Language Generation via DAG Transduction

Yajie Ye, Weiwei Sun, Xiaojun Wan


Abstract
A DAG automaton is a formal device for manipulating graphs. By augmenting a DAG automaton with transduction rules, a DAG transducer has potential applications in fundamental NLP tasks. In this paper, we propose a novel DAG transducer to perform graph-to-program transformation. The target structure of our transducer is a program licensed by a declarative programming language rather than linguistic structures. By executing such a program, we can easily get a surface string. Our transducer is designed especially for natural language generation (NLG) from type-logical semantic graphs. Taking Elementary Dependency Structures, a format of English Resource Semantics, as input, our NLG system achieves a BLEU-4 score of 68.07. This remarkable result demonstrates the feasibility of applying a DAG transducer to resolve NLG, as well as the effectiveness of our design.
Anthology ID:
P18-1179
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1928–1937
Language:
URL:
https://aclanthology.org/P18-1179
DOI:
10.18653/v1/P18-1179
Bibkey:
Cite (ACL):
Yajie Ye, Weiwei Sun, and Xiaojun Wan. 2018. Language Generation via DAG Transduction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1928–1937, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Language Generation via DAG Transduction (Ye et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1179.pdf
Software:
 P18-1179.Software.zip
Presentation:
 P18-1179.Presentation.pdf
Video:
 https://aclanthology.org/P18-1179.mp4