6 papers
I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures
Timothee Mickus, Raúl Vázquez, Joseph Attieh
Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study,…
SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
Timothee Mickus, Elaine Zosa, Raúl Vázquez +5
This paper presents the results of the SHROOM, a shared task focused on detecting hallucinations: outputs from natural language generation (NLG) systems that are fluent, yet inaccu…
Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?
Shaoxiong Ji, Timothee Mickus, Vincent Segonne +1
Multilingual pretraining and fine-tuning have remarkably succeeded in various natural language processing tasks. Transferring representations from one language to another is especi…
MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki
Timothee Mickus, Stig-Arne Grönroos, Joseph Attieh +7
NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled. The trend goes to modularization, a necessary ste…
Grounded and Well-rounded: A Methodological Approach to the Study of Cross-modal and Cross-lingual Grounding
Timothee Mickus, Elaine Zosa, Denis Paperno
Grounding has been argued to be a crucial component towards the development of more complete and truly semantically competent artificial intelligence systems. Literature has divide…
Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings
Timothee Mickus, Raúl Vázquez
A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inp…