As dialog systems are getting more and more ubiquitous, there is an increasing number of application domains for natural language generation, and generation objectives are getting more diverse (e.g., generating information-ally dense vs. less complex utterances, as a function of target user and usage situation). Flexible generation is difficult and labourintensive with traditional template-based generation systems, while fully data-driven approaches may lead to less grammatical output, particularly if the measures used for generation objectives are correlated with measures of grammaticality. We here explore the combination of a data-driven approach with two very simple automatic grammar induction methods, basing its implementation on OpenCCG.
CITATION STYLE
Fischer, A., Demberg, V., & Klakow, D. (2015). Towards flexible, small-domain surface generation: Combining data-driven and grammatical approaches. In ENLG 2015 - Proceedings of the 15th European Workshop on Natural Language Generation (pp. 105–108). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w15-4718
Mendeley helps you to discover research relevant for your work.