P. Wazinski. Generating Spatial Descriptions for Cross-Modal References. In Proceedings of the Third Conference on Applied Natural Language Processing, pages 56--63, Trento, Italy, 1992.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... relative to an illustration (e.g. the circle in the right section of the illustration) or relative to other objects in the illustration (e.g. the circle next to the triangle) Furthermore, objects may be localized relative to parts of an illustration (e.g. the corners) or object groups (cf. [69]) An important prerequisite for the generation of referring expressions in a multimedia discourse is the explicit representation of the linguistic and pictorial context. In the CUBRICON system [57] the linguistic context is represented by a focus list of entities and propositions to which the ....

P. Wazinski. Generating Spatial Descriptions for Cross-Modal References. In Proceedings of the Third Conference on Applied Natural Language Processing, pages 56--63, Trento, Italy, 1992.

....of applicability, the higher the degree of applicability. Figure 3: 2D applicability fields for the relations (a) east (b) north east (c) east north east. 3D 2D Figure 4: Partitioning of the reference object to compute interior projective relations. 2. 2 Internal Projective Relations In [ Wazinski, 1992 ] a partitioning of the reference object into three parts for each dimension 2 was proposed in order to compute internal projective relations. The regions covered by an object were used to compute its relationship to the reference object. By dividing up the reference object into three regions ....

P. Wazinski. Generating spatial descriptions for cross-modal references. In 3rd Conference on Applied Natural Language Processing, Trento, Italy, pages 56--63. Association for Computer Linguistics, 1992.

....we have investigated additional possibilities for distinguishing objects from their alternatives. We can refer not only to features of an object in a scene, but also to features of the graphical model, their interpretation and to the position of picture objects within the picture, see also [Wazinski 92] A detailed description of our discrimination algorithm can be found in [Schneiderl ochner 94] Task b) can be accomplished by correlating the visual and the textual focus, by redundantly encoding object attributes, or by explicitly informing the user about a Coref relationship. Such a ....

P. Wazinski. Generating Spatial Descriptions for Cross-Modal References. In: Proc. of the Third Conference on Applied Natural Language Processing, pp. 56--63, Trento, Italy, 1992.

....have investigated additional possibilities for distinguishing objects from their alternatives. We are able to refer not only to features of an object in a scene, but also to features of the graphical model, their interpretation, and to the position of picture objects within the picture (see also [Wazinski 92] A detailed description of our discrimination algorithm can be found in [Schneiderl ochner 94] Task (b) can be accomplished by correlating the visual with the textual focus, by redundantly encoding object attributes, or by explicitly informing the user about a Coref relationship. Such a ....

P. Wazinski. Generating Spatial Descriptions for Cross-Modal References. In: Proc. of the Third Conference on Applied Natural Language Processing, pp. 56--63, Trento, Italy, 1992.

.... attributes to be selected for referent disambiguation To discriminate objects from alternatives, the system may refer not only to features of an object in a scene, but also to features of the presentation model, their interpretation and to the position of objects within a presentation, see also [10]. ffl the determination of an appropriate media combination To discriminate an object against its alternatives through visual attributes, such as shape or surface, or its location, illustrations are used. Pointing gestures are planned to disambiguate or simplify a referring expression or to ....

.... orientation of the space which is either given by the intrinsic organization of the reference object or the location of the observer (see e.g. 11] While we assumed in our previous work on the semantics of spatial prepositions that the user s location coincides with the presenter s location (cf. [10]) we now have to distinguish whether an object is localized from the user s point of view or the Persona s point of view as the situated presenter. ffl Referring to moving target objects A still unsolved problem results from the dynamic nature of online presentations. Since image attributes may ....

P. Wazinski. Generating Spatial Descriptions for Cross-Modal References. In Proceedings of the Third Conference on Applied Natural Language Processing, pages 56--63, Trento, Italy, 1992.

No context found.

P. Wazinski. Generating spatial descriptions for cross-modal references. In ANLP-92 [43]. Also appears as DFKI Technical Memo TM-91-11, Saarbrucken, West Germany, 1991.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC