Learning to Select, Track, and Generate for Data-to-Text

Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura


Abstract
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our proposed model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generations. Experimental results show that our proposed model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.
Anthology ID:
P19-1202
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2102–2113
Language:
URL:
https://aclanthology.org/P19-1202
DOI:
10.18653/v1/P19-1202
Bibkey:
Cite (ACL):
Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, and Hiroya Takamura. 2019. Learning to Select, Track, and Generate for Data-to-Text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2102–2113, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Learning to Select, Track, and Generate for Data-to-Text (Iso et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1202.pdf
Poster:
 P19-1202.Poster.pdf
Code
 aistairc/sports-reporter +  additional community code
Data
Rotowire-Modified