A Flexible Pragmatics-Driven Language Generator for Animated Agents

A Flexible Pragmatics-driven Language Generator for Animated Agents Paul Piwek ITRI — Information Technology Research Institute University of Brighton Paul.Piwek@itri.bton.ac.uk Abstract This paper describes the NECA MNLG; a fully implemented Multimodal Natu- ral Language Generation module. The MNLG is deployed as part of the NECA system which generates dialogues be- tween animated agents. The genera- tion module supports the seamless inte- gration of full grammar rules, templates and canned text. The generator takes in- put which allows for the specification of syntactic, semantic and pragmatic con- straints on the output. 1 Introduction This paper introduces the NECA MNLG; a Multi- modal Natural Language Generator. It has been developed in the context of the NECA system) The NECA system generates dialogue scripts for animated characters. A first demonstrator in the car sales domain (ESHowRoom) has been imple- mented. It allows a user to browse a database of cars, select a car, select two characters and their attributes, and subsequently view an automatically generated film of a dialogue about the selected car. The demonstrator takes the following input: • A database with facts about the selected car (maximum speed, horse power, etc.). • A database which correlates facts with value judge- ments. 1 NECA stands for 'Net Environment for Embodied Emo- tional Conversational Agents' and is an EU-IST project. • Information about the characters: 1. Personality traits such as extroversion and agreeableness. 2. Personal preferences concerning cars (e.g., a preference for safe cars). 3. Role of the character (seller or customer). This input is processed in a pipeline that consists of the following modules in this order: • A DIALOGUE PLANNER, which produces an abstract description of the dialogue (the dialogue plan). • A MULTI-MODAL NATURAL LANGUAGE GENERA- TOR which specifies linguistic and non-linguistic real- izations for the dialogue acts in the dialogue plan. • A SPEECH SYNTHESIS MODULE, which adds infor- mation for Speech. • A GESTURE ASSIGNMENT MODULE, which controls the temporal coordination of gestures and speech. • A PLAYER, which plays the animated characters and the corresponding speech sound files. Each step in the pipeline adds more concrete in- formation to the dialogue plan/script until finally a player can render it. A single XML compliant representation language, called RRL, has been de- veloped for representing the Dialogue Script at its various stages of completion (Piwek et al., 2002). In this paper, we describe the requirements for the NECA MNLG, how these have been translated into design solutions and finally some of aspects of the implementation. 2 Requirements The requirements in this section derive primarly from the use case of the NECA system. We do, however, try to indicate in what respects these re- quirements transcend this specific application and are desirable for generation systems in general. 151 REQUIREMENT 1: The linguistic resources of the gen- erator should support seamless integration of canned text, templates and full grammar rules. In the NECA system, the dialogue planner creates a dialogue plan consisting of (1) a description of the participants, (2) a …

Content truncated to 500 words