Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Data sonification (8)
- Contour icons (5)
- Dna sonification (3)
- Mobile devices (3)
- Machine learning (2)
-
- Speech (2)
- Auditory display (1)
- Boolean sonification (1)
- Budget (1)
- Computational semantics (1)
- Computer security breaches; crackers; Jungian archetypes; filmic representations; movie hacking; popular media representation; computer hackers; film hacking; hacking movies; data analysis. (1)
- Corpus bias (1)
- Deep learning (1)
- Emotion (1)
- Emotional dimensions (1)
- Emotional speech (1)
- Ephemeral data (1)
- Error annotation (1)
- F-score (1)
- Factored models (1)
- Feature analysis (1)
- Gain (1)
- Harmonic combination (1)
- Hate speech (1)
- Human evaluation (1)
- Hypernym detection (1)
- Idiom dictionary (1)
- Idiom identification (1)
- Judgement (1)
- Judgement analysis (1)
- Publication
Articles 1 - 15 of 15
Full-Text Articles in Other Computer Engineering
Examining A Hate Speech Corpus For Hate Speech Detection And Popularity Prediction, Filip Klubicka, Raquel Fernandez
Examining A Hate Speech Corpus For Hate Speech Detection And Popularity Prediction, Filip Klubicka, Raquel Fernandez
Other resources
As research on hate speech becomes more and more relevant every day, most of it is still focused on hate speech detection. By attempting to replicate a hate speech detection experiment performed on an existing Twitter corpus annotated for hate speech, we highlight some issues that arise from doing research in the field of hate speech, which is essentially still in its infancy. We take a critical look at the training corpus in order to understand its biases, while also using it to venture beyond hate speech detection and investigate whether it can be used to shed light on other …
Is It Worth It? Budget-Related Evaluation Metrics For Model Selection, Filip Klubicka, Giancarlo Salton, John D. Kelleher
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 …
Adapt At Semeval-2018 Task 9: Skip-Gram Word Embeddings For Unsupervised Hypernym Discovery In Specialised Corpora, Alfredo Maldonado, Filip Klubicka
Adapt At Semeval-2018 Task 9: Skip-Gram Word Embeddings For Unsupervised Hypernym Discovery In Specialised Corpora, Alfredo Maldonado, Filip Klubicka
Other resources
This paper describes a simple but competitive unsupervised system for hypernym discovery. The system uses skip-gram word embeddings with negative sampling, trained on specialised corpora. Candidate hypernyms for an input word are predicted based on cosine similar- ity scores. Two sets of word embedding mod- els were trained separately on two specialised corpora: a medical corpus and a music indus- try corpus. Our system scored highest in the medical domain among the competing unsu- pervised systems but performed poorly on the music industry domain. Our approach does not depend on any external data other than raw specialised corpora.
Quantitative Fine-Grained Human Evaluation Of Machine Translation Systems: A Case Study On English To Croatian, Filip Klubicka, Antonio Toral, Victor Manuel Sanchez-Cartagena
Quantitative Fine-Grained Human Evaluation Of Machine Translation Systems: A Case Study On English To Croatian, Filip Klubicka, Antonio Toral, Victor Manuel Sanchez-Cartagena
Articles
This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established Multidimensional Quality Metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-to- Croatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different paradigms: pure phrase-based, factored phrase-based and neural. First, we design an MQM-compliant error taxonomy tailored to the relevant …
Judging Emotion From Low-Pass Filtered Naturalistic Emotional Speech, John Snel, Charlie Cullen
Judging Emotion From Low-Pass Filtered Naturalistic Emotional Speech, John Snel, Charlie Cullen
Conference papers
In speech, low frequency regions play a significant role in paralinguistic communication such as the conveyance of emotion or mood. The extent to which lower frequencies signify or contribute to affective speech is still an area for investigation. To investigate paralinguistic cues, and remove interference from linguistic cues, researchers can low-pass filter the speech signal on the assumption that certain acoustic cues characterizing affect are still discernible. Low-pass filtering is a practical technique to investigate paralinguistic phenomena, and is used here to investigate the inference of naturalistic emotional speech. This paper investigates how listeners perceive the level of Activation, and …
Obtaining Speech Assets For Judgement Analysis On Low-Pass Filtered Emotional Speech, John Snel, Charlie Cullen
Obtaining Speech Assets For Judgement Analysis On Low-Pass Filtered Emotional Speech, John Snel, Charlie Cullen
Conference papers
Investigating the emotional content in speech from acoustic characteristics requires separating the semantic con- tent from the acoustic channel. For natural emotional speech, a widely used method to separate the two channels is the use of cue masking. Our objective is to investigate the use of cue masking in non-acted emotional speech by analyzing the extent to which filtering impacts the perception of emotional content of the modified speech material. However, obtaining a corpus of emotional speech can be quite difficult whereby verifying the emotional content is an issue thoroughly discussed. Currently, speech research is showing a tendency toward constructing …
Forty Years Of Movie Hacking: Considering The Potential Implications Of The Popular Media Representation Of Computer Hackers From 1968 To 2008, Damian Gordon
Articles
Increasingly movies are being produced which feature plots that incorporate elements of computer security and hacking, and cumulatively these movies are creating a public perception as to the nature of computer security. This research examines movies that feature hackers (and hacking) to identify if any common themes emerge from these movies in their representation of these issues. To achieve this, first a corpus of hacking movies is created, and then using a qualitative data analysis technique, guidelines are developed which distinguish those movies that actually have the potential to create a perception with the general public. The resultant dataset is …
Harmonically Combined Contour Icons For Concurrent Auditory Display, Charlie Cullen, Eugene Coyle
Harmonically Combined Contour Icons For Concurrent Auditory Display, Charlie Cullen, Eugene Coyle
Conference papers
This paper considers the harmonic combination of basic melodic shapes known as contour icons in concurrent auditory displays. Existing work in the field (such as that concerning earcons) has considered the combination of patterns designed using low level cognitive features, and so effective streaming is difficult. This work investigates means by which musical patterns with high level cognitive features (such as contour) representing data values can be rendered concurrently, so that multiple data sets can be effectively conveyed using an auditory display. The detection and comprehension of harmonically combined contour icons was tested in comparison to those combined uniquely (non …
Musical Pattern Design Using Contour Icons, Charlie Cullen, Eugene Coyle
Musical Pattern Design Using Contour Icons, Charlie Cullen, Eugene Coyle
Conference papers
This paper considers the use of Contour Icons in the design and implementation of musical patterns, for the purposes of detection and recognition. Research work had endeavoured to deliver musical patterns that were both distinct and memorable, and to this end a set of basic melodic shapes were introduced using a Sonification application called TrioSon that had been designed for the purpose. Existing work in the field (such as that concerning Earcon design) has considered the mechanisms by which patterns may be made distinctive, but it is argued that separate consideration must be given to the method of making such …
Information Delivery On Mobile Devices Using Contour Icon Sonification, Charlie Cullen, Eugene Coyle
Information Delivery On Mobile Devices Using Contour Icon Sonification, Charlie Cullen, Eugene Coyle
Conference papers
This paper examines the use of musical patterns to convey information, specifically in the context of mobile devices. Existing mechanisms (such as the popularity of the Morse code SMS alert) suggest that the use of musical patterns on mobile devices can be a very efficient and powerful method of data delivery. Unique musical patterns based on templates known as Contour Icons are used to represent specific data variables, with the output rendering of these patterns being referred to as a Sonification of that data. Contour Icon patterns mimic basic shapes and structures, thus providing listeners with a means of categorising …
Trioson: A Graphical User Interface For Pattern Sonification, Charlie Cullen, Eugene Coyle
Trioson: A Graphical User Interface For Pattern Sonification, Charlie Cullen, Eugene Coyle
Conference papers
The TrioSon software allows users to map musical patterns to input data variables via a graphical user interface (GUI). The application is a Java routine designed to take input files of standard Comma Separated Values (CSV) format and output Standard Midi Files (SMF) using the internal Java Sound API. TrioSon renders output Sonifications from input data files for up to 3 user-defined parameters, allocated as bass, chord and melody instruments for the purposes of arrangement. In this manner each parameter concerned is distinguished by its individual instrumental timbre, with the option of rendering any combination of 1 to 3 parameters …
Information Delivery On Mobile Devices Using Boolean Sonification Patterns, Charlie Cullen, Eugene Coyle
Information Delivery On Mobile Devices Using Boolean Sonification Patterns, Charlie Cullen, Eugene Coyle
Conference papers
Sonification is the means by which non-speech audio can be used to convey information. Existing work has produced methods for delivering information in a wide range of fields, and recent work has considered the huge potential of mobile devices for Sonification. Boolean Sonification is a method of defining two related musical patterns as boolean conditions (true/false, yes/no etc.), such that one is considered contrary to the other by the listener. The final pattern set ideally comprises of two musical events that are closely enough related as to be considered a group, yet distinct enough to be perceived as separate entities. …
Analysis Of Data Sets Using Trio Sonification, Charlie Cullen, Eugene Coyle
Analysis Of Data Sets Using Trio Sonification, Charlie Cullen, Eugene Coyle
Conference papers
Recent advances in technology have suggested that sound and audio play a far greater part in our daily working lives than ever before. Mobile phone ring tones are now based upon polyphonic music sequences that allow relatively complex audio to be generated from a handset by way of conveying information (i.e. a call or message is incoming). This real world example of sonification suggests that far more could be made of sonification techniques for analysis- particularly in the business environment. One advantage of sonification is its relatively hands free nature in that once a sequence is being played it does …
Orchestration Within The Sonification Of Basic Data Sets, Charlie Cullen, Eugene Coyle
Orchestration Within The Sonification Of Basic Data Sets, Charlie Cullen, Eugene Coyle
Conference papers
The use of sonification as a means of representing and analysing data has become a growing field of research in recent years and as such has become a far more accepted means of working with data. Existing work carried out as part of this research has focused primarily on the sonification of DNA/RNA sequences and their subsequent protein structures for the purposes of analysis. This sonification work raised many questions as regards the need for sequences to be set to music in a standard manner so that different strands could be analysed by comparison, and hence the orchestration and instrumentation …
Rhythmic Parsing Of Sonified Dna And Rna Sequences, Charlie Cullen, Eugene Coyle
Rhythmic Parsing Of Sonified Dna And Rna Sequences, Charlie Cullen, Eugene Coyle
Conference papers
Sonification allows existing mathematical data to be used as the model for audio output, notably that the audio produced is related to or representative of that data in some way. Existing work in the field has been largely focused on the aesthetic tailoring of the output audio for compositional benefit rather than as a framework for audio representation and analysis. It is the goal of this research to apply existing techniques for pitch substitution to an analytical method that seeks to define and represent patterns within existing data sets (primarily DNA and RNA sequences). It is often the case that …