research
∙
05/21/2022
Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese
Multilingual language models such as mBERT have seen impressive cross-li...
share
research
∙
11/15/2021
Data Augmentation for Speech Recognition in Maltese: A Low-Resource Perspective
Developing speech technologies is a challenge for low-resource languages...
research
∙
09/14/2021
On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning
Recent work has shown evidence that the knowledge acquired by multilingu...
research
∙
08/14/2020
Annotating for Hate Speech: The MaNeCo Corpus and Some Input from Critical Discourse Analysis
This paper presents a novel scheme for the annotation of hate speech in ...
research
∙
08/13/2020
MASRI-HEADSET: A Maltese Corpus for Speech Recognition
Maltese, the national language of Malta, is spoken by approximately 500,...
research
∙
07/23/2020
The societal and ethical relevance of computational creativity
In this paper, we provide a philosophical account of the value of creati...
research
∙
06/21/2020
A blindspot of AI ethics: anti-fragility in statistical prediction
With this paper, we aim to put an issue on the agenda of AI ethics that ...
research
∙
06/09/2019
Learning to Predict Novel Noun-Noun Compounds
We introduce temporally and contextually-aware models for the novel task...
research
∙
06/06/2019
Measuring the compositionality of noun-noun compounds over time
We present work in progress on the temporal progression of compositional...
research
∙
03/10/2018