activity
20162024
most citedAutoregressive Convolutional Recurrent Neural Network for Univariate and Multivariate Time Series Prediction

11 citations · 42 across the 17 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2024

Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain

Antoine Louis, Gijs van Dijck, Gerasimos Spanakis

Hybrid search has emerged as an effective strategy to offset the limitations of different matching paradigms, especially in out-of-domain contexts where notable improvements in ret…

cs.CL2021

Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer

Błażej Dolicki, Gerasimos Spanakis

There is an increasing amount of evidence that in cases with little or no data in a target language, training on a different language can yield surprisingly good results. However,…

cs.CL2020

"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…

cs.CL202011 cited

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…

cs.CL20201 cited

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…

cs.CL2020

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…