Logo des Repositoriums

Auflistung nach Autor:in "Wanner, Leo"

1 - 7 von 7
  • Konferenzbeitrag
    Addressee-Tailored Interpretation of Air Quality Data
    (Environmental Informatics and Systems Research, 2007) Nicklaß, Daniel; Bouayad, Nadjet; Wanner, Leo
    Most of the available air quality information systems deliver only raw air quality data like pollutant concentrations. This raw data is rarely self-explanatory and is not sufficient to inform the general public on air quality. To provide comprehensive air quality information to the public the data has to be assessed and interpreted focusing on the addressees requirements. These requirements differ a lot depending on social, cultural and knowledge backgrounds or the state of health. This paper will show how this user tailored interpretation is implemented in the EU funded project MARQUIS (Multimodal AiR QUality Information Service for General Public).
  • Konferenzbeitrag
    Automatic Production of Multilingual Environmental Information
    (Environmental Informatics and Systems Research, 2007) Bohnet, Bernd; Lareau, Francois; Wanner, Leo
    Multilingual environmental information is communicated via different media. These media can be newspapers, TV, internet, WAP, SMS, etc. Each of the media has a presentation mode which fits best. Thus, it turned out that for newspapers, pictograms which indicate good, normal, and bad conditions, a map with pictograms and/or a very short text are to be preferred. In contrast, the information provided in the internet, can be very detailed and personalized and contain the latest data available at the moment the user requests the information. Furthermore, in the internet, the user can interactively select more details or change the presentation mode. For all media, the most challenging information mode is text. Since a template-based method where predefined sentences with empty slots filled at the time of generation cannot ensure coherent and cohesive text for all contextual settings, full-fledged generation techniques are needed. In this paper, we present the generation techniques as used for the production of multilingual air quality information in the framework of the MARQUIS-project.
  • Konferenzbeitrag
    Generation of Multilingual Personalized Environmental Bulletins from an OWL-based Ontology
    (EnviroInfo Dessau 2012, Part 2: Open Data and Industrial Ecological Management, 2012) Bouayad-Agha, Nadjet; Casamayor, Gerard; Mille, Simon; Rospocher, Marco; Serafini, Luciano; Moßgraber, Jürgen; Wanner, Leo
    In this paper, we tackle the problem of generation of user-oriented multilingual environmental information from ontologies in the context of a personalized environmental decision support service. We present a unified multiple layer ontology framework modeled in OWL that consists of three ontology layers: the domain ontology, the domain communication ontology, and the communication ontology. The domain ontology contains factual application-neutral concept configurations and relations. The domain communication ontology models data aggregation, qualitative interpretation of numerical data, user tailored warnings and recommendations triggered by an environmental condition given in a specific context, etc., while the communication ontology specifies knowledge needed for the tasks involved in the generation process, and is populated using a pipeline of SPARQL queries. We show how a large scale instantiation of this framework in the environmental domain serves multilingual NLG.
  • Konferenzbeitrag
    Involving the Expert in the Delivery of Environmental Information from the Web
    (Proceedings of the 27th Conference on Environmental Informatics - Informatics for Environmental Protection, Sustainable Development and Risk Management, 2013) Wanner, Leo; Bosch, Harald; Vrochidis, Stefanos; Bouayad-Agha, Nadjet; Casamayor, Gerard; Johansson, Lasse; Karppinen, Ari; Moumtzidou, Anastasia; Kompatsiaris, Ioannis; Ertl, Thomas
    Automatic provision of accurate user need- and profile-tailored environmental information is of increasing demand. However, it is a challenging task with many facets. Among them is the difficulty to compile and cast into a formal representation all the expert knowledge needed to accurately and exhaustively acquire, assess and process the data in order to be able to reliably judge their relevance to the user and to produce an adequate summary and recommendations. Studies in Human-Computer Interaction show that both the satisfaction of the users with an application and the objective performance of a service increases if the users (in particular, experts) are assigned an active role in the system. Based on this insight, we propose a largely interactive environmental information acquisition and generation framework. The PESCaDO service involves the experts in four central tasks: (i) determination of criteria for the search of environmental nodes in the web; (ii) assessment of the relevance of the identified nodes; (iii) assessment of the quality of the data provided by the nodes, and (iv) selection of the content to be communicated to the user. Quantitative evaluations and user trials show that the performance of the system is good and the satisfaction with the service is high.
  • Konferenzbeitrag
    Pollen: A Challenge for Environmental Information Services
    (Environmental Informatics and Systems Research, 2007) Karppinen, Ari; Sofiev, Makhail; Siljamo, Pilvi; Kukkonen, Jaakko; Ranta, Hanna; Linkosalo, Tapio; Jäger, Siegfried; Rasmunssen, Alix; Nicklaß, Daniel; Wanner, Leo
    Diseases due to aeroallergens, such as rhinitis and asthma, are among major causes of loss of productivity and demand for healthcare. The adverse health effects of allergens can be significantly reduced by either pre-emptive medical measures or behavioural adaptation of the outdoor activity. However, their planning requires reliable allergy-related forecasts several days ahead. Such forecasts should include the start time of pollen season, expected pollen concentration, area of exposure to a particular pollen type, timing of the peak concentrations and durations of the high season. This paper presents a current status of the Finnish Pollen Forecasting system. The system has been already used for operational pollen forecasts during spring of 2007 and also the systematic re-analysis of historical periods is ongoing.
  • Konferenzbeitrag
    Text Planning of Air Quality Information
    (Environmental Informatics and Systems Research, 2007) Bouayad-Agha, Nadjet; Wanner, Leo
    Two of the premises of the Multimodal Air Quality Information System known as MARQUIS are that (1) air quality information is dynamic (i.e., it might change every hour) and different data variations should be expressed differently, (2) people have different expertises, needs and interests about air quality and this must be reflected in the content and style in which this information is conveyed to them. The text planning module in MARQUIS achieves precisely that: it selects the content that is of relevance to a specific user from the mass of air quality information produced by the interpretation module, and arranges this information into a coherent discourse that takes into account the dynamic content and the profile of the user in the required platform. In this paper, we describe how we addressed these issues of dynamic content selection (section 2) and user modelling (section 3) in the text planning system of the MARQUIS project. These play an active role in the production of the ouput text plan (section 4) as they contrain the order of propositions and the types of discourse relations that occur between the propositions (section 5). We describe the architecture of the text planner (section 6) before giving some conclusions (section 7).
  • Konferenzbeitrag
    Towards New Generation Environmental Information Services
    (Environmental Informatics and Systems Research, 2007) Wanner, Leo
    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.