| dc.description.abstract | Current environmental information services still too often offer “raw” pollution figures in terms of tables and graphics – possibly accompanied by pointers to general background information on the nature of the pollution and its relevance to human health. However, we must be aware that, on the one hand, non-specialists are not able to assess and interpret raw figures, and, on the other hand, certain kinds of pollution (e.g., air pollution) have a highly differentiated impact on different individuals. Therefore, new generation environmental information services must make recourse to techniques of Artificial Intelligence and Computational Linguistics (such as interpretation and reasoning, natural language generation, etc.) to provide adequate information. In this paper, we focus, first of all, on the language aspect. We elaborate first on the requirements with respect to environmental information services and assess then the MARQUIS service in the light of these requirements. | de |
