Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction

Yuta Hitomi, Hideaki Tamori, Naoaki Okazaki, Kentaro Inui


Abstract
This paper explores the idea of robot editors, automated proofreaders that enable journalists to improve the quality of their articles. We propose a novel neural model of multi-task learning that both generates proofread sentences and predicts the editing operations required to rewrite the source sentences and create the proofread ones. The model is trained using logs of the revisions made professional editors revising draft newspaper articles written by journalists. Experiments demonstrate the effectiveness of our multi-task learning approach and the potential value of using revision logs for this task.
Anthology ID:
I17-2074
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
436–441
Language:
URL:
https://aclanthology.org/I17-2074
DOI:
Bibkey:
Cite (ACL):
Yuta Hitomi, Hideaki Tamori, Naoaki Okazaki, and Kentaro Inui. 2017. Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 436–441, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction (Hitomi et al., IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-2074.pdf