Safe transfer learning for dialogue applications

Nicolas Carrara (1, 2) , Romain Laroche (3) , Jean-Léon Bouraoui (1) , Tanguy Urvoy (1) , Olivier Pietquin (4)

1 Orange Labs [Lannion]
2 SEQUEL - Sequential Learning
3 Maluuba
4 Google Inc

In this paper, we formulate the hypothesis that the first dialogues with a new user should be handle in a very conservative way, for two reasons : avoid user dropout; gather more successful dialogues to speedup the learning of the asymptotic strategy. To this extend, we propose to transfer a safe strategy to initiate the first dialogues.

Mots clés: Safety; Transfer Learning; Dialogue

Domaines: Intelligence artificielle [cs.AI]; Informatique [cs]; Apprentissage [cs.LG]

Nicolas Carrara, Romain Laroche, Jean-Léon Bouraoui, Tanguy Urvoy, Olivier Pietquin. Safe transfer learning for dialogue applications. SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing, Oct 2018, Mons, Belgium. ⟨hal-01928102⟩