| Horswill, I. (1995). Integrating vision and natural language without central models. In Proceedings of the AAAI Fall Symposium on Embodied Language and Action, Cambridge. |
....of speech and visual data are two of the most difficult problems in Artificial Intelligence(AI) So the first idea may be that combining two of the most difficult problems in AI results in an even more difficult problem. However, some researchers [Bischoff and Graefe, 1999, Srihari, 1994, Horswill, 1995] argued that a good solution of the combination problem should reduce the complexity of the separated tasks. In practice, the use of multiple modalities is meaningful in many different contexts, so the related research areas are highly diverse and interdisciplinary. In the robotics literature, ....
Horswill, I. (1995). Integrating vision and natural language without central models. In Proceedings of the AAAI Fall Symposium on Embodied Language and Action, Cambridge.
....with a mobile robot (Torrance 1994) and Hashimoto et al. developed humanoid robots with dialogue capability (Hashimoto et al. 1997) Shibata et al. Shibata et al. 1997) resolve ambiguities in route descriptions in natural language, using spatial relationships between the elements of the route. Horswill(Horswill 1995) integrated a simplified SHRDLU like language processing system with a real time vision system. These modern systems use language as a tool for interacting with the robot but are not particularly concerned with the principled application of linguistic or discourse theories. Takeda et al. Takeda ....
Horswill, I. 1995. Integrating Vision and Natural Language without Central Models, In Proceedings of the AAAI Fall Symposium on Embodied Language and Action, Cambridge.
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