Smart Word Suggestions for Writing Assistance
Chenshuo Wang, Shaoguang Mao, Tao Ge, Wenshan Wu, Xun Wang, Yan Xia, Jonathan Tien, Dongyan Zhao
Abstract
Enhancing word usage is a desired feature for writing assistance. To further advance research in this area, this paper introduces “Smart Word Suggestions” (SWS) task and benchmark. Unlike other works, SWS emphasizes end-to-end evaluation and presents a more realistic writing assistance scenario. This task involves identifying words or phrases that require improvement and providing substitution suggestions. The benchmark includes human-labeled data for testing, a large distantly supervised dataset for training, and the framework for evaluation. The test data includes 1,000 sentences written by English learners, accompanied by over 16,000 substitution suggestions annotated by 10 native speakers. The training dataset comprises over 3.7 million sentences and 12.7 million suggestions generated through rules. Our experiments with seven baselines demonstrate that SWS is a challenging task. Based on experimental analysis, we suggest potential directions for future research on SWS. The dataset and related codes will be available for research purposes.
BibTeX
@inproceedings{wang-etal-2023-smart,
title = "Smart Word Suggestions for Writing Assistance",
author = "Wang, Chenshuo and
Mao, Shaoguang and
Ge, Tao and
Wu, Wenshan and
Wang, Xun and
Xia, Yan and
Tien, Jonathan and
Zhao, Dongyan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.712/",
doi = "10.18653/v1/2023.findings-acl.712",
pages = "11212--11225"
}