Paul A. Crook

Learn More
— For mobile robots, as well as other learning systems, the ability to highlight unexpected features of their environment – novelty detection – is very useful. One particularly important application for a robot equipped with novelty detection is inspection, highlighting potential problems in an environment. In this paper two novelty filters, both of which(More)
We point out several problems in scaling-up 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(More)
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(More)
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(More)
We present a novel application of hypothesis ranking (HR) for the task of domain detection in a multi-domain, multi-turn dialog system. Alternate, domain dependent, semantic frames from a spoken language understanding (SLU) analysis are ranked using a gradient boosted decision trees (GBDT) ranker to determine the most likely domain. The ranker, trained(More)
Due to the unavoidable fact that a robot's sensors will be limited in some manner, it is entirely possible that it can find itself unable to distinguish between differing states of the world (the world is in effect partially observable). If reinforcement learning is used to train the robot, then this confounding of states can have a serious effect on its(More)
We propose Inference Knowledge Graph, a novel approach of remapping existing, large scale, semantic knowledge graphs into Markov Random Fields in order to create user goal tracking models that could form part of a spoken dialog system. Since semantic knowledge graphs include both entities and their attributes, the proposed method merges the semantic(More)
This article describes an evaluation of a POMDP-based spoken dialogue system (SDS), using crowdsourced calls with real users. The evaluation compares a " Hidden Information State " POMDP system which uses a hand-crafted compression of the belief space, with the same system instead using an automatically computed belief space compression. Automatically(More)
Belief compression improves the tractability of large-scale partially observable Markov decision processes (POMDPs) by finding projections from high-dimensional belief space onto low-dimensional approximations, where solving to obtain action selection policies requires fewer computations. This paper develops a unified theoretical framework to analyse three(More)