论文信息 - A Flexible Pragmatics-Driven Language Generator for Animated Agents

A Flexible Pragmatics-Driven Language Generator for Animated Agents

This paper describes the NECA MNLG; a fully implemented Multimodal Natural Language Generation module. The MNLG is deployed as part of the NECA system which generates dialogues between animated agents. The generation module supports the seamless integration of full grammar rules, templates and canned text. The generator takes input which allows for the specification of syntactic, semantic and pragmatic constraints on the output.

Paul Piwek | P. Piwek

[1] Emiel Krahmer,et al. Efficient context-sensitive generation of referring expressions , 2002 .

[2] Brigitte Krenn,et al. What can we learn from users of avatars in net environments , 2002 .

[3] Brigitte Krenn,et al. RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA , 2004, ArXiv.

[4] Chris Mellish,et al. Approximate Generation from Non-Hierarchical Representations , 1996, INLG.

[5] Matthew Stone,et al. Sentence Planning as Description Using Tree Adjoining Grammar , 1997, ACL.

[6] Ehud Reiter,et al. Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[7] Tomek Strzalkowski,et al. From Discourse to Logic , 1991 .

[8] Ehud Reiter. Shallow vs. Deep Techniques for Handling Linguistic Constraints and Optimisations , 1999 .