Papers by Giancarlo Xompero
Every time I fire a conversational designer, the performance of the dialogue system goes down (2022.lrec-1)
Copied to clipboard
Giancarlo Xompero, Michele Mastromattei, Samir Salman, Cristina Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
| Challenge: | Incorporating handwritten domain scripts into neural-based task-oriented dialogue systems may be an effective way to reduce the need for large sets of annotated dialogues. |
| Approach: | They propose a system where domain scripts are coded in semi-logical rules and evaluated semi-logic rules produced by differently-skilled conversational designers. |
| Outcome: | The proposed system outperforms state-of-the-art systems when trained with smaller sets of annotated dialogues. |