You are here

Publications

  1. A. Bianchi; Massimo Zancanaro,
    Tracking users'movements in an artistic physical space,
    Proceedings of the i³ Annual Conference, European Network for Intelligent Information Interfaces,
    1999
    , pp. 103-
    106
  2. Bernardo Magnini; A. Artale; M. Huber; Carlo Strapparava; Massimo Zancanaro,
    Efficient Natural Language Access to Databases: The TAMIC-P System,
    the 37th Annual Meeting of the Association for Computational Linguistics, [ACL'99],
    1999
  3. L. Hunsberger; Massimo Zancanaro,
    A Mechanism for Group Decision Making in Collaborative Activity,
    1999
  4. Elena Not; D. Petrelli; M. Sarini; Oliviero Stock; Carlo Strapparava; Massimo Zancanaro,
    Hypernavigation in the Physical Space: Adapting Presentations to the User and to the Situational Context,
    1998
    , pp. 33 -
    45
  5. Elena Not; Massimo Zancanaro,
    Content Adaptation for Audio-based Hypertexts in Physical Environments,
    Proceedings of the Second Workshop on Adaptive Hypertext and Hypermedia (held in conjunction with the Ninth ACM Conference on Hypertext and Hypermedia - HYPERTEXT ’98),
    1998
  6. Roberto Brunelli; Ornella Mich,
    VIDEO: Video and Image Data Exploration and Organization,
    Workshop on Image and Video Content-based Retrieval,
    no publisher,
    1998
    , pp. 119-
    126
    , (Workshop on Image and Video Content-based Retrieval,
    02/1998)
  7. Elena Not; Massimo Zancanaro,
    The Texture Resolution Module: a General-Purpose Customizable Anaphora Resolutor,
    According to the definition provided by Systemic Functional Linguistics, the texture of a text is related to the listener`s perception of coherence and is manifested by a set of semantic relations, called cohesive ties, holding between text chunks. Coreference is one of the most studied ties, but many other relations deserve attention. This paper presents a module, called `Texture Resolution Module` (TRM), which attempts to identify the relevant anaphoric semantic relations linking the current sentence to the preceding ones. TRM tracks the entities mentioned as long as they are introduced in the discourse and uses a set of declarative rules to guess which ties hold for a certain referring expression. The architecture designed for TRM highly emphasizes system modularity and resource reuse: new rules can easily be added to deal with new linguistic phenomena encountered in the domain, allowing for an incremental tuning of the module. Rules can be written independently to one another, assigning to each of them a confidence score that expresses the certainty of the guess made by the rule. Some of the rules have general validity and can be applied across different domains,
    1998
  8. Elena Not; Massimo Zancanaro,
    TRM - Texture Resolution Module – User´s and Programmer´s Manual,
    The Texture Resolution Module (TRM) has been developed within the European Project FACILE (LE 2440). The module attempts to identify relevant semantic relations that link the current sentence to the preceding ones, by analysing the referring expressions that appear in the text. It suggests how mentioned entities are related to each other by exploiting knowledge about discourse phenomena. Since from the beginning of the TRM design and implementation, a specific application setting -that of information extraction from financial news- and an underlying text analysis environment -the Deep Analyser developed for the FACILE project- were available to help identify and specify the requirements of the texture resolution task. However, during the overall phases of design and implementation of the module we pursued in any case the goals of generality, modularity and flexibility for the new component. This justifies the TRM rule-based approach and the clear separation of the different resolutions steps, in order to simplify the tuning and maintainance of the system as well as the porting to different domains or languages. TRM can work either with full and partial analysis of the text. Therefore, the module could be integrated also in full text understanding systems: this integration -provided that the API to the underlying system does not change- would simply require an accurate tuning of the resolution rules, given that TRM can rely on more complete parsing information. Some parts of TRM can be easily customized to different theories for discourse modelling: the object oriented methodology adopted during the design and implentation of the module allows for an easy plug-in of theory dependent parts, therefore providing a flexible testing environment for alternative solutions. Furthermore, the portion of TRM in charge for the recording and maintainance of the discourse attentional state could also stand independently and could be exported alone for other uses (for example, it could be adapted to model the attentional state evolution in a dialogue system and used also with different resolution engines). In this manual, the TRM user will found a description of the approach that has been adopted to model the texture resolution process and information on how to use the module, as it is, within the FACILE information extraction environment. Appendices A and B contain a description of the functions a TRM user should know. Appendix C, instead, is intentended for a TRM programmer who wishes to port TRM to a new domain, language, or different underlying text analysis environment. The examples reported in this manual are taken from the FACILE text corpus or from real executions of TRM,
    1998
  9. Massimo Zancanaro; Oliviero Stock; Carlo Strapparava,
    Multimodal Dialogue for Information Access: Exploiting Cohesion' (vecchio titolo: Cohesion in Multimodal Interaction for Information Access,
    1997
    , pp. 439 -
    464
  10. Oliviero Stock; Carlo Strapparava; Massimo Zancanaro,
    Multimodal Information Exploration,
    1997
    , pp. 275 -
    293

Pages