From rule-based to data-driven lexical entrainment models in spoken dialog systems

This paper presents uses a data-driven approach to improve Spoken Dialog System (SDS) performance by automatically finding the most appropriate terms to be used in system prompts. The literature shows that speakers use one another's terms (entrain) when trying to create common ground during a spoken dialog. Those terms are commonly called “primes”, since they influence the interlocutors' linguistic decision-making. This approach emulates human interaction, with a system built to propose primes to the user and accept the primes that the user proposes. These primes are chosen on the fly during the interaction, based on a set of features that indicate good candidate primes. A good candidate is one that we know is easily recognized by the speech recognizer, and is also a normal word choice given the context. The system is trained to follow the user's choice of prime if system performance is not negatively affected. When system performance is affected, the system proposes a new prime. In our previous work we have shown how we can identify the prime candidates and how the system can select primes using rules. In this paper we go further, presenting a data-driven method to perform the same task. Live tests with this method show that use of on-the-fly entrainment reduces out-of-vocabulary and word error rate, and also increases the number of correctly transferred concepts.