Shallow Dialogue Processing Using Machine Learning Algorithms (or not)

This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staff or business meetings. Four components of the model are defined, and several machine learning techniques are used to extract features from dialogue transcripts: maximum entropy classifiers for dialogue acts, latent semantic analysis for topic segmentation, or decision tree classifiers for discourse markers. A rule-based approach is proposed for solving cross-modal references to meeting documents. The methods are trained and evaluated thanks to a common data set and annotation format. The integration of the components into an automated shallow dialogue parser opens the way to multimodal meeting processing and retrieval applications.

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.

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.

Made in God's Image! - What Does It Mean? Science and Religion in Conversation

How can we best interpret the traditional Christian affirmation that human beings are made in God's image in light of contact and dialogue between religion and science? And what, if any, are the environmental implications of this conversation between the two?

Normative Practical Reasoning via Argumentation and Dialogue

Postprint

Equal Partners in Dialogue? Participation Equality in a Transnational Deliberative Poll (Europolis)

By gathering a representative sample of citizens from all 27 EU Member States, the deliberative poll Europolis created the opportunity for the inclusion of a wide variety of European voices. Taking up claims of difference democrats who argue that informal hurdles to participation can endure even after individuals gain formal access to the floor, this article argues for an extended approach to evaluate equality in deliberative minipublics. Specifically, it assesses whether participants contributed in roughly equal measures to the discussion and whether their discussion partners considered their contributions on equal merits. In doing so, the article adds to the small but growing literature on deliberation that expresses reservations about taking the willingness to engage with others' claims for granted. In order to account for the intrinsically relational aspect of interpersonal communication, measures of social network analysis are introduced as possible tools to evaluate participation equality in deliberative encounters.

De la science du droit en Allemagne depuis 1815 /

Extrait de la "Revue étrangère et française de législation, de jurisprudence et d'économie politique", 1841.

Du mouvement et de la résistance en politique /

Mode of access: Internet.

Cours d'instruction civique : simples notions de droit public, de droit privé droit privé et d'economie politique ... /

Mode of access: Internet.

Le ministre d'estat : avec le veritable usage de la politique moderne /

Fictitious imprint.

Fragmens de politique et d'histoire.

Goldsmiths'-Kress no. 15076.

La Republique de Platon, ou Dialogue sur la justice : divisé en dix livres.

Vol. 1: ciij, [1], 261, [3] p. (the last 3 pages blank); v. 2: [4], 406, [2] p. (the last 2 pages blank).

Essais de philosophie, de politique et de littérature /

v. 1-2. Philosophie -- v. 3. Politique -- v. 4. Littérature.