Dependency-Based N-Gram Models for General Purpose Sentence Realisation

摘要

We present dependency-based n-gram models for general-purpose, wide-coverage, probabilistic sentence realisation. Our method linearises unordered dependencies in input representations directly rather than via the application of grammar rules, as in traditional chart-based generators. The method is simple, efficient, and achieves competitive accuracy and complete coverage on standard English (Penn-II, 0.7440 BLEU, 0.05 sec/sent) and Chinese (CTB6, 0.7123 BLEU, 0.14 sec/sent) test data.