Concept-to-text Generation via Discriminative Reranking

Ioannis Konstas, Mirella Lapata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 approach is to reduce the tasks of content selection (“what to say”) and surface realization (“how to say”) into a common parsing problem. We define a probabilistic context-free grammar that describes the structure of the in-put (a corpus of database records and text describing some of them) and represent it compactly 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 setting. Experimental evaluation on the A TIS domain shows that our model outperforms a competitive discriminative system both using BLEU and in a judgment elicitation study.
Original languageEnglish
Title of host publicationThe 50th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics
Number of pages10
Publication statusPublished - 2012


Dive into the research topics of 'Concept-to-text Generation via Discriminative Reranking'. Together they form a unique fingerprint.

Cite this