This paper discusses semantic processing using the Hidden Vector State (HVS) model. The HVS model extends the basic discrete Markov model by encoding context in each state as a vector. State transitions are then factored into a stack shift operation similar to those of a push-down automaton followed by a push of a new preterminal semantic category label. The key feature of the model is that it can capture hierarchical structure without the use of treebank data for training. Experiments have been conducted in the travel domain using the relatively simple ATIS corpus and the more complex DARPA Communicator Task. The results show that the HVS model can be robustly trained from only minimally annotated corpus data. Furthermore, when measured by its ability to extract attribute-value pairs from natural language queries in the travel domain, the HVS model outperforms a conventional finite-state semantic tagger by 4.1 % in F-measure for ATIS and by 6.6 % in F-measure for Communicator, suggesting that the benefit of the HVS model’s ability to encode context increases as the task becomes more complex.

Partially observable Markov decision processes (POMDPs) provide a principled mathematical framework for modelling the uncertainty inherent in spoken dialog systems. However, conventional POMDPs scale poorly with the size of state and observation space. This paper describes a variation of the classic POMDP called the Hidden Information State (HIS) model in which belief distributions are represented efficiently by grouping states together into partitions and policy optimisation is made tractable by using a master to summary space mapping. An implementation of the HIS model is described for a Tourist Information application and aspects of its training and operation are illustrated. Index Terms — statistical dialog modelling; partially observable Markov decision processes (POMDPs) 1.

Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular, the degree to which strategies learned with a user model generalise to real user populations has not be investigated. This paper presents a series of experiments that qualitatively and quantitatively examine the effect of the user model on the learned strategy. Our results show that the performance and characteristics of the strategy are in fact highly dependent on the user model. Furthermore, a policy trained with a poor user model may appear to perform well when tested with the same model, but fail when tested with a more sophisticated user model. This raises significant doubts about the current practice of learning and evaluating strategies with the same user model. The paper further investigates a new technique for testing and comparing strategies directly on real human-machine dialogues, thereby avoiding any evaluation bias introduced by the user model. 1.

Computer Speech and Language xxx (2009) xxx–xxx COMPUTER SPEECH AND LANGUAGE www.elsevier.com/locate/csl

As the complexity of spoken dialogue systems has increased, there has been increasing interest spoken language generation (SLG). SLG promises portability across application domains and dialogue situations through the development of applicationindependent linguistic modules. However in practice, rulebased SLGs often have to be tuned to the application. Recently, a number of research groups have been developing hybrid methods for spoken language generation, combining general linguistic modules with methods for training parameters for particular applications. This paper describes the use of boosting to train a sentence planner to generate recommendations for restaurants in MATCH, a multimodal dialogue system providing entertainment information for New York. 1.

This paper explains how partially observable Markov decision processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialog systems. It briefly summarises the basic mathematics and explains why exact optimisation is intractable. It then describes a form of approximation called the Hidden Information State model which does scale and which can be used to build practical systems. Index Terms — statistical dialog modelling; partially observable Markov decision processes (POMDPs); hidden information state model 1.

We present a preliminary report of a probabilistic spoken-language interpretation mechanism that is part of a dialogue system for an office assistant robot. We offer a probabilistic formulation for the generation of candidate interpretations and the selection of the interpretation with the highest posterior probability. This formulation is implemented in a multi-layered interpretation process that integrates spoken and sensory input, and takes into account alternatives derived from a user’s utterance and expectations obtained from the context. Our preliminary results are encouraging. 1

We present a variant of the WOz paradigm we refer to as incremental ablation. The new feature involves incrementally restricting the human wizard’s capacities in the direction of a dialog system. We lay out a data collection design with six conditions of user-system and user-wizard interactions that allows us to more precisely identify how to close the communication gap between humans and systems. We describe the application of the method to analysis of contexts in which ASR errors occur, giving us a means to investigate the problemsolving strategies humans would resort to if their communication channel were restricted to be more like the machine’s. We describe how we can use the methodology to collect data that is more relevant to a particular learning paradigm involving Markov Decision Processes (MDP).

Abstract. This paper presents a corpus-based approach for cooperative response generation in a spoken dialog system for the Hong Kong tourism domain. A corpus with 3874 requests and responses is collected using Wizard-of-Oz framework. The corpus then undergoes a regularization process that simplifies the interactions to ease subsequent modeling. A semi-automatic process is developed to annotate each utterance in the dialog turns in terms of their key concepts (KC), task goal (TG) and dialog acts (DA). TG and DA characterize the informational goal and communicative goal of the utterance respectively. The annotation procedure is integrated with a dialog modeling heuristic and a discourse inheritance strategy to generate a semantic abstraction (SA), in the form of {TG, DA, KC}, for each user request and system response in the dialog. Semantic transitions, i.e. {TG, DA, KC}user→{TG, DA, KC} system, may hence be directly derived from the corpus as rules for response message planning. Related verbalization methods may also be derived from the corpus and used as templates for response message realization. All the rules and templates are stored externally in a human-readable text file which brings the advantage of easy extensibility of the system. Evaluation of this corpus based approach shows that 83 % of the generated responses are coherent with the user’s request and qualitative rating achieves a score of 4.0 on a five-point Likert scale.

This overview article reviews the structure of a fully statistical spoken dialogue system (SDS), using as illustration, various systems and components built at Cambridge over the last few years. Most of the components in an SDS are essentially classifiers which can be trained using supervised learning. However, the dialogue management component must track the state of the dialogue and optimise a reward accumulated over time. This requires techniques for statistical inference and policy optimisation using reinforcement learning. The potential advantages of a fully statistical SDS are the ability to train from data without hand-crafting, increased robustness to environmental noise and user uncertainty, and the ability to adapt and learn on-line. Index Terms: spoken dialogue systems, reinforcement learning, speech understanding, speech synthesis, natural language