We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novel Writing-editing Network that can attend to both the title and the previously generated abstract drafts and then iteratively revise and polish the abstract. With two series of Turing tests, where the human judges are asked to distinguish the system-generated abstracts from human-written ones, our system passes Turing tests by junior domain experts at a rate up to 30% and by non-expert at a rate up to 80%.
Cite
@article{arxiv.1805.06064,
title = {Paper Abstract Writing through Editing Mechanism},
author = {Qingyun Wang and Zhihao Zhou and Lifu Huang and Spencer Whitehead and Boliang Zhang and Heng Ji and Kevin Knight},
journal= {arXiv preprint arXiv:1805.06064},
year = {2020}
}
Comments
* Equal contribution. 6 pages. Accepted by ACL 2018; The code and dataset are available at https://github.com/EagleW/Writing-editing-Network