Paper Abstract Writing through Editing Mechanism

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%.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Datasets


Introduced in the Paper:

ACL Title and Abstract Dataset
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Paper generation ACL Title and Abstract Dataset Writing-editing Network ROUGE-L 20.3 # 1
METEOR 14.0 # 1

Methods