no code implementations • ACL (NL4XAI, INLG) 2020 • Juliette Faille, Albert Gatt, Claire Gardent
End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain.
no code implementations • Findings (EMNLP) 2021 • Juliette Faille, Albert Gatt, Claire Gardent
While powerful pre-trained language models have improved the fluency of text generation models, semantic adequacy -the ability to generate text that is semantically faithful to the input- remains an unsolved issue.
no code implementations • 11 Apr 2024 • Juliette Faille, Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona, Claire Gardent
We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation.