Stage-wise fine-tuning for graph-to-text generation

Qingyun Wang, Semih Yavuz, Xi Victoria Lin, Heng Ji, Nazneen Fatema Rajani

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

Abstract

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the interdependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.

Original languageEnglish (US)
Title of host publicationACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Student Research Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages16-22
Number of pages7
ISBN (Electronic)9781954085558
StatePublished - 2021
Event2021 Student Research Workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 - Virtual, Online
Duration: Aug 5 2021Aug 6 2021

Publication series

NameACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Student Research Workshop

Conference

Conference2021 Student Research Workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
CityVirtual, Online
Period8/5/218/6/21

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Stage-wise fine-tuning for graph-to-text generation'. Together they form a unique fingerprint.

Cite this