Journal of Natural Language Processing
Online ISSN : 2185-8314
Print ISSN : 1340-7619
ISSN-L : 1340-7619
General Paper
Learning to Select, Track, and Generate for Data-to-Text
Hayate IsoYui UeharaTatsuya IshigakiHiroshi NojiEiji AramakiIchiro KobayashiYusuke MiyaoNaoaki OkazakiHiroya Takamura
Author information

2020 Volume 27 Issue 3 Pages 599-626


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 remembers which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. In addition, we also explore the effectiveness of the writer information for generation. Experimental results show that our 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.

Content from these authors
© 2020 The Association for Natural Language Processing
Previous article Next article