Di Maro, Maria (2021) "Shouldn't I use a polarquestion?" Proper Question Forms Disentangling Inconsistencies in Dialogue Systems. [Tesi di dottorato]
Anteprima |
Testo
DI_MARO_33.pdf Download (11MB) | Anteprima |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | "Shouldn't I use a polarquestion?" Proper Question Forms Disentangling Inconsistencies in Dialogue Systems |
| Autori: | Autore Email Di Maro, Maria maria.dimaro2@unina.it |
| Data: | 2021 |
| Numero di pagine: | 196 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Studi Umanististici |
| Dottorato: | Mind, gender and languages |
| Ciclo di dottorato: | 33 |
| Coordinatore del Corso di dottorato: | nome email Bacchini, Dario dario.bacchini@unina.it |
| Tutor: | nome email Cutugno, Francesco [non definito] Kopp, Stefan [non definito] Turrizziani, Paolo [non definito] |
| Data: | 2021 |
| Numero di pagine: | 196 |
| Parole chiave: | common ground inconsistensies, clarification requests, human-machine interaction |
| Settori scientifico-disciplinari del MIUR: | Area 10 - Scienze dell'antichità, filologico-letterarie e storico-artistiche > L-LIN/01 - Glottologia e linguistica |
| Depositato il: | 25 Apr 2021 15:32 |
| Ultima modifica: | 07 Giu 2023 10:22 |
| URI: | http://www.fedoa.unina.it/id/eprint/14051 |
Abstract
This work reports on the description of a specific class of clarification requests, adopted for the negotiation of pieces of information part of the common ground for argumentation strategies in human-machine interaction. Two studies are carried out to prove the adequateness of a specific form of polar question in a specific pragmatic situation, where a presupposition is contradicted by a new evidence. Whereas the first one proves the appropriateness of the negative form, the second one also demonstrate how the use of such a form, in the aforementioned pragmatic situation, can affect the principle of robustness, in terms of observability and recoverability, important in human–machine interaction applications. Given the results obtained in the two studies, dialogue systems with such capabilities are, therefore, a desirable goal, as they are expected to lead to improved usability and naturalness in conversation. For this reason, I present here a system capable of detecting conflicts and of using argumentation strategies to signal them consistently with previous observations.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
