2018 AGraphtoSequenceModelforAMRtoTe

• (Song et al., 2018) ⇒ Linfeng Song, Yue Zhang, Zhiguo Wang, and Daniel Gildea. (2018). “A Graph-to-Sequence Model for AMR-to-Text Generation.” In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) Volume 1: Long Papers. DOI:10.18653/v1/P18-1150

Subject Headings: Abstract Meaning Representation, AMR-to-Text Generation Task, Natural Language Generation Task, Graph-to-Sequence Model, Graph-to-Sequence AMR-to-Text Generation System, Copy Mechanism, Character LSTM.

Notes

• Version(s) and Link(s):
  • ACL Anthology: https://www.aclweb.org/anthology/P18-1150/
  • ArXiv: https://arxiv.org/abs/1805.02473
  • DBLP: https://dblp.org/rec/html/conf/acl/GildeaWZS18
• Addtional Material
  • Conference Poster: https://www.aclweb.org/anthology/attachments/P18-1150.Poster.pdf

Cited By

• Google Scholar: ~ 57 Citations.
• Semantic Scholar: ~ 79 Citations.
• MS Academic: ~ 37 Citations.

Quotes

Abstract

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. Although being able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus facing challenges with large-graphs, which result in long sequences. We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics. On a standard benchmark, our model shows superior results to existing methods in the literature.

BibTeX

@inproceedings{2018_AGraphtoSequenceModelforAMRtoTe,
  author    = {Linfeng Song and
               Yue Zhang and
               Zhiguo Wang and
               Daniel Gildea},
  editor    = {Iryna Gurevych and
               Yusuke Miyao},
  title     = {A Graph-to-Sequence Model for AMR-to-Text Generation},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational
               Linguistics (ACL 2018)  Volume 1: Long Papers, Melbourne, Australia, July 15-20, 2018.},
  pages     = {1616--1626},
  publisher = {Association for Computational Linguistics},
  year      = {2018},
  url       = {https://www.aclweb.org/anthology/P18-1150/},
  doi       = {10.18653/v1/P18-1150},
}

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2018 AGraphtoSequenceModelforAMRtoTe	Daniel Gildea Linfeng Song Yue Zhang Zhiguo Wang			A Graph-to-Sequence Model for AMR-to-Text Generation						2018