This study is set in the framework of taskoriented conversational agents in which dialogue management is obtained via reinforcement Learning. The aim is to explore the possibility to overcome the typical end-to-end training approach through the integration of a quantitative model developed in the field of persuasion psychology. Such integration is expected to accelerate the training phase and improve the quality of the dialogue obtained. In this way, the resulting agent would take advantage of some subtle psychological aspects of the interaction that would be difficult to elicit via end-to-end training. We propose a theoretical architecture in which the psychological model above is translated into a probabilistic predictor and then integrated in the reinforcement learning process, intended in its partially observable variant. The experimental validation of the architecture proposed is currently ongoing.
Di Massimo, F., Carfora, V., Catellani, P., Marco, P., Applying psychology of persuasion to conversational agents through reinforcement learning: An exploratory study, <<Proceedings of the Sixth Italian Conference on Computational Linguistics>>, 2019; (2481): 1-6 [http://hdl.handle.net/10807/151044]
Applying psychology of persuasion to conversational agents through reinforcement learning: An exploratory study
Carfora, ValentinaSecondo
;Catellani, PatriziaPenultimo
;
2019
Abstract
This study is set in the framework of taskoriented conversational agents in which dialogue management is obtained via reinforcement Learning. The aim is to explore the possibility to overcome the typical end-to-end training approach through the integration of a quantitative model developed in the field of persuasion psychology. Such integration is expected to accelerate the training phase and improve the quality of the dialogue obtained. In this way, the resulting agent would take advantage of some subtle psychological aspects of the interaction that would be difficult to elicit via end-to-end training. We propose a theoretical architecture in which the psychological model above is translated into a probabilistic predictor and then integrated in the reinforcement learning process, intended in its partially observable variant. The experimental validation of the architecture proposed is currently ongoing.File | Dimensione | Formato | |
---|---|---|---|
18_clicit2019.pdf
accesso aperto
Tipologia file ?:
Versione Editoriale (PDF)
Licenza:
Creative commons
Dimensione
453.24 kB
Formato
Adobe PDF
|
453.24 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.