Paper Abstract Writing through Editing Mechanism

Qingyun Wang, Zhihao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang +2 more
5/15/2018
cs.CLcs.AI

Official code: EagleW/Writing-editing-Network (74 stars, MIT, PyTorch, last commit 2021-05-31). 1 more implementation below.

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%.

View on arXivView PDF

Code Implementations(2)

EagleW/Writing-editing-NetworkOfficial100%
PyTorchMIT

Code for Paper Abstract Writing through Editing Mechanism

7420PythonMay 7, 20185 years agoMIT
attention-mechanismdatasetsdeep-learningend-to-end-learninggeneration+4 more
EagleW/ACL_titles_abstracts_datasetCommunity100%
MIT
193Apr 21, 20186 years agoMIT
acldatasetgenerationpaper

Similar Papers

SciLit: A Platform for Joint Scientific Literature Discovery, Summarization and Citation Generation

79% match1 repo102023

Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

79% match2026

Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training

78% match2026

Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing

78% match2025

Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation

78% match2026

PaperRobot: Incremental Draft Generation of Scientific Ideas

77% match1 repo4792019

Cite this paper

@article{wang2018paper,
  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},
  year   = {2018},
  eprint = {1805.06064},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1805.06064}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1805.06064.svg)](https://codeofpaper.com/paper/1805.06064)

Discussion