Computer Science (Scholarly Publications): Recent submissions
Now showing items 181-200 of 1420
-
Detecting the Point of Release of Virtual Projectiles in AR/VR
(2021)Our aim is to detect the point of release of a thrown virtual projectile in VR/AR. We capture the full-body motion of 18 participants throwing virtual projectiles and extract motion features, such as position, velocity, ... -
Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing
(2018)Convolutional neural networks (CNNs) are one of the most successful machine-learning techniques for image, voice, and video processing. CNNs require large amounts of processing capacity and memory bandwidth. Hardware ... -
A Modified AIM Quality Questionnaire
(2019) -
An Ontology for Standardising Trustworthy AI
(IntechOpen, 2021)Worldwide, there are a multiplicity of parallel activities being undertaken in developing international standards, regulations and individual organisational policies related to AI and its trustworthiness characteristics. ... -
Continuous Measurement Scales in Human Evaluation of Machine Translation
(Association for Computational Linguistics, 2013)We explore the use of continuous rating scales for human evaluation in the context of machine translation evaluation, comparing two assessor-intrinsic quality-control techniques that do not rely on agreement with expert ... -
TRECVID 2018: Benchmarking Video Activity Detection, Video Captioning and Matching, Video Storytelling Linking and Video Search
(2018)The TREC Video Retrieval Evaluation (TRECVID)2018 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in research and development of content-based exploitation and retrieval ... -
Results of the WMT17 Metrics Shared Task
(Association for Computational Linguistics, 2017)This paper presents the results of the WMT17 Metrics Shared Task. We asked participants of this task to score the outputs of the MT systems involved in the WMT17 news translation task and Neural MT training task. We collected ... -
Findings of the 2017 Conference on Machine Translation (WMT17)
(2017)This paper presents the results of theWMT17 shared tasks, which included three machine translation (MT) tasks(news, biomedical, and multimodal), two evaluation tasks (metrics and run-time estimation of MT quality), ... -
Accurate Evaluation of Segment-level Machine Translation Metrics
(Association for Computational Linguistics, 2015) -
Is all that glitters in MT quality estimation really gold standard?
(2016)Human-targeted metrics provide a compromise between human evaluation of machine translation, where high inter-annotator agreement is difficult to achieve, and fully automatic metrics, such as BLEU or TER, that lack the ... -
Role of Identity, Identification, and Receipts for Consent
(2021)This article outlines issues in the current ecosystem of data sharing based on consent and the role of identity and identification. It argues how the consent mechanism is hostile to individuals in the form of: (a) inscrutable ... -
Challenge-based learning in higher education: an exploratory literature review
(2020)The application of Challenge-Based Learning (CBL) has increased in higher education institutions, fostering student transversal competencies, knowledge of sociotechnical problems, and collaboration with industry and community ... -
Improving Document-level Sentiment Analysis with User and Product Context
(Association for Computational Linguistics, 2020)Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investigate incorporating additional review text ... -
Assessing Human-Parity in Machine Translation on the Segment Level
(Association for Computational Linguistics, 2020)Recent machine translation shared tasks have shown top-performing systems to tie or in some cases even outperform human translation. Such conclusions about system and human performance are, however, based on estimates ... -
The Third Multilingual Surface Realisation Shared Task (SR-20): Overview and Evaluation Results
(2020)This paper presents results from the Third Shared Task on Multilingual Surface Realisation (SR’20) which was organised as part of the COLING’20 Workshop on Multilingual Surface Realisation. As in SR’18 and SR’19, the shared ... -
The Impact of Training Data Bias on Automatic Generation of Video Captions
(2019)A major issue in machine learning is availability of training data. While this historically referred to the availability of a sufficient volume of training data, recently this has shifted to the availability of sufficient ... -
Statistical Power and Translationese in Machine Translation Evaluation
(Association for Computational Linguistics, 2020)The term translationese has been used to describe features of translated text, and in this paper, we provide detailed analysis of potential adverse effects of translationese on machine translation evaluation. Our analysis ... -
Urban Intelligence with Deep Edges
(2020)With the increased accuracy available from state of the art deep learning models and new embedded devices at the edge of the network capable of running and updating these models there is potential for urban intelligence ... -
[How] Do Users Benefit From Giving Consent?
(2021)Consent is meant to empower users by giving them a choice regarding the use of their personal data. Thus, organisations have the incentive to provide benefits, whether directly or indirectly, in return ... -
Crowd-sourcing Multi-Domain Issues in Consent Dialogues for Automated Generation of Legal Complaints
(2021)Analysis of dark patterns in consent dialogues includes issues that several domains: HCI for the analysis of interaction mechanisms; psychology and ethics for understanding impact to the individual, technological understanding ...
