tailieunhanh - Báo cáo khoa học: "Automated planning for situated natural language generation"

We present a natural language generation approach which models, exploits, and manipulates the non-linguistic context in situated communication, using techniques from AI planning. We show how to generate instructions which deliberately guide the hearer to a location that is convenient for the generation of simple referring expressions, and how to generate referring expressions with context-dependent adjectives. | Automated planning for situated natural language generation Konstantina Garoufi and Alexander Koller Cluster of Excellence Multimodal Computing and Interaction Saarland University Saarbrucken Germany garoufi koller @ Abstract We present a natural language generation approach which models exploits and manipulates the non-linguistic context in situated communication using techniques from AI planning. We show how to generate instructions which deliberately guide the hearer to a location that is convenient for the generation of simple referring expressions and how to generate referring expressions with context-dependent adjectives. We implement and evaluate our approach in the framework of the Challenge on Generating Instructions in Virtual Environments finding that it performs well even under the constraints of realtime generation. 1 Introduction The problem of situated natural language generation NLG . of generating natural language in the context of a physical or virtual environment has received increasing attention in the past few years. On the one hand this is because it is the foundation of various emerging applications including human-robot interaction and mobile navigation systems and is the focus of a current evaluation effort the Challenges on Generating Instructions in Virtual Environments GIVE Koller et al. 2010b . On the other hand situated generation comes with interesting theoretical challenges Compared to the generation of pure text the interpretation of expressions in situated communication is sensitive to the non-linguistic context and this context can change as easily as the user can move around in the environment. One interesting aspect of situated communication from an NLG perspective is that this non-linguistic context can be manipulated by the speaker. Consider the following segment of discourse between an instruction giver IG and an instruction follower IF which is adapted from the SCARE corpus Stoia et al. 2008 1 IG Walk