Data-driven sentence generation with non-isomorphic trees

Ballesteros, Miguel; Bohnet, Bernd; Mille, Simon; Wanner, Leo

Data-driven sentence generation with non-isomorphic trees

Citation

Ballesteros M, Bohnet B, Mille S, Wanner L. Data-driven sentence generation with non-isomorphic trees. In: Mihalcea R, Chai J, Anoop S, editors. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies; 2015 May 31 - June 5; Denver, Colorado, United States. [Stroudsburg]: ACL; 2015. p. 387-97.

Abstract

Abstract structures from which the generation naturally starts often do not contain any functional nodes, while surface-syntactic structures or a chain of tokens in a linearized tree contain all of them. Therefore, data-driven linguistic generation needs to be able to cope with the projection between non-isomorphic structures that differ in their topology and number of nodes. So far, such a projection has been a challenge in data-driven generation/nand was largely avoided. We present a fully stochastic generator that is able to cope with projection between non-isomorphic structures. The generator, which starts from PropBank-like structures, consists of a cascade/nof SVM-classifier based submodules that map in a series of transitions the input structures onto sentences. The generator has been evaluated for English on the Penn-Treebank and for Spanish on the multi-layered AncoraUPF corpus.

Description

Comunicació presentada a la 2015 Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL HLT 2015), celebrada del 31 de maig al 5 de juny 2015 a Denver (CO, EUA).