Revisiting the binary linearization technique for surface realization

Yevgeniy Puzikov, Claire Gardent, Ido Dagan, Iryna Gurevych

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

1 Scopus citations

Abstract

End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks. Yet, they often lack transparency of the underlying decision-making process, hindering error analysis and certain model improvements. In this work, we revisit the binary linearization approach to surface realization, which exhibits more interpretable behavior, but was falling short in terms of prediction accuracy. We show how enriching the training data to better capture word order constraints almost doubles the performance of the system. We further demonstrate that encoding both local and global prediction contexts yields another considerable performance boost. With the proposed modifications, the system which ranked low in the latest shared task on multilingual surface realization now achieves best results in five out of ten languages, while being on par with the state-of-the-art approaches in others. 1,.

Original languageEnglish
Title of host publicationINLG 2019 - 12th International Conference on Natural Language Generation, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages268-278
Number of pages11
ISBN (Electronic)9781950737949
StatePublished - 2019
Event12th International Conference on Natural Language Generation, INLG 2019 - Tokyo, Japan
Duration: 29 Oct 20191 Nov 2019

Publication series

NameINLG 2019 - 12th International Conference on Natural Language Generation, Proceedings of the Conference

Conference

Conference12th International Conference on Natural Language Generation, INLG 2019
Country/TerritoryJapan
CityTokyo
Period29/10/191/11/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'Revisiting the binary linearization technique for surface realization'. Together they form a unique fingerprint.

Cite this