Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model

Paper: Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model

ACL ID	E09-1097
Title	Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model
Venue	Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session	Main Conference
Year	2009
Authors	Stephen Wan (Macquarie University, Sydney Australia; CSIRO, Sydney Australia) Mark Dras (Macquarie University, Sydney Australia) Robert Dale (CSIRO, Sydney Australia) Cécile L. Paris

Abstract-like text summarisation requires a means of producing novel summary sen- tences. In order to improve the grammati- cality of the generated sentence, we model a global (sentence) level syntactic struc- ture. We couch statistical sentence genera- tion as a spanning tree problem in order to search for the best dependency tree span- ning a set of chosen words. We also intro- duce a new search algorithm for this task that models argument satisfaction to im- prove the linguistic validity of the gener- ated tree. We treat the allocation of modi- fiers 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 improve- ment, illustrating the benefit of the spa...

Click Here to View the Paper In XML Format