Paper: Accurate and Robust LFG-Based Generation for Chinese

ACL ID W08-1112
Title Accurate and Robust LFG-Based Generation for Chinese
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2008
Authors

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 inap- propriate independence assumptions implicit in the PCFG models. In addition, we pro- vide techniques for lexical smoothing and rule smoothing to increase the generation cover- age. Trained on 15,663 automatically LFG f- structure annotated sentences of the Penn Chi- nese treebank and tested on 500 sentences ran- domly selected from the treebank test set, the lexicalised model achieves a BLEU score of 0.7265 at 100% coverage, while the history- based model achieves a BLEU score of 0.7245 also at 1...