Evaluation of a User-Adapted Spoken Language Dialogue System: Measuring the Relevance of the Contextual Information Sources

We present an evaluation of a spoken language dialogue system with a module for the management of userrelated information, stored as user preferences and privileges. The flexibility of our dialogue management approach, based on Bayesian Networks (BN), together with a contextual information module, which performs different strategies for handling such information, allows us to include user information as a new level into the Context Manager hierarchy. We propose a set of objective and subjective metrics to measure the relevance of the different contextual information sources. The analysis of our evaluation scenarios shows that the relevance of the short-term information (i.e. the system status) remains pretty stable throughout the dialogue, whereas the dialogue history and the user profile (i.e. the middle-term and the long-term information, respectively) play a complementary role, evolving their usefulness as the dialogue evolves.

Mutual Information and Perplexity based Clustering of Dialogue Information for Dynamic Adaptation of Language Models

We present two approaches to cluster dialogue-based information obtained by the speech understanding module and the dialogue manager of a spoken dialogue system. The purpose is to estimate a language model related to each cluster, and use them to dynamically modify the model of the speech recognizer at each dialogue turn. In the first approach we build the cluster tree using local decisions based on a Maximum Normalized Mutual Information criterion. In the second one we take global decisions, based on the optimization of the global perplexity of the combination of the cluster-related LMs. Our experiments show a relative reduction of the word error rate of 15.17%, which helps to improve the performance of the understanding and the dialogue manager modules.

Mutual Information and Perplexity based Clustering of Dialogue Information for Dynamic Adaptation of Language Models

We present two approaches to cluster dialogue-based information obtained by the speech understanding module and the dialogue manager of a spoken dialogue system. The purpose is to estimate a language model related to each cluster, and use them to dynamically modify the model of the speech recognizer at each dialogue turn. In the first approach we build the cluster tree using local decisions based on a Maximum Normalized Mutual Information criterion. In the second one we take global decisions, based on the optimization of the global perplexity of the combination of the cluster-related LMs. Our experiments show a relative reduction of the word error rate of 15.17%, which helps to improve the performance of the understanding and the dialogue manager modules.

Estimating Adaptacion of Dialogue Partners with Different Verbal Intelligence

This work investigates to what degree speakers with different verbal intelligence may adapt to each other. The work is based on a corpus consisting of 100 descriptions of a short film (monologues), 56 discussions about the same topic (dialogues), and verbal intelligence scores of the test participants. Adaptation between two dialogue partners was measured using cross-referencing, proportion of "I", "You" and "We" words, between-subject correlation and similarity of texts. It was shown that lower verbal intelligence speakers repeated more nouns and adjectives from the other and used the same linguistic categories more often than higher verbal intelligence speakers. In dialogues between strangers, participants with higher verbal intelligence showed a greater level of adaptation.

Relating dominance of dialogue participants with their verbal intelligence scores

In this work we investigated whether there is a relationship between dominant behaviour of dialogue participants and their verbal intelligence. The analysis is based on a corpus containing 56 dialogues and verbal intelligence scores of the test persons. All the dialogues were divided into three groups: H-H is a group of dialogues between higher verbal intelligence participants, L-L is a group of dialogues between lower verbal intelligence participant and L-H is a group of all the other dialogues. The dominance scores of the dialogue partners from each group were analysed. The analysis showed that differences between dominance scores and verbal intelligence coefficients for L-L were positively correlated. Verbal intelligence scores of the test persons were compared to other features that may reflect dominant behaviour. The analysis showed that number of interruptions, long utterances, times grabbed the floor, influence diffusion model, number of agreements and several acoustic features may be related to verbal intelligence. These features were used for the automatic classification of the dialogue partners into two groups (lower and higher verbal intelligence participants); the achieved accuracy was 89.36%.

On the dynamic adaptation of language models based on dialogue information

We present an approach to adapt dynamically the language models (LMs) used by a speech recognizer that is part of a spoken dialogue system. We have developed a grammar generation strategy that automatically adapts the LMs using the semantic information that the user provides (represented as dialogue concepts), together with the information regarding the intentions of the speaker (inferred by the dialogue manager, and represented as dialogue goals). We carry out the adaptation as a linear interpolation between a background LM, and one or more of the LMs associated to the dialogue elements (concepts or goals) addressed by the user. The interpolation weights between those models are automatically estimated on each dialogue turn, using measures such as the posterior probabilities of concepts and goals, estimated as part of the inference procedure to determine the actions to be carried out. We propose two approaches to handle the LMs related to concepts and goals. Whereas in the first one we estimate a LM for each one of them, in the second one we apply several clustering strategies to group together those elements that share some common properties, and estimate a LM for each cluster. Our evaluation shows how the system can estimate a dynamic model adapted to each dialogue turn, which helps to improve the performance of the speech recognition (up to a 14.82% of relative improvement), which leads to an improvement in both the language understanding and the dialogue management tasks.

Revisión de:Sport facing cultural diversity. Integration and intercultural dialogue in Europe: analysis and practical example, de Wiliam Gasparini y Aurélie Cometti

Con motivo de la celebracio?n en 2008 del An?o Europeo del Dia?logo Intercultural, el Con- sejo de Europa promovio? una serie de encuentros y foros de debate en torno al papel de Europa en la gestio?n de la inmigracio?n, desde sus mu?ltiples dimensiones. Entre ellas, se encuentra el a?mbito deportivo, por su papel socializador como elemento cultural de dia?logo e identidad, aun- que tambie?n como espacio de confrontacio?n y discriminacio?n, que concierne tanto a participantes como espectadores, desde una perspectiva global y local. Con el objetivo de contrastar experien- cias y reflexiones a este respecto, tuvo lugar la primera conferencia europea con el nombre ?De- porte y Diversidad?, celebrada en Estrasburgo y organizada por la Agencia para la Educacio?n a trave?s del Deporte, el Consejo de Europa - a trave?s del EPAS - y la Universidad de Estrasburgo.