36 citations · 154 across the 56 of their papers we have counts for
5 papers · 2 filters
"Thy algorithm shalt not bear false witness": An Evaluation of Multiclass Debiasing Methods on Word Embeddings
Thalea Schlender, Gerasimos Spanakis
With the vast development and employment of artificial intelligence applications, research into the fairness of these algorithms has been increased. Specifically, in the natural la…
Evaluating Bias In Dutch Word Embeddings
Rodrigo Alejandro Chávez Mulsa, Gerasimos Spanakis
Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world app…
Adapting End-to-End Speech Recognition for Readable Subtitles
Danni Liu, Jan Niehues, Gerasimos Spanakis
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce out…
Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
Danni Liu, Gerasimos Spanakis, Jan Niehues
Encoder-decoder models provide a generic architecture for sequence-to-sequence tasks such as speech recognition and translation. While offline systems are often evaluated on qualit…
Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification
Maria Mihaela Trusca, Gerasimos Spanakis
The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of…