Edinburgh Research Explorer

Structural Neural Encoders for AMR-to-text Generation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://www.aclweb.org/anthology/papers/N/N19/N19-1366/
Original languageEnglish
Title of host publicationProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics
EditorsJill Burstein, Christy Doran, Thamar Solorio
Place of PublicationMinneapolis, Minnesota
PublisherAssociation for Computational Linguistics (ACL)
Pages3649–3658
Number of pages10
Volume1
Publication statusPublished - 7 Jun 2019
Event2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics - Minneapolis, United States
Duration: 2 Jun 20197 Jun 2019
https://naacl2019.org/

Conference

Conference2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Abbreviated titleNAACL-HLT 2019
CountryUnited States
CityMinneapolis
Period2/06/197/06/19
Internet address

Abstract

AMR-to-text generation is a problem recently introduced to the NLP community, in which the goal is to generate sentences from Abstract Meaning Representation (AMR) graphs. Sequence-to-sequence models can be used to this end by converting the AMR graphs to strings. Approaching the problem while working directly with graphs requires the use of graph-to-sequence models that encode the AMR graph into a vector representation. Such encoding has been shown to be beneficial in the past, and unlike sequential encoding, it allows us to explicitly capture reentrant structures in the AMR graphs. We investigate the extent to which reentrancies (nodes with multiple parents) have an impact on AMR-to-text generation by comparing graph encoders to tree encoders, where reentrancies are not preserved. We show that improvements in the treatment of reentrancies and long-range dependencies contribute to higher overall scores for graph encoders. Our best model achieves 24.40 BLEU on LDC2015E86, outperforming the state of the art by 1.1 points and 24.54 BLEU on LDC2017T10, outperforming the state of the art by 1.24 points.

ID: 85697538