Paper: Concept-to-text Generation via Discriminative Reranking

ACL ID P12-1039
Title Concept-to-text Generation via Discriminative Reranking
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

This paper proposes a data-driven method for concept-to-text generation, the task of automatically producing textual output from non-linguistic input. A key insight in our ap- proach is to reduce the tasks of content se- lection (?what to say?) and surface realization (?how to say?) into a common parsing prob- lem. We define a probabilistic context-free grammar that describes the structure of the in- put (a corpus of database records and text de- scribing some of them) and represent it com- pactly as a weighted hypergraph. The hyper- graph structure encodes exponentially many derivations, which we rerank discriminatively using local and global features. We propose a novel decoding algorithm for finding the best scoring derivation and generating in this set- ting. Experimental evaluation on...