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 are(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)
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. This confounding of states, also referred to as perceptual aliasing, has serious effects on the ability of reinforcement learning algorithms to learn stable policies.(More)
Spoken language understanding and dialog management have emerged as key technologies in interacting with personal digital assistants (PDAs). The coverage, complexity, and the scale of PDAs are much larger than previous conversational understanding systems. As such, new problems arise. In this paper, we provide an overview of the language understanding and(More)
In applying reinforcement learning to agents acting in the real world we are often faced with tasks that are non-Markovian in nature. Much work has been done using state estimation algorithms to try to uncover Markovian models of tasks in order to allow the learning of optimal solutions using reinforcement learning. Unfortunately these algorithms which(More)
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(More)
We present a novel application of hypothesis ranking (HR) for the task of domain detection in a multi-domain, multiturn 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 using(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)
We demonstrate the Task Completion Platform (TCP); a multi-domain, multi-turn dialogue platform that can host and execute large numbers of goal-orientated dialogue tasks. The platform features a task configuration language, Task Form, that allows the definition of each individual task to be decoupled from the overarching dialogue policy used by the platform(More)
In this paper, we present an approach to improve the accuracy of multi-domain multi-turn spoken dialog system (SDS) by including alternate results from automatic speech recognition (ASR). Often, even if the top ranked result from the ASR is not correct, the correct result may still be available in the NBest list or in the word confusion network (WCN). Thus,(More)