This paper explores the use of statistical machine translation (SMT) methods for tactical natural language generation. We present results on using phrase-based SMT for learning to map meaning representations to natural language. Improved results are obtained by inverting a semantic parser that uses SMT methods to map sentences into meaning representations. Finally, we show that hybridizing these two approaches results in still more accurate generation systems. Automatic and human evaluation of generated sentences are presented across two domains and four languages.

PDF, PS

In Proceedings of Human Language Technologies: The Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT-07), pp. 172-179, Rochester, NY 2007.

@InProceedings{wong:naacl07, title={Generation by Inverting a Semantic Parser That Uses Statistical Machine Translation}, author={Yuk Wah Wong and Raymond J. Mooney}, booktitle={Proceedings of Human Language Technologies: The Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT-07)}, address={Rochester, NY}, pages={172-179}, url="http://www.cs.utexas.edu/users/ai-lab?wong:naacl07", year={2007} }