Paper: Incorporating Information Status into Generation Ranking

ACL ID P09-1092
Title Incorporating Information Status into Generation Ranking
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2009

We investigate the influence of informa- tionstatus(IS)onconstituentorderinGer- man, and integrate our findings into a log- linear surface realisation ranking model. We show that the distribution of pairs of IS categories is strongly asymmetric. More- over, each category is correlated with mor- phosyntactic features, which can be au- tomatically detected. We build a log- linear model that incorporates these asym- metries for ranking German string reali- sations from input LFG F-structures. We show that it achieves a statistically signif- icantly higher BLEU score than the base- line system without these features.