Spoken dialog systems based on online generated stochastic finite-state transducers

Abstract

In this paper, we present an approach for the development of spoken dialog systems based on the statistical modelization of the dialog manager. This work focuses on three points: the modelization of the dialog manager using Stochastic Finite-State Transducers, an unsupervised way to generate training corpora, and a mechanism to address the problem of coverage that is based on the online generation of synthetic dialogs. Our proposal has been developed and applied to a sport facilities booking task at the university. We present experimentation evaluating the system behavior on a set of dialogs that was acquired using the Wizard of Oz technique as well as experimentation with real users. The experimentation shows that the method proposed to increase the coverage of the Dialog System was useful to find new valid paths in the model to achieve the user goals, providing good results with real users.

Adaptive dialogue management using intent clustering and fuzzy rules

“…The DM 1 and DM 2 dialogue models for the Edecan task respectively achieved a 83 and 80% of successful dialogues. With regard to the previous studies that have used the Edecan corpus, a 78.80% percentage of successful dialogues were obtained for the statistical dialogue model and user simulation techniques proposed in (Griol et al, 2014), a percentage of 73.40% successful dialogues was obtained in a stochastic finite‐state transducers model proposed in (Hurtado et al, 2016).…”

“…EDECAN (Hurtado, Planells, Segarra, & Sanchis, 2016) is a multilingual, multimodal, mixed-initiative information system for booking sport facilities.…”

“…However, in certain scenarios it may be difficult and costly to foresee which form of system behaviour will lead to a quick and successful completion of the dialogue. This has motivated the research community to find ways for automating dialogue learning using statistical models trained with real conversations (Griol et al, 2014; Griol, Hurtado, Segarra, & Sanchis, 2008; Hurtado, Planells, Segarra, Sanchis, & Griol, 2010; Young, Gasic, Thomson, & Williams, 2013). These models allow to explore a wider range of strategies to model the variability of user behaviours.…”

“…However, it is limited to small‐scale problems, since they require many hand‐crafted features for the state and action space representation (Young, Schatzmann, Weilhammer, & Ye, 2007). Other interesting approaches for statistical DM are based on modelling the system by means of Hidden Markov models (HMMs; Cuayáhuitl, Renals, Lemon, & Shimodaira, 2005), stochastic finite‐state transducers (Hurtado et al, 2010), Bayesian networks (Meng, Wai, & Pieraccini, 2003), or recurrent neural networks (Gao, Galley, & Li, 2019) and Reinforcement Deep Learning Cuayáhuitl, Keizer, and Lemon (2015).…”

“…EDECAN (Hurtado, Planells, Segarra, & Sanchis, 2016) is a multilingual, multimodal, mixed‐initiative information system for booking sport facilities. Users can book, cancel and ask for the availability of sport facilities.…”