Cross-Lingual spoken language understanding from unaligned data using discriminative classification models and machine translation

This paper investigates several approaches to bootstrapping a new spoken language understanding (SLU) component in a target language given a large dataset of semantically-annotated utterances in some other source language. The aim is to reduce the cost associated with porting a spoken dialogue system from one language to another by minimising the amount of data required in the target language. Since word-level semantic annotations are costly, Semantic Tuple Classifiers (STCs) are used in conjunction with statistical machine translation models both of which are trained from unaligned data to further reduce development time. The paper presents experiments in which a French SLU component in the tourist information domain is bootstrapped from English data. Results show that training STCs on automatically translated data produced the best performance for predicting the utterance's dialogue act type, however individual slot/value pairs are best predicted by training STCs on the source language and using them to decode translated utterances. © 2010 ISCA.

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. © 2011 Elsevier Ltd. All rights reserved.

Gaussian processes for fast policy optimisation of POMDP-based dialogue managers

Modelling dialogue as a Partially Observable Markov Decision Process (POMDP) enables a dialogue policy robust to speech understanding errors to be learnt. However, a major challenge in POMDP policy learning is to maintain tractability, so the use of approximation is inevitable. We propose applying Gaussian Processes in Reinforcement learning of optimal POMDP dialogue policies, in order (1) to make the learning process faster and (2) to obtain an estimate of the uncertainty of the approximation. We first demonstrate the idea on a simple voice mail dialogue task and then apply this method to a real-world tourist information dialogue task. © 2010 Association for Computational Linguistics.

Everywhere and nowhere: nearshore software development in the context of globalisation

Offshore software development has been identified as one of the most striking manifestations of contemporary globalisation and as evidence of placelessness, the idea that information and communication technologies have rendered location irrelevant. Research in the International Business and Information Systems fields, in contrast, has suggested that all locations are not equal and has identified a number of characteristics that may influence the attractiveness of a location for multinational investment and offshoring, respectively. These literatures, however, focus almost exclusively on quantitative, economic characteristics that are seen as fixed and applying uniformly throughout a whole country. They therefore offer little guidance on the suitability of particular locations as offshoring destinations, especially in countries without a track record in offshore software development. Drawing on two cases of nearshore software development centres set up by offshore service providers in the Caribbean, this paper illustrates that, while the initial decision to establish the ventures reflected a logic of placelessness, characteristics of these particular locations affected their subsequent success. Through the findings, we therefore develop a typology of espoused, unanticipated and remediable locational characteristics, which illustrates that locational attractiveness may vary significantly within countries and that offshore service providers and government agencies can modify locational characteristics to their advantage.

Reusing steel and aluminum components at end of product life.

Reusing steel and aluminum components would reduce the need for new production, possibly creating significant savings in carbon emissions. Currently, there is no clearly defined set of strategies or barriers to enable assessment of appropriate component reuse; neither is it possible to predict future levels of reuse. This work presents a global assessment of the potential for reusing steel and aluminum components. A combination of top-down and bottom-up analyses is used to allocate the final destinations of current global steel and aluminum production to product types. A substantial catalogue has been compiled for these products characterizing key features of steel and aluminum components including design specifications, requirements in use, and current reuse patterns. To estimate the fraction of end-of-life metal components that could be reused for each product, the catalogue formed the basis of a set of semistructured interviews with industrial experts. The results suggest that approximately 30% of steel and aluminum used in current products could be reused. Barriers against reuse are examined, prompting recommendations for redesign that would facilitate future reuse.