Paper Abstract Writing through Editing Mechanism

TL;DR

This paper introduces an attentive neural sequence-to-sequence system with a novel editing mechanism that automatically generates and refines paper abstracts from titles, achieving human-like quality in Turing tests.

Contribution

The paper proposes a new Writing-editing Network that iteratively revises abstracts by attending to both titles and drafts, improving automatic abstract generation.

Findings

System passes Turing tests with 30% success from junior experts

Achieves 80% success rate in non-expert Turing tests

Demonstrates effective automatic abstract refinement

Abstract

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%.