Reinforcement Learning for Personalized Dialogue Management

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hengst, Floris den, Hoogendoorn, Mark, van Harmelen, Frank, Bosman, Joost
Formato: Preprint
Publicado: 2019
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914670639579136
author Hengst, Floris den
Hoogendoorn, Mark
van Harmelen, Frank
Bosman, Joost
author_facet Hengst, Floris den
Hoogendoorn, Mark
van Harmelen, Frank
Bosman, Joost
contents Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.
format Preprint
id arxiv_https___arxiv_org_abs_1908_00286
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Reinforcement Learning for Personalized Dialogue Management
Hengst, Floris den
Hoogendoorn, Mark
van Harmelen, Frank
Bosman, Joost
Machine Learning
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.
title Reinforcement Learning for Personalized Dialogue Management
topic Machine Learning
Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/1908.00286