Accurate and robust LFG-based generation for Chinese
Guo, Yuqing, Wang, Haifeng and van Genabith, Josef
(2008)
Accurate and robust LFG-based generation for Chinese.
In: INLG 08 - 5th International Natural Language Generation Conference, 12-14 June 2008, Salt Fork, Ohio, USA.
We describe three PCFG-based models for Chinese sentence realisation from Lexical-Functional Grammar (LFG) f-structures. Both the lexicalised model and the history-based model improve on the accuracy of a simple
wide-coverage PCFG model by adding lexical and contextual information to weaken inappropriate independence assumptions implicit in the PCFG models. In addition, we provide techniques for lexical smoothing and rule smoothing to increase the generation coverage. Trained on 15,663 automatically LFG fstructure annotated sentences of the Penn Chinese treebank and tested on 500 sentences randomly
selected from the treebank test set, the lexicalised model achieves a BLEU score of 0.7265 at 100% coverage, while the historybased model achieves a BLEU score of 0.7245
also at 100% coverage.