Auflistung nach:
Auflistung Künstliche Intelligenz 30(1) - Februar 2016 nach Erscheinungsdatum
1 - 10 von 19
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelInformation Density and Linguistic Encoding (IDeaL)(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Crocker, Matthew W.; Demberg, Vera; Teich, ElkeWe introduce IDeaL (Information Density and Linguistic Encoding), a collaborative research center that investigates the hypothesis that language use may be driven by the optimal use of the communication channel. From the point of view of linguistics, our approach promises to shed light on selected aspects of language variation that are hitherto not sufficiently explained. Applications of our research can be envisaged in various areas of natural language processing and AI, including machine translation, text generation, speech synthesis and multimodal interfaces.
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016)
- ZeitschriftenartikelMultimodal Behavior Analytics for Interactive Technologies(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Scherer, Stefan
- ZeitschriftenartikelEnglisch or/oder Deutsch?(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Timpf, Sabine
- ZeitschriftenartikelCompanion-Technology: An Overview(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Biundo, Susanne; Höller, Daniel; Schattenberg, Bernd; Bercher, PascalCompanion-technology is an emerging field of cross-disciplinary research. It aims at developing technical systems that appear as “Companions” to their users. They serve as co-operative agents assisting in particular tasks or, in a more general sense, even give companionship to humans. Overall, Companion-technology enables technical systems to smartly adapt their services to individual users’ current needs, their requests, situation, and emotion. We give an introduction to the field, discuss the most relevant application areas that will benefit from its developments, and review the related research projects.
- ZeitschriftenartikelSearch Challenges in Natural Language Generation with Complex Optimization Objectives(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Demberg, Vera; Hoffmann, Jörg; Howcroft, David M.; Klakow, Dietrich; Torralba, ÁlvaroAutomatic natural language generation (NLG) is a difficult problem already when merely trying to come up with natural-sounding utterances. Ubiquituous applications, in particular companion technologies, pose the additional challenge of flexible adaptation to a user or a situation. This requires optimizing complex objectives such as information density, in combinatorial search spaces described using declarative input languages. We believe that AI search and planning is a natural match for these problems, and could substantially contribute to solving them effectively. We illustrate this using a concrete example NLG framework, give a summary of the relevant optimization objectives, and provide an initial list of research challenges.
- ZeitschriftenartikelCognitive Space and Spatial Cognition: The SFB/TR 8 Spatial Cognition(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Ragni, Marco; Barkowsky, Thomas; Nebel, Bernhard; Freksa, ChristianSpace and time are two of the most fundamental categories any human, animal, or other cognitive agent such as an autonomous robot has to deal with. They need to perceive their environments, make sense of their perceptions, and make interactions as embodied entities with other agents and their environment. The theoretical foundations and practical implications have been investigated from a cognitive perspective (i.e., from an information processing point of view) within the Sonderforschungsbereich/Transregio SFB/TR 8 Spatial Cognition (http://www.sfbtr8.spatial-cognition.de) over the past 12 years jointly by the Universities of Bremen and Freiburg. The research covered fundamental questions: what are the specific requirements of reasoning about space and time, for acting in space, and for any form of interaction including communication in spatio-temporal domains? It has been a success story in all research lines from foundational research to applications of spatial cognition in robotics, interaction and communication. The SFB/TR 8 actually shaped a new research field by extending a previous subfield of cognitive science with its own interdisciplinary techniques.
- ZeitschriftenartikelModeling Grounding for Interactive Social Companions(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Mehlmann, Gregor; Janowski, Kathrin; André, ElisabethGrounding is an important process that underlies all human interaction. Hence, it is also crucial for social companions to interact naturally. Maintaining the common ground requires domain knowledge but has also numerous social aspects, such as attention, engagement and empathy. Integrating these aspects and their interplay with the dialog management in a computational interaction model is a complex task. We present a modeling approach overcoming this challenge and illustrate it based on some social companion applications.
- ZeitschriftenartikelSearch Complexities for HTN Planning(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Alford, Ronald
- ZeitschriftenartikelHybrid Planning and Scheduling(KI - Künstliche Intelligenz: Vol. 30, No. 1, 2016) Schattenberg, Bernd