Open–domain dialogue systems should be able to cover a very large set of domains and at the same time keep the user engaged in the interaction. Current approaches to dialogue modeling are divided between domain–independent, non–modular approaches using sequence–to–sequence models and the domain–specific modular systems developed for task–based dialogue. Furthermore, user engagement in dialogue, addressed in this bot challenge, is a rather new research area. In this work we describe Roving Mind, a dialogue system which combines domain– independence with a modular architecture for open–domain spoken conversation, with a specific module for user engagement. Our architecture takes a balanced approach between human expert design and data–driven approaches, adapting the traditional task–based architecture relying on slots and intents to open–domain conversation using entities and domain-independent dialogue acts. The system was tested extensively during the Alexa Prize semifinals and received ratings from a large number of users, which allowed us to draw statistically relevant facts on how users interact with an open domain, non task-based social bot. Our experiments show that on average users give higher ratings to task-driven conversations (using user–entertaining strategies) compared to completely open–topic conversations. We also find a correlation between cumulative sentiment (using sentiment and dialogue acts) and user ratings and argue that this could be investigated to estimate an error–signal for strategy computation.

Roving Mind: a balancing act between open–domain and engaging dialogue systems / Cervone, Alessandra; Tortoreto, Giuliano; Mezza, Stefano; Gambi, Enrico; Riccardi, Giuseppe. - ELETTRONICO. - 1:(2017), pp. 1-10. (Intervento presentato al convegno Alexa Prize tenutosi a Las Vegas nel 20 November 2017).

Roving Mind: a balancing act between open–domain and engaging dialogue systems

Cervone, Alessandra;Tortoreto, Giuliano;Riccardi, Giuseppe
2017-01-01

Abstract

Open–domain dialogue systems should be able to cover a very large set of domains and at the same time keep the user engaged in the interaction. Current approaches to dialogue modeling are divided between domain–independent, non–modular approaches using sequence–to–sequence models and the domain–specific modular systems developed for task–based dialogue. Furthermore, user engagement in dialogue, addressed in this bot challenge, is a rather new research area. In this work we describe Roving Mind, a dialogue system which combines domain– independence with a modular architecture for open–domain spoken conversation, with a specific module for user engagement. Our architecture takes a balanced approach between human expert design and data–driven approaches, adapting the traditional task–based architecture relying on slots and intents to open–domain conversation using entities and domain-independent dialogue acts. The system was tested extensively during the Alexa Prize semifinals and received ratings from a large number of users, which allowed us to draw statistically relevant facts on how users interact with an open domain, non task-based social bot. Our experiments show that on average users give higher ratings to task-driven conversations (using user–entertaining strategies) compared to completely open–topic conversations. We also find a correlation between cumulative sentiment (using sentiment and dialogue acts) and user ratings and argue that this could be investigated to estimate an error–signal for strategy computation.
2017
1st Alexa Prize Proceedings
Seattle
Amazon
Cervone, Alessandra; Tortoreto, Giuliano; Mezza, Stefano; Gambi, Enrico; Riccardi, Giuseppe
Roving Mind: a balancing act between open–domain and engaging dialogue systems / Cervone, Alessandra; Tortoreto, Giuliano; Mezza, Stefano; Gambi, Enrico; Riccardi, Giuseppe. - ELETTRONICO. - 1:(2017), pp. 1-10. (Intervento presentato al convegno Alexa Prize tenutosi a Las Vegas nel 20 November 2017).
File in questo prodotto:
File Dimensione Formato  
Rovingmind.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 654.53 kB
Formato Adobe PDF
654.53 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/193586
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact