Instance-Based Natural Language Generation

S. Varges, C. Mellish

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)


We investigate the use of instance-based ranking methods for surface realization in natural language generation. Our approach to instance-based natural language generation (IBNLG) employs two components: a rule system that ‘overgenerates’ a number of realization candidates from a meaning representation and an instance-based ranker that scores the candidates according to their similarity to examples taken from a training corpus. We develop an efficient search technique for identifying the optimal candidate based on a novel extension of the A* algorithm. The rule system is produced automatically from a semantically annotated fragment of the Penn Treebank II containing management succession texts. We detail the annotation scheme and grammar induction algorithm and evaluate the efficiency and output of the generator. We also discuss issues such as input coverage (completeness) and fluency that are relevant to surface generation in general.
Original languageEnglish
Pages (from-to)309-346
Number of pages37
JournalNatural Language Engineering
Issue number3
Early online date12 May 2010
Publication statusPublished - Jul 2010


Dive into the research topics of 'Instance-Based Natural Language Generation'. Together they form a unique fingerprint.

Cite this