Improving grammaticality in statistical sentence generation: Introducing a dependency spanning tree algorithm with an argument satisfaction model

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

24 Citations (Scopus)

Abstract

Abstract-like text summarisation requires a means of producing novel summary sentences. In order to improve the grammaticality of the generated sentence, we model a global (sentence) level syntactic structure. We couch statistical sentence generation as a spanning tree problem in order to search for the best dependency tree spanning a set of chosen words. We also introduce a new search algorithm for this task that models argument satisfaction to improve the linguistic validity of the generated tree. We treat the allocation of modifiers to heads as a weighted bipartite graph matching (or assignment) problem, a well studied problem in graph theory. Using BLEU to measure performance on a string regeneration task, we found an improvement, illustrating the benefit of the spanning tree approach armed with an argument satisfaction model.

Original languageEnglish
Title of host publicationEACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings
EditorsKemal Oflazer, David Schlangen
Place of PublicationStroudsburg, PA
Pages852-860
Number of pages9
Publication statusPublished - 2009
Event12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009 - Athens, Greece
Duration: 30 Mar 20093 Apr 2009

Other

Other12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009
CountryGreece
CityAthens
Period30/03/093/04/09

Fingerprint Dive into the research topics of 'Improving grammaticality in statistical sentence generation: Introducing a dependency spanning tree algorithm with an argument satisfaction model'. Together they form a unique fingerprint.

Cite this