Syntax-Based Word Ordering Incorporating a Large-Scale Language Model
Yue Zhang, Graeme Blackwood, Stephen Charles Clark · 2012
A fundamental problem in text generation is word ordering. Word ordering is a computationally difficult problem, which can be constrained to some extent for particular applications, for example by using synchronous grammars for statistical machine translation. There have been some recent attempts at the unconstrained problem of generating a sentence from a multi-set of input words (Wan et al., 2009; Zhang and Clark, 2011). By using CCG and learning guided search, Zhang and Clark reported the highest scores on this task. One limitation of their system is the absence of an N-gram language model, which has been used by text generation systems to improve fluency. We take the Zhang and Clark system as the baseline, and incorporate an N-gram model by applying online large-margin training. Our system significantly improved on the baseline by 3.7 BLEU points. 1