A Statistical Spoken Dialogue System using Complex User Goals and Value Directed Compression
نویسندگان
چکیده
This paper presents the first demonstration of a statistical spoken dialogue system that uses automatic belief compression to reason over complex user goal sets. Reasoning over the power set of possible user goals allows complex sets of user goals to be represented, which leads to more natural dialogues. The use of the power set results in a massive expansion in the number of belief states maintained by the Partially Observable Markov Decision Process (POMDP) spoken dialogue manager. A modified form of Value Directed Compression (VDC) is applied to the POMDP belief states producing a near-lossless compression which reduces the number of bases required to represent the belief distribution.
منابع مشابه
Lossless Value Directed Compression of Complex User Goal States for Statistical Spoken Dialogue Systems
This paper presents initial results in the application of Value Directed Compression (VDC) to spoken dialogue management belief states for reasoning about complex user goals. On a small but realistic SDS problem VDC generates a lossless compression which achieves a 6-fold reduction in the number of dialogue states required by a Partially Observable Markov Decision Process (POMDP) dialogue manag...
متن کاملRepresenting Uncertainty about Complex User Goals in Statistical Dialogue Systems
We point out several problems in scalingup statistical approaches to spoken dialogue systems to enable them to deal with complex but natural user goals, such as disjunctive and negated goals and preferences. In particular, we explore restrictions imposed by current independence assumptions in POMDP dialogue models. This position paper proposes the use of Automatic Belief Compression methods to ...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملReal user evaluation of a POMDP spoken dialogue system using automatic belief compression
This article describes an evaluation of a POMDP-based spoken dialogue system (SDS), using crowdsourced calls with real users. he evaluation compares a “Hidden Information State” POMDP system which uses a hand-crafted compression of the belief space, ith the same system instead using an automatically computed belief space compression. Automatically computed compressions re a way of introducing a...
متن کامل