This paper describes the submission of the UPC Machine Translation group...
Data scarcity is one of the main issues with the end-to-end approach for...
Transformers have been the dominant architecture for Speech Translation ...
Speech translation models are unable to directly process long audios, li...
This paper describes the submission to the IWSLT 2021 offline speech
tra...
The standard approach to incorporate linguistic information to neural ma...
Current end-to-end approaches to Spoken Language Translation (SLT) rely ...
We propose a modular architecture of language-specific encoder-decoders ...
State-of-the-art multilingual machine translation relies on a universal
...
The dominant language modeling paradigms handle text as a sequence of
di...
Multilingual Neural Machine Translation approaches are based on the use ...
The dominant neural machine translation models are based on the
encoder-...
A common intermediate language representation or an interlingua is the h...
Universal language representation is the holy grail in machine translati...
Sorting networks are oblivious sorting algorithms with many practical
ap...
Sorting networks are oblivious sorting algorithms with many interesting
...
Natural language inference (NLI) is a central problem in language
unders...
Neural Machine Translation (MT) has reached state-of-the-art results.
Ho...
In this paper we derive variability measures for the conditional probabi...