Ramón Granell

Unsupervised Classification of Dialogue Acts using a Dirichlet Process Mixture Model

In recent years Dialogue Acts have become a popular means of modelling the communicative intentions of human and machine utterances in many modern dialogue systems. Many of these systems rely heavily on the availability of dialogue corpora that have been annotated with Dialogue Act labels. The manual annotation of dialogue corpora is both tedious and expensive. Consequently, there is a growing interest in unsupervised systems that are capable of automating the annotation process. This paper investigates the use of a Dirichlet Process Mixture Model as a means of clustering dialogue utterances in an unsupervised manner. These clusters can then be analysed in terms of the possible Dialogue Acts that they might represent. The results presented here are from the application of the Dirichlet Process Mixture Model to the Dihana corpus.

Statistical framework for a Spanish spoken dialogue corpus

Dialogue systems are one of the most interesting applications of speech and language technologies. There have recently been some attempts to build dialogue systems in Spanish, and some corpora have been acquired and annotated. Using these corpora, statistical machine learning methods can be applied to try to solve problems in spoken dialogue systems. In this paper, two statistical models based on the maximum likelihood assumption are presented, and two main applications of these models on a Spanish dialogue corpus are shown: labelling and decoding. The labelling application is useful for annotating new dialogue corpora. The decoding application is useful for implementing dialogue strategies in dialogue systems. Both applications centre on unsegmented dialogue turns. The obtained results show that, although limited, the proposed statistical models are appropriate for these applications.

Impacts of Raw Data Temporal Resolution Using Selected Clustering Methods on Residential Electricity Load Profiles

There is growing interest in discerning behaviors of electricity users in both the residential and commercial sectors. With the advent of high-resolution time-series power demand data through advanced metering, mining this data could be costly from the computational viewpoint. One of the popular techniques is clustering, but depending on the algorithm the resolution of the data can have an important influence on the resulting clusters. This paper shows how temporal resolution of power demand profiles affects the quality of the clustering process, the consistency of cluster membership (profiles exhibiting similar behavior), and the efficiency of the clustering process. This work uses both raw data from household consumption data and synthetic profiles. The motivation for this work is to improve the clustering of electricity load profiles to help distinguish user types for tariff design and switching, fault and fraud detection, demand-side management, and energy efficiency measures. The key criterion for mining very large data sets is how little information needs to be used to get a reliable result, while maintaining privacy and security.

Segmented and Unsegmented Dialogue-Act Annotation with Statistical Dialogue Models

Dialogue systems are one of the most challenging applications of Natural Language Processing. In recent years, some statistical dialogue models have been proposed to cope with the dialogue problem. The evaluation of these models is usually performed by using them as annotation models. Many of the works on annotation use information such as the complete sequence of dialogue turns or the correct segmentation of the dialogue. This information is not usually available for dialogue systems. In this work, we propose a statistical model that uses only the information that is usually available and performs the segmentation and annotation at the same time. The results of this model reveal the great influence that the availability of a correct segmentation has in obtaining an accurate annotation of the dialogues.

Investigation of Data Communication Networks to Enable Demand Response and Dynamic Tariffs

Demand-side Response and dynamic tariffs are two examples of advanced functionality that may benefit both electricity consumers and distribution network operators. To be successful, the ICT infrastructure needs to be able to reliably cope with the data traffic. Within the wider UK context of the proposed centralised smart meter data transmission scenario, this paper demonstrates the scaling capability of two widely exploited communications protocols. Both payload (transmission overhead) and end-to-end delay times are examined.

Simultaneous Dialogue Act Segmentation and Labelling using Lexical and Syntactic Features

Segmentation of utterances and annotation as dialogue acts can be helpful for several modules of dialogue systems. In this work, we study a statistical machine learning model to perform these tasks simultaneously using lexical features and incorporating deterministic syntactic restrictions. There is a slight improvement in both segmentation and labelling due to these restrictions.