We present a novel PCFG-based architecture for robust probabilistic generation based on wide-coverage LFG approximations (Cahill et al., 2004) automatically extracted from treebanks, maximising the probability of a tree given an f-structure. We evaluate our approach using stringbased evaluation. We currently achieve coverage of , a BLEU score of and string accuracy of on the Penn-II WSJ Section 23 sentences of length ≤20. grammar for generation. Belz (2005) describes a method for building statistical generation models using an automatically created generation treebank for weather forecasts. .
