2 code implementations • 19 Jul 2021 • William Blanzeisky, Pádraig Cunningham, Kenneth Kennedy
A significant impediment to progress in research on bias in machine learning (ML) is the availability of relevant datasets.
1 code implementation • ACL 2021 • Linyi Yang, Jiazheng Li, Pádraig Cunningham, Yue Zhang, Barry Smyth, Ruihai Dong
While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data.
no code implementations • 31 May 2021 • William Blanzeisky, Pádraig Cunningham
Algorithmic Bias can be due to bias in the training data or issues with the algorithm itself.
1 code implementation • 28 Apr 2021 • William Blanzeisky, Pádraig Cunningham
It is fair to say that many of the prominent examples of bias in Machine Learning (ML) arise from bias that is there in the training data.
no code implementations • 11 Oct 2020 • Vivek Mahato, Pádraig Cunningham
It is well understood that Dynamic Time Warping (DTW) is effective in revealing similarities between time series that do not align perfectly.
no code implementations • 12 Jan 2016 • Ewa Młynarska, Derek Greene, Pádraig Cunningham
In this paper we conduct an analysis of Moodle activity data focused on identifying early predictors of good student performance.
no code implementations • 29 Jul 2014 • Xiangju Qin, Derek Greene, Pádraig Cunningham
Collaborations such as Wikipedia are a key part of the value of the modern Internet.
1 code implementation • 16 Apr 2014 • Derek Greene, Derek O'Callaghan, Pádraig Cunningham
Topic modeling refers to the task of discovering the underlying thematic structure in a text corpus, where the output is commonly presented as a report of the top terms appearing in each topic.
no code implementations • 12 Mar 2014 • Igor Brigadir, Derek Greene, Pádraig Cunningham
In this paper we examine the effectiveness of adaptive mechanisms for tracking and summarizing breaking news stories.
no code implementations • 15 Apr 2013 • Conrad Lee, Bobo Nick, Ulrik Brandes, Pádraig Cunningham
State-of-the-art link prediction utilizes combinations of complex features derived from network panel data.