Natural Language Techniques for Multimodal Interaction (マルチモ-ダルインタフェ-スと要素技術論文<特集>)

スポンサーリンク

概要

• 論文の詳細を見る

• Although graphics and direct manipulation are effective interface technologies for some classes of problems, they are limited in many ways. In particular, they provide little support for identifying objects not on the screen, for specifying temporal relations, for identifying and operating on large sets of entities, and for using the context of interaction. On the other hand, these are precisely strengths of natural language. This paper describes interface techniques that integrate natural language processing and direct manipulation technologies, using each for their characteristic advantages. Specifically, the paper shows how to blend graphical user interfaces with natural language to describe obejcts and temporal relations, and how to use direct manipulation for overcoming hard natural language problems involving the establishment and use of context and pronominal reference. These techniques have been implemented in a number of systems as SRI, including Shoptalk, a prototype information and decision-support system for manufacturing, the Open Agent Architecture, a system integrating pen and voice-based modalities for controlling a set of networked software agents, and a Directory User Agent built for the X.500-based DoD Directory.

• 1994-08-25

著者

• Cohen Philip

  The Author Is With The Computer Dialogue Laboratory Artificial Intelligence Center Sri International

関連論文

• Natural Language Techniques for Multimodal Interaction (マルチモ-ダルインタフェ-スと要素技術論文)

スポンサーリンク