Evaluating automatic extraction of rules for sentence plan construction

The freely available SPaRKy sentence planner uses hand-written weighted rules for sentence plan construction, and a user-or domain-specific second-stage ranker for sentence plan selection. However, coming up with sentence plan construction rules for a new domain can be difficult. In this paper, we automatically extract sentence plan construction rules from the RST-DT corpus. In our rules, we use only domain-independent features that are available to a sentence planner at runtime. We evaluate these rules, and outline ways in which they can be used for sentence planning. We have integrated them into a revised version of SPaRKy.