we investigate the degree of truth to which each argument can be considered accepted, rejected and undecided by an abstract argumentation semantics. We propose a truth-compositional recursive computation, and we discuss examples using the major multi-valued logics such as Godel’s, Zadeh’s and Łukasiewicz's logic. The findings are a contribution in the field of non-monotonic approximate reasoning and they also represent a well-grounded proposal towards the introduction …

Exploring Customer Specific Kpi Selection Strategies For An Adaptive Time Critical User Interface, Ingo Keck, Robert J. Ross

Conference papers

Rapid growth in the number of measures available to describe customer-organization relationships has presented a serious challenge for Business Intelligence (BI) interface developers as they attempt to provide business users with key customer information without requiring users to painstakingly sift through many interface windows and layers. In this paper we introduce a prototype Intelligent User Interface that we have deployed to partially address this issue. The interface builds on machine learning techniques to construct a ranking model of Key Performance Indicators (KPIs) that are used to select and present the most important customer metrics that can be made available to …

A Comparison Of Evidence Fusion Rules For Situation Recognition In Sensor-Based Environments, Susan Mckeever, Juan Ye

Conference papers

Dempster-Shafer (DS) theory, and its associated Dempster rule of combination, has been widely used to determine belief based on uncertain evi-dence sources. Variations to the original Dempster rule of combination have appeared in the literature to support particular scenarios where unreliable results may result from the use of original DS theory. While theoretical explanations of the rule variations are explained, there is a lack of empirical comparisons of the DS theory and its variations against real data sets. In this work, we examine several variations to DS theory. Using two real-world sensor data sets, we com-pare the performance of DS …

Improving Performance By Re-Rating In The Dynamic Estimation Of Rater Reliability, Alexey Tarasov, Sarah Jane Delany, Brian Macnamee

Conference papers

Nowadays crowdsourcing is widely used in supervised machine learning to facilitate the collection of ratings for unlabelled training sets. In order to get good quality results it is worth rejecting results from noisy/unreliable raters, as soon as they are discovered. Many techniques for filtering unreliable raters rely on the presentation of training instances to the raters identified as most accurate to date. Early in the process, the true rater reliabilities are not known and unreliable raters may be used as a result. This paper explores improving the quality of ratings for train- ing instances by performing re-rating. The re-rating relies …

Drift Detection Using Uncertainty Distribution Divergence, Patrick Lindstrom, Brian Mac Namee, Sarah Jane Delany

Conference papers

Concept drift is believed to be prevalent inmost data gathered from naturally occurring processes andthus warrants research by the machine learning community.There are a myriad of approaches to concept drift handlingwhich have been shown to handle concept drift with varyingdegrees of success.

However, most approaches make the keyassumption that the labelled data will be available at nolabelling cost shortly after classification, an assumption whichis often violated. The high labelling cost in many domainsprovides a strong motivation to reduce the number of labelledinstances required to handle concept drift. Explicit detectionapproaches that do not require labelled instances to detectconcept drift show great …